To see the other types of publications on this topic, follow the link: Thai printed text recognition.
Journal articles on the topic 'Thai printed text recognition'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Thai printed text recognition.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Mookdarsanit, Lawankorn, and Pakpoom Mookdarsanit. "Combating the hate speech in Thai textual memes." Indonesian Journal of Electrical Engineering and Computer Science 21, no. 3 (2021): 1493–502. https://doi.org/10.11591/ijeecs.v21.i3.pp1493-1502.
Full textAbstract:
Thai textual memes have been popular in social media, as a form of image information summarization. Unfortunately, many memes contain some hateful content that easily causes the controversy in Thailand. For global protection, the hateful memes challengeis also provided by Facebook AI to enable researchers to compete their algorithms for combating the hate speech on memes as one of NeurIPS’20 competitions. As well as in Thailand, this paper introduces the Thai textual meme detection as a new research problem in Thai natural language processing (Thai-NLP) that is the settlement of transmission linkage between scene text localization, Thai optical recognition (Thai-OCR) and language understanding. From the results, both regular and irregular text position can be localized by one-stage detection pipeline. More scene text can be augmented by different resolution and rotation. The accuracy of Thai-OCR using convolutional neural network (CNN) can be improved by recurrent neural network (RNN). Since misspelling Thai words are frequently used in social, this paper categorizes them as synonyms to train on multi-task pre-trained language model.
2
Lin, Cheng-Jian, Yu-Cheng Liu, and Chin-Ling Lee. "Automatic Receipt Recognition System Based on Artificial Intelligence Technology." Applied Sciences 12, no. 2 (2022): 853. http://dx.doi.org/10.3390/app12020853.
Full textAbstract:
In this study, an automatic receipt recognition system (ARRS) is developed. First, a receipt is scanned for conversion into a high-resolution image. Receipt characters are automatically placed into two categories according to the receipt characteristics: printed and handwritten characters. Images of receipts with these characters are preprocessed separately. For handwritten characters, template matching and the fixed features of the receipts are used for text positioning, and projection is applied for character segmentation. Finally, a convolutional neural network is used for character recognition. For printed characters, a modified You Only Look Once (version 4) model (YOLOv4-s) executes precise text positioning and character recognition. The proposed YOLOv4-s model reduces downsampling, thereby enhancing small-object recognition. Finally, the system produces recognition results in a tax declaration format, which can upload to a tax declaration system. Experimental results revealed that the recognition accuracy of the proposed system was 80.93% for handwritten characters. Moreover, the YOLOv4-s model had a 99.39% accuracy rate for printed characters; only 33 characters were misjudged. The recognition accuracy of the YOLOv4-s model was higher than that of the traditional YOLOv4 model by 20.57%. Therefore, the proposed ARRS can considerably improve the efficiency of tax declaration, reduce labor costs, and simplify operating procedures.
3
Deepika Kongara. "A Framework for Character Recognition APP Using ML Kit." Journal of Information Systems Engineering and Management 10, no. 41s (2025): 940–52. https://doi.org/10.52783/jisem.v10i41s.8021.
Full textAbstract:
Character recognition applications are pivotal in enabling real-time translation and digitization of printed and handwritten text. Text recognition can be implemented using a variety of technologies found in the field of software development, but here for Android mobile development, the ML Kit is used. The goal is to create an Android character recognition app, especially for Devanagari script (with language converter software included as a feature), using the ML kit without Firebase that will make recognizing, learning, and language translation easier and will promote stress-free communication. Using ML Kit is a boon for developers without extensive knowledge of machine learning, as it simplifies the integration of complex ML features and saves significant time in learning and implementation. This app has the ability to recognise in real time as well as storage-based recognition on both handwritten and printed scripts. The app incorporates real-time recognition and offline translation features, supporting recognition in six languages and translating text into 59 languages. This app will perform more effectively than other existing programmes since it will use optimized code for the translation and recognition process. The major goal is to have the software operate even when it is not connected to the internet.
4
Et.al, Siddharth Salar. "Automate Identification and Recognition of Handwritten Text from an Image." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 3 (2021): 3800–3808. http://dx.doi.org/10.17762/turcomat.v12i3.1666.
Full textAbstract:
Handwritten text acknowledgment is yet an open examination issue in the area of Optical Character Recognition (OCR). This paper proposes a productive methodology towards the advancement of handwritten text acknowledgment frameworks. The primary goal of this task is to create AI calculation to empower element and information extraction from records with manually written explanations, with an, expect to distinguish transcribed words on a picture.
 The main aim of this project is to extract text, this text can be handwritten text or it can machine printed text and convert it into computer understandable or wNe can say computer editable format. To implement thais project we have used PyTesseract which is an open-sourcemOCR engine used to recognize handwritten text and OpenCV a library in python used to solve computer vision problems. So the input image is executed in various steps, first there is pre-processing of an image then there is text localization after that there is character segmentation and character recognition and finally we have post-processing of image. Further image processingalgorithms can also be used to deal with the multiple characters input in a single image, tilt image, or rotated image. The prepared framework gives a normal precision of more than 95 % with the concealed test picture.
5
Miyao, Hidetoshi, Yasuaki Nakano, Atsuhiko Tani, Hirosato Tabaru, and Toshihiro Hananoi. "Printed Japanese Character Recognition Using Multiple Commercial OCRs." Journal of Advanced Computational Intelligence and Intelligent Informatics 8, no. 2 (2004): 200–207. http://dx.doi.org/10.20965/jaciii.2004.p0200.
Full textAbstract:
This paper proposes two algorithms for maintaining matching between lines and characters in text documents output by multiple commercial optical character readers (OCRs). (1) a line matching algorithm using dynamic programming (DP) matching and (2) a character matching algorithm using character string division and standard character strings. The paper proposes a method that introduces majority logic and reject processing in character recognition. To demonstrate the feasibility of the method, we conducted experiments on line matching recognition for 127 document images using five commercial OCRs. Results demonstrated that the method extracted character areas with more accuracy than a single OCR along with appropriate line matching. The proposed method enhanced recognition from 97.61% provided by a single OCR to 98.83% in experiments using the character matching algorithm and character recognition. This method is expected to be highly useful in correcting locations at which unwanted lines or characters occur or required lines or characters disappear.
6
Sable, Prof A. V., Avantika Patil, Mayur Rathi, and Ayush Shriwas. "Interpreting Doctor Notes using Handwriting Recognition." International Journal for Research in Applied Science and Engineering Technology 12, no. 4 (2024): 3118–23. http://dx.doi.org/10.22214/ijraset.2024.60663.
Full textAbstract:
Abstract: Handwriting recognition of medical prescriptions has been a challenging problem over the recent years with constant research in providing possible accurate solutions. Indecipherable handwritten prescription and inefficiency of Pharmacist to understand the medical prescription can lead to serious and harmful effect to the patients. Even in the recognition of handwriting, mainly doctors notes, they are very difficult for everyone to understand and it takes time for a person to analyse it. So, this idea mainly focused on interpreting doctor’s notes using handwritten recognition and deep learning techniques. The handwritten or printed document pictures are transformed into their electronic counterparts using an optical character recognition (OCR) system. Due to individuals' inconsistent writing styles, dealing with handwritten texts is significantly more difficult than dealing with printed ones. Handwritten text recognition could be done by Image processing, Machine Learning or Deep Learning Techniques. Out of these Deep Learning remains to be the most popular and prominent. Some of the Deep Learning techniques includes Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs). This gives a review of the various recognition methodologies used for interpreting handwritten texts. It includes the most important algorithms that could be used for detecting the handwritten word/text/character by using various approaches for the recognition process. In the end we are thus comparing the accuracies provided by these systems.
7
BS, Ujwala, and Ujwala K. "A REVIEW PAPER ON OCR USING CONVOLUTIONAL NEURAL NETWORKS." International Journal of Engineering Applied Sciences and Technology 7, no. 7 (2022): 102–6. http://dx.doi.org/10.33564/ijeast.2022.v07i07.018.
Full textAbstract:
this paper presents a literature review on OCR for different languages using convolutional neural network techniques. Optical Character Recognition is the process of converting an input text image into a machine encoded format. Different methods are used in OCR for different languages. The main steps of optical character recognition are pre-processing, segmentation and recognition. Recognizing handwritten text is harder than recognizing printed text. Convolutional Neural Network has shown remarkable improvement in recognizing characters of different languages. The novelty of the OCR is its robustness to image quality, image contrast, font style and font size. Common machine learning methods usually apply a combination of feature extractor and trainable classifier. The use of CNN leads to significant improvements across different machine-learning classification algorithms.
8
Shafique, A. Awan, Nawaz Hakro Dil, Lashari Intzar, H. Jalbani Akhtar, and Hameed Maryam. "A Complete Off-line Sindhi Handwritten Text Recognition: A Survey." International Journal of Management Sciences and Business Research 6, no. 4 (2017): 131–38. https://doi.org/10.5281/zenodo.3469359.
Full textAbstract:
Artificial Intelligence is finding ways to make machines more intelligent and work like human being. Image processing, Natural language processing and Optical Character Recognition (OCR) are the active fields of computer vision, where the computers are made more versatile to understand, read and write natural human languages spoken around the word. Optical Characters Recognition (OCR) and Intelligent Characters Recognition (ICR) differ in recognizing printed and handwritten characters respectively. Intelligent Characters Recognition (ICR) is an active field in which handwritten characters are converted into editable text from the image, and remain the point of interest for researchers around the world. Many of the languages of the world possess their Intelligent Characters Recognition (ICR) or their ICR systems are in process. Latin scripts possess their ICR and are near to perfect whereas Arabic script and its adopting languages need more attention for the development of ICR systems. Sindhi language is a language having rich background and culture of more than 5000 years still lacks the ICR system. As there is no any handwritten recognition system for Sindhi Language, so there is no handwritten database is available for testing and training. Enhanced segmentation and feature extraction algorithms are needed which can fully suit with Sindhi script. An integrated handwritten system will be the output of this system in which handwritten text is recognized and editable text will be available for the further processing.
9
Shafiro, Valeriy, Daniel Fogerty, Kimberly Smith, and Stanley Sheft. "Perceptual Organization of Interrupted Speech and Text." Journal of Speech, Language, and Hearing Research 61, no. 10 (2018): 2578–88. http://dx.doi.org/10.1044/2018_jslhr-h-17-0477.
Full textAbstract:
Purpose Visual recognition of interrupted text may predict speech intelligibility under adverse listening conditions. This study investigated the nature of the linguistic information and perceptual processes underlying this relationship. Method To directly compare the perceptual organization of interrupted speech and text, we examined the recognition of spoken and printed sentences interrupted at different rates in 14 adults with normal hearing. The interruption method approximated deletion and retention of rate-specific linguistic information (0.5–64 Hz) in speech by substituting either white space or silent intervals for text or speech in the original sentences. Results A similar U-shaped pattern of cross-rate variation in performance was observed in both modalities, with minima at 2 Hz. However, at the highest and lowest interruption rates, recognition accuracy was greater for text than speech, whereas the reverse was observed at middle rates. An analysis of word duration and the frequency of word sampling across interruption rates suggested that the location of the function minima was influenced by perceptual reconstruction of whole words. Overall, the findings indicate a high degree of similarity in the perceptual organization of interrupted speech and text. Conclusion The observed rate-specific variation in the perception of speech and text may potentially affect the degree to which recognition accuracy in one modality is predictive of the other.
10
Rakesh T M. "Hybrid CNN-BiLSTM with CTC for Enhanced Text Recognition in Complex Background Images." Journal of Information Systems Engineering and Management 10, no. 50s (2025): 89–102. https://doi.org/10.52783/jisem.v10i50s.10121.
Full textAbstract:
The problems that robotic reading of text faces such as poor light, messy backgrounds and blurriness, resemble those found in human vision. Addressing these concerns results in applications such as document digitization and assistive technology. The study introduces a way to help identify text by joining CNNs, BiLSTMs and a CTC decoder. This CNN part is able to detect spatial features of text even from crowded images, while BiLSTMs help recognize text printed in different styles, turned over and in varying sizes. Because the CTC decoder does not require separate segmentation of characters, the text is aligned accurately. On ICDAR 2015 and SVT datasets, the approach demonstrated by this study shows very high accuracy of 98.50% and 98.80%. Quality measurements reveal high accuracy of the model on motion-blurred (no more than 15 pixels), partially occluded (40%) and distorted (half of text is skewed by up to 30 degrees) images. It proposes a method that helps to identify text by using CNNs, BiLSTMs and a CTC decoder.
11
Mohd Kadir, Nasibah Husna, Sharifah Nur Syafiqah Mohd Nur Hidayah, Norasiah Mohammad, and Zaidah Ibrahim. "Comparison of convolutional neural network and bag of features for multi-font digit recognition." Indonesian Journal of Electrical Engineering and Computer Science 15, no. 3 (2019): 1322. http://dx.doi.org/10.11591/ijeecs.v15.i3.pp1322-1328.
Full textAbstract:
<span>This paper evaluates the recognition performance of Convolutional Neural Network (CNN) and Bag of Features (BoF) for multiple font digit recognition. Font digit recognition is part of character recognition that is used to translate images from many document-input tasks such as handwritten, typewritten and printed text. BoF is a popular machine learning method while CNN is a popular deep learning method. Experiments were performed by applying BoF with Speeded-up Robust Feature (SURF) and Support Vector Machine (SVM) classifier and compared with CNN on Chars74K dataset. The recognition accuracy produced by BoF is just slightly lower than CNN where the accuracy of CNN is 0.96 while the accuracy of BoF is 0.94.</span>
12
Voon, Chen Huey, Tang Ker Shin, and Ng Wei Shean. "Chinese Character Recognition Using Non-negative Matrix Factorization." Jurnal Kejuruteraan 36, no. 2 (2024): 653–60. http://dx.doi.org/10.17576/jkukm-2024-36(2)-24.
Full textAbstract:
Non-negative matrix factorization (NMF) was introduced by Paatero and Tapper in 1994 and it was a general way of reducing the dimension of the matrix with non-negative entries. Non-negative matrix factorization is very useful in many data analysis applications such as character recognition, text mining, and others. This paper aims to study the application in Chinese character recognition using non-negative matrix factorization. Python was used to carry out the LU factorization and non-negative matrix factorization of a Chinese character in Boolean Matrix. Preliminary analysis confirmed that the data size of and and are chosen for the NMF of the Boolean matrix. In this project, one hundred printed Chinese characters were selected, and all the Chinese characters can be categorized into ten categories according to the number of strokes , for . The Euclidean distance between the Boolean matrix of a Chinese character and the matrix after both LU factorization and NMF is calculated for further analysis. Paired t-test confirmed that the factorization of Chinese characters in the Boolean matrix using NMF is better than the LU factorization. Finally, ten handwritten Chinese characters were selected to test whether the program is able to identify the handwritten and the printed Chinese characters. Experimental results showed that 70% of the characters can be recognized via the least Euclidean distance obtained. NMF is suitable to be applied in Chinese character recognition since it can reduce the dimension of the image and the error between the original Boolean matrix and after NMF is less than 5%.
13
Nazdryukhin, A. S., I. N. Khramtsov, and A. N. Tushev. "PROCESSING IMAGES OF SALES RECEIPTS FOR ISOLATING AND RECOGNISING TEXT INFORMATION." Herald of Dagestan State Technical University. Technical Sciences 46, no. 4 (2020): 113–22. http://dx.doi.org/10.21822/2073-6185-2019-46-4-113-122.
Full textAbstract:
Objectives. This article presents an application for the processing of scanned images of sales receipts for subsequent extraction of text information using the Tesseract OCR Engine. Such an application is useful for maintaining a family budget or for accounting in small companies. The main problem of receipt recognition is the low quality of ink and printing paper, which results in creasing and tears, as well as the rapid fading of printed characters.Methods. The study is based on a number of algorithms based on mathematical morphology methods for opening, closing and morphological gradient operations, as well as image conversion, which can significantly improve the final recognition of characters by Tesseract.Results. In order to solve this problem, a special image normalisation algorithm is proposed, which includes locating a receipt on an image, processing the received image section, removing image capture and carrier defects, as well as point processing for restoring missing characters. The developed application supports increased recognition accuracy of text information when using Tesseract OCR.Conclusion. The developed system recognises characters with fairly high accuracy, demonstrates a result that is better than that obtained when using the unmodified Tesseract method, but which is still inferior to the recognition accuracy of ABBY FineReader. Methods are also been proposed aimed at improving the developed algorithm.
14
Tofiq, Tofiq Ahmed, and Jamal Ali Hussein. "Kurdish Text Segmentation using Projection-Based Approaches." UHD Journal of Science and Technology 5, no. 1 (2021): 56–65. http://dx.doi.org/10.21928/uhdjst.v5n1y2021.pp56-65.
Full textAbstract:
An optical character recognition (OCR) system may be the solution to data entry problems for saving the printed document as a soft copy of them. Therefore, OCR systems are being developed for all languages, and Kurdish is no exception. Kurdish is one of the languages that present special challenges to OCR. The main challenge of Kurdish is that it is mostly cursive. Therefore, a segmentation process must be able to specify the beginning and end of the characters. This step is important for character recognition. This paper presents an algorithm for Kurdish character segmentation. The proposed algorithm uses the projection-based approach concepts to separate lines, words, and characters. The algorithm works through the vertical projection of a word and then identifies the splitting areas of the word characters. Then, a post-processing stage is used to handle the over-segmentation problems that occur in the initial segmentation stage. The proposed method is tested using a data set consisting of images of texts that vary in font size, type, and style of more than 63,000 characters. The experiments show that the proposed algorithm can segment Kurdish words with an average accuracy of 98.6%.
15
Mahadevkar, Supriya, Shruti Patil, Ketan Kotecha, and Ajith Abraham. "A comparison of deep transfer learning backbone architecture techniques for printed text detection of different font styles from unstructured documents." PeerJ Computer Science 10 (February 23, 2024): e1769. http://dx.doi.org/10.7717/peerj-cs.1769.
Full textAbstract:
Object detection methods based on deep learning have been used in a variety of sectors including banking, healthcare, e-governance, and academia. In recent years, there has been a lot of attention paid to research endeavors made towards text detection and recognition from different scenesor images of unstructured document processing. The article’s novelty lies in the detailed discussion and implementation of the various transfer learning-based different backbone architectures for printed text recognition. In this research article, the authors compared the ResNet50, ResNet50V2, ResNet152V2, Inception, Xception, and VGG19 backbone architectures with preprocessing techniques as data resizing, normalization, and noise removal on a standard OCR Kaggle dataset. Further, the top three backbone architectures selected based on the accuracy achieved and then hyper parameter tunning has been performed to achieve more accurate results. Xception performed well compared with the ResNet, Inception, VGG19, MobileNet architectures by achieving high evaluation scores with accuracy (98.90%) and min loss (0.19). As per existing research in this domain, until now, transfer learning-based backbone architectures that have been used on printed or handwritten data recognition are not well represented in literature. We split the total dataset into 80 percent for training and 20 percent for testing purpose and then into different backbone architecture models with the same number of epochs, and found that the Xception architecture achieved higher accuracy than the others. In addition, the ResNet50V2 model gave us higher accuracy (96.92%) than the ResNet152V2 model (96.34%).
16
Susanty, Meredita, and Herminarto Nugroho. "OPTICAL CHARACTER RECOGNITION IMPLEMENTATION FOR ADMISSION SYSTEM IN UNIVERSITAS PERTAMINA." Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer 11, no. 1 (2020): 165–70. http://dx.doi.org/10.24176/simet.v11i1.3838.
Full textAbstract:
Starting in 2019, prospective college students require to take Computer-Based Writing Exam (UTBK) to register for the state universities in Indonesia. Some private university also adopts this exam as a requirement for admission. One of the private university that adopts it is Universitas Pertamina. UTBK consist of several exam group score printed in a digital certificate in image format (jpg). The university admission team must download the UTBK certificate that has uploaded by applicants, read and record the score for each exam group then make a calculation to make a decision whether the applicant is accepted in a certain school in the university. This research proposes to replace the manual process performed by the admission team with optical character recognition (OCR). The OCR engine will extract text from an image. Some information from the extracted text is calculated to provide an acceptance decision. The research shows that OCR cannot accurately convert text from an image when there is a grayscale background in the image. However, image preprocessing can improve overall accuracy. Lastly, Tesseract performs better in converting black text with white-background than white text with a black background.
17
Shareef, Shareef Maulod, and Abbas Mohamad Ali. "Deep learning-based digitization of Kurdish text handwritten in the e-government system." Indonesian Journal of Electrical Engineering and Computer Science 35, no. 3 (2024): 1865. http://dx.doi.org/10.11591/ijeecs.v35.i3.pp1865-1875.
Full textAbstract:
Many government institutions in developing countries such as the Kurdistan Region of Iraq (KRI) keep a variety of paper-based records that are available in printed or handwritten format. The need for technology that turns handwritten writing into digital text is therefore highly demanded. E-government in developed and developing countries is a crucial facilitator for the provision of such services. This paper aims to develop a deep learning model based on the mask region convolutional neural network (mask-RCNN) to effectively digitize kurdish handwritten text recognition (KHTR). In this research, typical datasets, which includes the isolated handwritten Central Kurdish character images, an extensive database of 40,410 images, and 390 native writers have been produced to determine the developed approach’s performance in terms of identification rates. This approach achieves adequate outcomes in terms of training time and accuracy. The proposed model gives higher performance for detection, localization, and recognition when using a dataset containing many challenges, the results were 80%, 96%, and 87.6 for precision, recall, and F-score respectively. The findings revealed that the proposed model obtained better results compared to other similar works. The accuracy of optical character recognition (OCR) is more than 99%.
18
Shareef, Maulod Shareef Abbas Mohamad Ali. "Deep learning-based digitization of Kurdish text handwritten in the e-government system." Indonesian Journal of Electrical Engineering and Computer Science 35, no. 3 (2024): 1865–75. https://doi.org/10.11591/ijeecs.v35.i3.pp1865-1875.
Full textAbstract:
Many government institutions in developing countries such as the Kurdistan Region of Iraq (KRI) keep a variety of paper-based records that are available in printed or handwritten format. The need for technology that turns handwritten writing into digital text is therefore highly demanded. E-government in developed and developing countries is a crucial facilitator for the provision of such services. This paper aims to develop a deep learning model based on the mask region convolutional neural network (mask-RCNN) to effectively digitize kurdish handwritten text recognition (KHTR). In this research, typical datasets, which includes the isolated handwritten Central Kurdish character images, an extensive database of 40,410 images, and 390 native writers have been produced to determine the developed approach’s performance in terms of identification rates. This approach achieves adequate outcomes in terms of training time and accuracy. The proposed model gives higher performance for detection, localization, and recognition when using a dataset containing many challenges, the results were 80%, 96%, and 87.6 for precision, recall, and F-score respectively. The findings revealed that the proposed model obtained better results compared to other similar works. The accuracy of optical character recognition (OCR) is more than 99%.
19
Tiptur Parashivamurthy, Supreetha Patel, and Dr Sannangi Viswaradhya Rajashekararadhya. "An Efficient Kannada Handwritten Character Recognition Framework with Serial Dilated Cascade Network for Kannada Scripts." Advances in Artificial Intelligence and Machine Learning 04, no. 03 (2024): 2499–516. http://dx.doi.org/10.54364/aaiml.2024.43146.
Full textAbstract:
The most significant problem present in the digitized world is handwritten character recognition and identification because it is helpful in various applications. The manual work needed for changing the handwritten character document into machine-readable texts is highly reduced by using the automatic identification approaches. Due to the factors of high variance in the writing styles beyond the globe, handwritten text size and low quality of handwritten text rather than printed text make handwritten character recognition to be very complex. The Kannada language has originated over the past 1000 years, where the consonants and vowels are symmetric in nature and also curvy, therefore, the recognition of Kannada characters online is very difficult. Thus, it is essential to overcome the above-mentioned complications presented in the classical Kannada handwritten character recognition model. The recognition of characters from Kannada Scripts is also difficult. Hence, this work aims to design a new Kannada handwritten character recognition framework using deep learning techniques from Kannada scripts. There are two steps to be followed in the proposed model that is collection of images and classification of handwritten characters. At first, essential handwritten Kannada characters are collected from the benchmark resources. Next, the acquired handwritten Kannada images are offered to the handwritten Kannada character recognition phase. Here, Kannada character recognition is performed using Serial Dilated Cascade Network (SDCN), which utilized the Visual Geometry Group 16 (VGG16) and Deep Temporal Convolution Network (DTCN) technique for the observation. When compared to the baseline recognition works, the proposed handwritten Kannada character recognition model achieves a significantly higher performance rate.
20
Thorvaldsen, Gunnar, Joana Maria Pujadas-Mora, Trygve Andersen, et al. "A Tale of Two Transcriptions. Machine-Assisted Transcription of Historical Sources." Historical Life Course Studies 2 (January 29, 2015): 1–19. http://dx.doi.org/10.51964/hlcs9355.
Full textAbstract:

 
 
 This article explains how two projects implement semi-automated transcription routines: for census sheets in Norway and marriage protocols from Barcelona. The Spanish system was created to transcribe the marriage license books from 1451 to 1905 for the Barcelona area; one of the world’s longest series of preserved vital records. Thus, in the Project “Five Centuries of Marriages” (5CofM) at the Autonomous University of Barcelona’s Center for Demographic Studies, the Barcelona Historical Marriage Database has been built. More than 600,000 records were transcribed by 150 transcribers working online. The Norwegian material is cross-sectional as it is the 1891 census, recorded on one sheet per person. This format and the underlining of keywords for several variables made it more feasible to semi-automate data entry than when many persons are listed on the same page. While Optical Character Recognition (OCR) for printed text is scientifically mature, computer vision research is now focused on more difficult problems such as handwriting recognition. In the marriage project, document analysis methods have been proposed to automatically recognize the marriage licenses. Fully automatic recognition is still a challenge, but some promising results have been obtained. In Spain, Norway and elsewhere the source material is available as scanned pictures on the Internet, opening up the possibility for further international cooperation concerning automating the transcription of historic source materials. Like what is being done in projects to digitize printed materials, the optimal solution is likely to be a combination of manual transcription and machine-assisted recognition also for hand-written sources.
 
 
21
KACEM ECHI, AFEF, IMEN BEN CHEIKH, and ABDEL BELAÏD. "COLLABORATIVE COMBINATION OF NEURON-LINGUISTIC CLASSIFIERS FOR LARGE ARABIC WORD VOCABULARY RECOGNITION." International Journal of Pattern Recognition and Artificial Intelligence 28, no. 01 (2014): 1453001. http://dx.doi.org/10.1142/s0218001414530012.
Full textAbstract:
Most of the actual research in writing recognition focuses on specific applications where the vocabulary is relatively small. Many applications can be opened up when handling with large vocabulary. In this paper, we studied the classifier collaboration interest for the recognition of a large vocabulary of arabic words. The proposed approach is based on three classifiers, named Transparent Neuronal Networks (TNN), which exploit the morphological aspect of the Arabic word and collaborate for a better word recognition. We focused on decomposable words which are derived from healthy tri-consonantal roots and easy to proof the decomposition. To perform word recognition, the system extracts a set of global structural features. Then it learns and recognizes roots, schemes and conjugation elements that compose the word. To help the recognition, some local perceptual information is used in case of ambiguities. This interaction between global recognition and local checking makes easier the recognition of complex scripts as Arabic. Several experiments have been performed using a vocabulary of 5757 words, organized in a corpus of more than 17 200 samples. In order to validate our approach and to compare the proposed system with systems reported in ICDAR 2011 competition, extensive experiments were conducted using the Arabic Printed Text Image (APTI) database. The best recognition performances achieved by our system have shown very promising results.
22
Qu, Z., E. Qu, J. Huang, M. A. Micale, and E. Li. "Utilization of 2D Barcode Technology to Create Surgical Pathology Reports." American Journal of Clinical Pathology 156, Supplement_1 (2021): S116. http://dx.doi.org/10.1093/ajcp/aqab191.247.
Full textAbstract:
Abstract Introduction/Objective After professional transcription service is eliminated, pathologists inevitably undertake the task of diagnostic data entry into pathology repot by adapting a variety of methods such as speech recognition, manual typing, and pre-texted command. Errors and inefficiency in reporting remain common problems, especially for information with unusual syntax such as genotype or nucleotide sequences. To overcome these shortcomings, we introduce here a novel application of a well-established technology as a complementary method, namely 2- dimensional (2D) barcode symbology. Methods/Case Report Commonly used diagnostic wordings of pathology reports including specimen type, surgical procedure, diagnosis, and test results are collated and organized by organ (specimen type) and by their frequency of usage/occurrence. Next, 2D data matrix barcodes are created for these diagnostic wordings using a on-line tool (www.free-barcode-generator.net/datamatrix/). The 2D barcodes along with their text are displayed on the computer screen (or printed out as a booklet). A 2D barcode scanner (Symbol LS2208, Motorola) was used to retrieve the text information from the barcodes and transfer into the pathology report. To assess the efficacy of this barcode method, we evaluated the time of data entry into reports for 117 routine cases using an on-line stopwatch and compared with those by other data entry methods. Results (if a Case Study enter NA) Unlike manual typing or speech recognition, the barcode method did not introduce typographic or phonosemantic errors since the method simply transferred pre-texted and proof-read text content to report. It was also faster than manual typing or speech recognition, and its speed was comparable to that of the pre-text method integrated in LIS but did not require human memorization of innumerable text commands to retrieve desired diagnosis wordings. Conclusion Our preliminary results demonstrated that the diagnostic data entry time was reduced from 28.5% by other methods to 22.1% by the barcode method although due to the small sample size, statistical analysis was not conclusive.
23
Moharkar, Lalita, Sudhanshu Varun, Apurva Patil, and Abhishek Pal. "A scene perception system for visually impaired based on object detection and classification using CNN." ITM Web of Conferences 32 (2020): 03039. http://dx.doi.org/10.1051/itmconf/20203203039.
Full textAbstract:
In this paper we have developed a system for visually impaired people using OCR and machine learning. Optical Character Recognition is an automated data entry tool. To convert handwritten, typed or printed text into data that can be edited on a computer, OCR software is used. The paper documents are scanned on simple systems with an image scanner. Then, the OCR program looks at the image and compares letter shapes to stored letter images. OCR in English has evolved over the course of half a century to a point that we have established application that can seamlessly recognize English text. This may not be the case for Indian languages, as they are much more complex in structure and computation compared to English. Therefore, creating an OCR that can execute Indian languages as suitably as it does for English becomes a must. Devanagari is one of the Indian languages spoken by more than 70% of people in Maharashtra, so some attention should be given to studying ancient scripts and literature. The main goal is to develop a Devanagari character recognition system that can be implemented in the Devanagari script to recognize different characters, as well as some words.
24
Polyakova, Marina V., and Alexandr G. Nesteryuk. "IMPROVEMENT OF THE COLOR TEXT IMAGE BINARIZATION METHOD USING THE MINIMUM-DISTANCE CLASSIFIER." Applied Aspects of Information Technology 4, no. 1 (2021): 57–70. http://dx.doi.org/10.15276/aait.01.2021.5.
Full textAbstract:
Optical character recognition systems for the images are used to convert books and documents into electronic form, to automate accounting systems in business, when recognizing markers using augmented reality technologies and etс. The quality of optical character recognition, provided that binarization is applied, is largely determined by the quality of separation of the foreground pixels from the background. Methods of text image binarization are analyzed and insufficient quality of binarization is noted. As a way of research the minimum-distance classifier for the improvement of the existing method of binarization of color text images is used. To improve the quality of the binarization of color text images, it is advisable to divide image pixels into two classes, “Foreground” and “Background”, to use classification methods instead of heuristic threshold selection, namely, a minimum-distance classifier. To reduce the amount of processed information before applying the classifier, it is advisable to select blocks of pixels for subsequent processing. This was done by analyzing the connected components on the original image. An improved method of the color text image binarization with the use of analysis of connected components and minimum-distance classifier has been elaborated. The research of the elaborated method showed that it is better than existing binarization methods in terms of robustness of binarization, but worse in terms of the error of the determining the boundaries of objects. Among the recognition errors, the pixels of images from the class labeled “Foreground” were more often mistaken for the class labeled “Background”. The proposed method of binarization with the uniqueness of class prototypes is recommended to be used in problems of the processing of color images of the printed text, for which the error in determining the boundaries of characters as a result of binarization is compensated by the thickness of the letters. With a multiplicity of class prototypes, the proposed binarization method is recommended to be used in problems of processing color images of handwritten text, if high performance is not required. The improved binarization method has shown its efficiency in cases of slow changes in the color and illumination of the text and background, however, abrupt changes in color and illumination, as well as a textured background, do not allowing the binarization quality required for practical problems.
25
Martínez-Muñoz, Carlos, Dorothee Huff, Marie Meister, and Christine Driller. "Mobilizing and Enhancing Legacy Biodiversity Data: The case of Karl Wilhelm Verhoeff's correspondence." Biodiversity Information Science and Standards 6 (August 23, 2022): e93679. https://doi.org/10.3897/biss.6.93679.
Full textAbstract:
A considerable amount of biological data is preserved as physical documents, the legacy of former explorers, collectors, researchers, and others. Mobilizing data from handwritten documents has been considered particularly challenging, with well-known cases such as the manual transcription of specimen labels and herbarium sheets by museum staff, or crowdsourced transcription of data card collections through online platforms.Here we present a pipeline of open-source software that can be used toautomatically transcribe handwritten text,make it publicly available,annotate it with e.g., scientific names,extract names in Darwin Core Archive (DwC-A) for third-party reuse, andautomatically recognize named entities in the machine-readable text.We based our use case on the correspondence of the German zoologist Karl Wilhelm Verhoeff, related to the Myriapoda collection held at the Musée Zoologique de Strasbourg.The documents were processed with Transkribus (Muehlberger et al. 2019), a mostly open-source virtual research environment (OS VRE), which allows text in images to be converted into machine-readable text amenable to semantic enrichment. We achieved a character error rate as low as 5%, a remarkable result for handwritten material, as an accuracy higher than 95% for printed material is acceptable (Deutsche Forschungsgemeinschaft 2016). We then used Myriatrix (Martínez-Muñoz 2019), an instance of the Scratchpads OS VRE (Smith et al. 2011), to create bibliographic references, publish the full text, and annotate the correspondence with scientific names of myriapods. During the process, we added new scientific name spellings and combinations to the taxonomic backbone of Myriatrix and exported the full taxon classification in DwC-A via the Global Biodiversity Information Facility (GBIF) for reuse by the Global Names Architecture and its open-source tools (Patterson et al. 2016, Mozzherin et al. 2017).As a next step we are planning to subject the corrected text from Transkribus to a specific text-preprocessing workflow combining natural language processing (NLP) and machine learning (ML) techniques (Lücking et al. 2021). This includes, inter alia, a multiple annotation approach for general and bioscientific term classification in order to detect the respective entities automatically. The workflow has been developed in the framework of the Specialized Information Service Biodiversity Research (Koch et al. 2017) to make biodiversity information available via a customized and (bio-)ontology-based semantic search engine (Pachzelt et al. 2021).We recommend our comprehensive approach to natural history institutions seeking to efficiently digitize and mobilize the rich biological data present in their archival documents.
26
Wong, Hoo Keat, Siew Ming Thang, Chee Hao Sue, Rosalind A. K. Ahju, and Fung Lan Loo. "Investigating the Relationship Between Visual Attention, Story Comprehension, and Vocabulary Skills in Malaysian Prereaders." International Journal of Computer-Assisted Language Learning and Teaching 13, no. 1 (2023): 1–19. http://dx.doi.org/10.4018/ijcallt.332878.
Full textAbstract:
Based on the cross-channel connections between auditory and pictorial representations, it has been proposed that the presentation of coherent narration along with the picture and text content may enhance children's story comprehension and vocabulary learning. The authors tested 40 four- to five-year-old Malaysian prereaders (17 Malays, 23 Chinese) for story comprehension while observing their eye movements to determine the degree to which the presence of pictures and/or text aids understanding of the narration and influences looking patterns. Both Malay and Chinese prereaders showed no interest in the printed text that was presented alongside the picture on the same page, which is consistent with earlier findings. This suggests that ethnic origins have little influence on how prereaders direct their visual attention to the relevant information for story comprehension. When there was no narration, they fixated longer on the text and less on the image, indicating that a significant amount of mental effort was required to process the words without verbal information. Regardless of stimulus congruency, storytelling performance affected how much children focused on target objects and keywords. More intriguingly, it was found that in Malay prereaders, there was a correlation between story comprehension and vocabulary skills across tasks. Additionally, Malay prereaders who performed well looked at the displayed stimuli longer than Chinese prereaders who performed well, especially when a narrator was presented alongside the visual stimulus. These novel findings are discussed along with their implications for multimedia learning and future research directions.
27
CHONG, WOO SUK, MI YEON SHIN, and CHANG HO YU. "STUDY ON VISION-BASED MULTIDIRECTIONAL POSTURE AND MOTION ANALYSIS SYSTEM DEVELOPMENT." Journal of Mechanics in Medicine and Biology 19, no. 08 (2019): 1940059. http://dx.doi.org/10.1142/s0219519419400591.
Full textAbstract:
In this study, a multidirectional posture and motion evaluation tool system using a camera-based vision system was developed. By installing a camera on the top, back, left, and front of the system, kinematical information of the participant was collected and analyzed on the sagittal, coronal, and transverse planes. A dedicated color light-emitting diode (LED) marker was developed for increasing recognition rate of marker. Based on LabVIEW, images collected from four cameras were printed on one screen, and the detection angle of each marker was calculated using the cosine second law. To evaluate the performance of this system, a motion analysis experiment was performed on 20 office workers in Jeonju area. The reliability was measured using POFOMO, Dartfish and the results were compared. The comparison results indicate that the concurrent validities of the two results for the knee angle, left shoulder, and right shoulder were highly correlated as [Formula: see text], 0.988, and 0.991, respectively. Because the POFOMO image analysis tool in the present system reduces the analysis time and involves a simpler measurement procedure than that of Dartfish, this system can be used as an effective device for measuring the posture alignment of the human body.
28
Amar, Dutta. "The Guide: Adaptation from Novel to Film." postScriptum: An Interdisciplinary Journal of Literary Studies 1, no. 1 (2016): 22–34. https://doi.org/10.5281/zenodo.1318792.
Full textAbstract:
Adaptation in the film industry is nothing new. Almost three-fourths of all films ever made have been adapted from novels, plays or short stories of the classic literature in every language. Our Indian film industry is of no exception. It is often said that the printed text is, in some way, superior to and more moral than the filmed version. The objective of this paper is to focus on such adaptation – the adaptation of R.K.Narayan’s Sahitya Akademi Award winning novel The Guide to Vijay Anand’s film Guide. After the release of the film Narayan was very unhappy because he felt that it could not capture the spirit of the story, and he did not like the unwarranted cuts and changes. This is true from the aesthetic view point, but it is equally true that a film director is not bound to the original and he or she has every right to eliminate or add some characters and incidents which are or are not there in the original text in order to cater the taste of all sorts of public. In the process of adaptation every film director recreates or gives new dimension to the original. The humble attempt in this paper is to trace the changes made by Vijay Anand and to show how these changes made the film a grand success and received several awards and recognition in spite of Narayan’s strong dislike.
29
Simran Sandeep, Redkar, Ganapathy Sankar Umaiorubagam, and Deepak Vignesh Raj S. "Understanding visual perception skills in autism spectrum disorder: A systematic review." Journal of Associated Medical Sciences 58, no. 1 (2025): 245–59. https://doi.org/10.12982/jams.2025.027.
Full textAbstract:
Background: Visual perception in individuals with autism spectrum disorder (ASD) can vary, often showcasing both strengths and challenges. Many individuals with ASD excel in detail-oriented processing, allowing them to focus on fine details rather than the overall picture, which can be advantageous in tasks requiring attention to small details, such as visual search and pattern recognition. Understanding these unique aspects of visual perception in ASD is crucial for developing tailored interventions and support strategies to enhance visual processing abilities and overall social functioning. Objective: To understand the visual perception skills in autism spectrum disorder. Materials and methods: The systematic review was registered in PROSPERO and followed the guidelines of PRISMA. A comprehensive search was conducted through the databases (Scopus, PubMed, ProQuest, EBSCOhost, and OTseeker) and printed journals. Studies were included if they focused on visual perception skills in children with autism aged 3-12 years, were peer-reviewed, published between January 2014 and February 2024, and were available in full-text in English. The AXIS Tool for Cross Sectional Studies was used to conduct the critical appraisal. Results: 19141 studies were derived for database search and 932 from printed journals. A total of sixteen (N=16) studies were identified within the scope of our study. AXIS Tool for Cross-sectional studies was used to evaluate the quality of the sixteen studies. Visual perception skills in ASD have yielded diverse findings, such as perceptual bias, enhanced visual processing, enhanced visual search, and differences in visual processing speed. The review suggested that visual perception impairments are commonly seen in ASD, impacting their functional independence. The review also highlights the importance of understanding the basis of visual perception impairments in this population. Conclusion: The systematic review concludes that visual perception deficits are one of the primary deficits in autism spectrum disorder. Furthermore, the review reflects on the complex and diverse nature of visual perception skills exhibited by individuals with autism spectrum disorder. These deficits impact overall performance in everyday functioning, especially self-care, academics, and socialization.
30
Salem Mohamed, Mofreh, Aida Abd El-Gwad, Fatma El-Zahraa Abou-Chadi, and Mohamed keshk. "Printed Arabic Text Recognition Algorithms.(Dept.E)." MEJ. Mansoura Engineering Journal 15, no. 2 (2021): 154–62. http://dx.doi.org/10.21608/bfemu.2021.171297.
Full text
31
KIMPAN, CHOM. "Invited paper Printed Thai character recognition using topological properties method." International Journal of Electronics 60, no. 3 (1986): 303–29. http://dx.doi.org/10.1080/00207218608920788.
Full text
32
Imjai, Thanongsak, Chirawat Wattanapanich, Uhamard Madardam, and Reyes Garcia. "Analysis of Ink/Toner Savings of English and Thai Ecofonts for Sustainable Printing." Sustainability 13, no. 7 (2021): 4070. http://dx.doi.org/10.3390/su13074070.
Full textAbstract:
The use of Ecofonts in printing can result in economic savings and lower environmental impact. However, most of the research on the use of Ecofonts focuses on Latin alphabets. Moreover, texts printed with Ecofonts can be perceived as being less legible than those printed with the original typefaces. This study (a) assesses toner use reductions in documents printed with English and Thai Ecofonts, and (b) studies the observers’ perception of texts printed either with Ecofonts or with original typefaces. To achieve this, black pixels were removed from 10 English and 13 Thai typefaces widely used in academia and other media. Visibility and legibility tests, as well as mass analyses tests, were then performed on texts printed with some such typefaces. Results from instrumental measurements and digital image analyses show that the use of Ecofonts reduces toner use of an inkjet printer by up to 28%. The study also proposes a new Ecofont typeface for the Thai language. Visual tests showed that the visual experience of text printed using this Thai Ecofont is satisfactory. Awareness of the benefits of using Ecofonts changes the users’ attitudes towards the printing quality of Ecofont. The removal of black pixels can lead to more sustainable printing, and this simple solution can be extended to other non-Latin languages as part of the global Green Information Technology efforts in South-East Asia.
33
Pavlidis, Theo. "Recognition of printed text under realistic conditions." Pattern Recognition Letters 14, no. 4 (1993): 317–26. http://dx.doi.org/10.1016/0167-8655(93)90097-w.
Full text
34
Jung, Kwanghee, Vinh T. Nguyen, Seung-Chul Yoo, Seungman Kim, Sohyun Park, and Melissa Currie. "PalmitoAR: The Last Battle of the U.S. Civil War Reenacted Using Augmented Reality." ISPRS International Journal of Geo-Information 9, no. 2 (2020): 75. http://dx.doi.org/10.3390/ijgi9020075.
Full textAbstract:
Various efforts are used to preserve American history including relying on formal education, distributing information (text, video or visual aids) on social channels, displaying artifacts in historical centers or more recently, virtual reality applications posted on a shared medium. However, many of the newly developed applications are designed specifically for dedicated hardware rather than for a broad audience, thus creating a barrier for disseminating cultural values. In this paper, we propose a web-based Augmented Reality (AR) application, namely PalmitoAR, which provides an intuitive way of observing one of the most significant historical Civil War battlefields, Palmito Ranch Battlefield located in Cameron County, Texas. The proposed AR application is designed to resurrect a series of events through (i) a printed map of Palmito Ranch with embedded markers that enables viewers to experience the battle without being present at the site, (ii) a mobile device with a WebGL supported browser that allows 3D contents to be rendered, and (iii) an AR library (A-Frame.io) that enables enthusiasts to recreate similar work. Our methodology strongly relies on the benefits of a simple, robust algorithm for AR marker recognition to position 3D models in a specific context and time. As a result, the proposed AR application is complementary to existing work and provides a seamless experience for a wide range of viewers. We evaluated and improved the application with the help of twenty-six users to gather perspectives on the specific benefits of employing AR in learning about battlefields and reenactment. The technology acceptance model was adapted to access an individual’s acceptance of information technology.
35
KUNTE, R. SANJEEV, and R. D. SUDHAKER SAMUEL. "WAVELET DESCRIPTORS FOR RECOGNITION OF BASIC SYMBOLS IN PRINTED KANNADA TEXT." International Journal of Wavelets, Multiresolution and Information Processing 05, no. 02 (2007): 351–67. http://dx.doi.org/10.1142/s0219691307001793.
Full textAbstract:
Optical Character Recognition (OCR) systems have been effectively developed for the recognition of printed characters of non-Indian languages. Efforts are underway for the development of efficient OCR systems for Indian languages, especially for Kannada, a popular South Indian language. We present in this paper an OCR system developed for the recognition of basic characters in printed Kannada text, which can handle different font sizes and font sets. Wavelets that have been progressively used in pattern recognition and on-line character recognition systems are used in our system to extract the features of printed Kannada characters. Neural classifiers have been effectively used for the classification of characters based on wavelet features. The system methodology can be extended for the recognition of other south Indian languages, especially for Telugu.
36
Sangkathum, Ousanee, and Ohm Sornil. "Printed Thai Character Recognition Using Conditional Random Fields and Hierarchical Centroid Distance." Applied Mechanics and Materials 411-414 (September 2013): 1238–46. http://dx.doi.org/10.4028/www.scientific.net/amm.411-414.1238.
Full textAbstract:
This paper presents a Thai character recognition method based on topological properties. The method first extracts gradient features from a character image. A two-step classification are then applied to recognize the character. In the first step, a conditional random fields model is used to generate a set of possible characters. Then a nearest neighbor model based on hierarchical centroid distance is employed to finally recognize the character. The proposed method is trained by printed characters from documents and vehicle license plates. The technique is evaluated and found to have the recognition rate of 96.96%.
37
Tkachenko, Kostiantyn, and Oleksii Zuienko. "Use of Multilayer LSTM Neural Network in the Process of Printed Texts Recognition." Digital Platform: Information Technologies in Sociocultural Sphere 5, no. 1 (2022): 199–215. https://doi.org/10.31866/2617-796X.5.1.2022.261305.
Full textAbstract:
The purpose of the article is to study, analyze and consider general problems and prospects for the development of printed text recognition systems based on the use of neural networks. The research methodology consists in methods of semantic analysis of this subject area’s basic concepts (recognition systems of printed texts). Approaches to the development and operation of recognition systems based on neural networks are considered. The scientific novelty of the research is the development of its own approach to text recognition based on neural networks, the results of which were used in the development of its own system of print recognition. Conclusions. The paper considers the well-known views on pattern recognition on the example of printed texts and analyzes modern approaches to the use of neural networks and their training. Taking into account the results of the analysis, the authors decided to develop a system for recognizing the languages of printed texts using learning neural networks.
38
Amin, A., and J. F. Mari. "Machine recognition and correction of printed Arabic text." IEEE Transactions on Systems, Man, and Cybernetics 19, no. 5 (1989): 1300–1306. http://dx.doi.org/10.1109/21.44052.
Full text
39
Alan Jiju, Shaun Tuscano, and Chetana Badgujar. "OCR Text Extraction." International Journal of Engineering and Management Research 11, no. 2 (2021): 83–86. http://dx.doi.org/10.31033/ijemr.11.2.11.
Full textAbstract:
This research tries to find out a methodology through which any data from the daily-use printed bills and invoices can be extracted. The data from these bills or invoices can be used extensively later on – such as machine learning or statistical analysis. This research focuses on extraction of final bill-amount, itinerary, date and similar data from bills and invoices as they encapsulate an ample amount of information about the users purchases, likes or dislikes etc. Optical Character Recognition (OCR) technology is a system that provides a full alphanumeric recognition of printed or handwritten characters from images. Initially, OpenCV has been used to detect the bill or invoice from the image and filter out the unnecessary noise from the image. Then intermediate image is passed for further processing using Tesseract OCR engine, which is an optical character recognition engine. Tesseract intends to apply Text Segmentation in order to extract written text in various fonts and languages. Our methodology proves to be highly accurate while tested on a variety of input images of bills and invoices.
40
Hoonchamlong, Yuphaphan. "A Karaoke Approach for Language Teaching: The Case of the “Learning to Read Thai from Songs” Project." MANUSYA 7, no. 3 (2004): 25–40. http://dx.doi.org/10.1163/26659077-00703004.
Full textAbstract:
Karaoke is music video with text lyrics on screen. Thus karaoke provides audio, visual, and also textual information at the same time. As a language-teaching material, karaoke can therefore be viewed as a short authentic text, with the sung vocals functioning as an audio reading model accompanied by a corresponding visual context. I will discuss the design and implementation of "Learning to Read Thai from Songs", a web-based, interactive, multimedia, instructional-materials project which makes use of the aforementioned desirable features of "karaoke" to create instructional materials for enhancing the instruction of the Thai writing system and students' Thai script recognition practice by using Thai songs.
41
Malik, Saud, Ahthasham Sajid, Arshad Ahmad, et al. "An Efficient Skewed Line Segmentation Technique for Cursive Script OCR." Scientific Programming 2020 (December 3, 2020): 1–12. http://dx.doi.org/10.1155/2020/8866041.
Full textAbstract:
Segmentation of cursive text remains the challenging phase in the recognition of text. In OCR systems, the recognition accuracy of text is directly dependent on the quality of segmentation. In cursive text OCR systems, the segmentation of handwritten Urdu language text is a complex task because of the context sensitivity and diagonality of the text. This paper presents a line segmentation algorithm for Urdu handwritten and printed text and subsequently to ligatures. In the proposed technique, the counting pixel approach is employed for modified header and baseline detection, in which the system first removes the skewness of the text page, and then the page is converted into lines and ligatures. The algorithm is evaluated on manually generated Urdu printed and handwritten dataset. The proposed algorithm is tested separately on handwritten and printed text, showing 96.7% and 98.3% line accuracy, respectively. Furthermore, the proposed line segmentation algorithm correctly extracts the lines when tested on Arabic text.
42
Koponen, Jarmo, Keijo Haataja, and Pekka Toivanen. "A novel deep learning method for recognizing texts printed with multiple different printing methods." F1000Research 12 (April 20, 2023): 427. http://dx.doi.org/10.12688/f1000research.131775.1.
Full textAbstract:
Background: Text recognition of cardboard pharmaceutical packages with machine vision is a challenging task due to the different curvatures of packaging surfaces and different printing methods. Methods: In this research, a novel deep learning method based on regions with convolutional neural networks (R-CNN) for recognizing binarized expiration dates and batch codes printed using different printing methods is proposed. The novel method recognizes the characters in the images without the need to extract handcrafted features. In detail, this approach performs text recognition considering the whole image as an input extracting and learning salient character features straight from packaging surface images. Results: The expiration date and manufacturing batch codes of a real-life pharmaceutical packaging image set are recognized with 91.1% precision with a novel deep learning-based model, while Tesseract OCR text recognition performance with the same image set is 38.3%. The novel model outperformed Tesseract OCR also in tests evaluating recall, accuracy, and F-Measure performance. Furthermore, the novel model was evaluated in terms of multi-object recognition accuracy and the number of unrecognized characters, in order to achieve performance values comparable to existing multi-object recognition methods. Conclusions: The results of this study reveal that the novel deep learning method outperforms the well-established optical character recognition method in recognizing texts printed using different printing methods. The novel method presented in the study recognizes texts printed with different printing methods with high precision. The novel deep learning method is suitable for recognizing texts printed on curved surfaces with proper preprocessing. The problem investigated in the study differs from previous research in the field, focusing on the recognition of texts printed with different printing methods. The research thus fills a gap in text recognition that existed in the research of the field. Furthermore, the study presents new ideas that will be utilized in our future research.
43
AL-SADOUN, HUMOUD B., and ADNAN AMIN. "A NEW STRUCTURAL TECHNIQUE FOR RECOGNIZING PRINTED ARABIC TEXT." International Journal of Pattern Recognition and Artificial Intelligence 09, no. 01 (1995): 101–25. http://dx.doi.org/10.1142/s0218001495000067.
Full textAbstract:
This paper proposes a new structural technique for Arabic text recognition. The technique can be divided into five major steps: (1) preprocessing and binarization; (2) thinning; (3) binary tree construction; (4) segmentation; and (5) recognition. The advantage of this technique is that its execution does not depend on either the font or size of character. Thus, this same technique might be utilized for the recognition of machine or hand printed text. The relevant algorithm is implemented on a microcomputer. Experiments were conducted to verify the accuracy and the speed of this algorithm using about 20,000 subwords each with an average length of 3 characters. The subwords used were written using different fonts. The recognition rate obtained in the experiments indicated an accuracy of 93.38 % with a speed of 2.7 characters per second.
44
Kimpan, C., A. Itoh, and K. Kawanishi. "Fine classification of printed Thai character recognition using the karhunen-loève expansion." IEE Proceedings E Computers and Digital Techniques 134, no. 5 (1987): 257. http://dx.doi.org/10.1049/ip-e.1987.0044.
Full text
45
NATARAJAN, PREMKUMAR, ZHIDONG LU, RICHARD SCHWARTZ, ISSAM BAZZI, and JOHN MAKHOUL. "MULTILINGUAL MACHINE PRINTED OCR." International Journal of Pattern Recognition and Artificial Intelligence 15, no. 01 (2001): 43–63. http://dx.doi.org/10.1142/s0218001401000745.
Full textAbstract:
This paper presents a script-independent methodology for optical character recognition (OCR) based on the use of hidden Markov models (HMM). The feature extraction, training and recognition components of the system are all designed to be script independent. The training and recognition components were taken without modification from a continuous speech recognition system; the only component that is specific to OCR is the feature extraction component. To port the system to a new language, all that is needed is text image training data from the new language, along with ground truth which gives the identity of the sequences of characters along each line of each text image, without specifying the location of the characters on the image. The parameters of the character HMMs are estimated automatically from the training data, without the need for laborious handwritten rules. The system does not require presegmentation of the data, neither at the word level nor at the character level. Thus, the system is able to handle languages with connected characters in a straightforward manner. The script independence of the system is demonstrated in three languages with different types of script: Arabic, English, and Chinese. The robustness of the system is further demonstrated by testing the system on fax data. An unsupervised adaptation method is then described to improve performance under degraded conditions.
46
Kim, Sue J. "The Dialectics of “Oriental” Images in American Trade Cards." Ethnic Studies Review 31, no. 2 (2008): 1–34. http://dx.doi.org/10.1525/esr.2008.31.2.1.
Full textAbstract:
A late nineteenth-century trade card, or a color-printed circulating advertisement, touts Shepherd and Doyle's new “Celluloid” waterproof collars, cuffs and shirt bosoms (Fig. 1).1 These “economical, durable, and handsome” clothing items require less starching and washing, and so remove the need for Chinese laundries. The text on the reverse side includes directions on how “to remove yellow stains,” and the image enacts a kind of literal version of this removal. The slovenly laundryshop (the clothes overflowing the basket, the linens hung up askew, the steaming basins), the mix-and-match, gender-ambiguous garments of the workers, and their thin, slouching bodies all participate in the racist stereotype of Asians as dirty, effeminate and alien others. The caption proclaims the product to be “The Last Invention”; the “last” indicates finality, both in terms of modernity as the final stage of history and of a solution to the problem of unwanted immigrants. A group of Chinese male laundry-workers are so taken aback by this product that their pigtails stand in erect consternation. Their reaction stems both from the realization that they must return to China because their services have become unnecessary as well as from pure awe at the invention itself; in both cases, the scenario and its appeal apparently rely on these acts of recognition by the Chinese characters. Furthermore, the advertisement's status as such - merely advertisement - hides the illogicality of the celluloid salesman's presence in the laundry at all. The salesman, wearing a garish plaid suit and a bowler hat, appears to be one of those traveling salesmen who might peddle patent medicines, yet he bears the product eliciting such awe and consternation. Rather than selling the product to the Chinese workers, he appears simply to be taking gratuitous pleasure in introducing the workers to the agent of their impending misfortunes.
47
Parween, Gulfeshan. "Design of an OCR System and its Hardware Implementation." International Journal for Research in Applied Science and Engineering Technology 9, no. 12 (2021): 159–74. http://dx.doi.org/10.22214/ijraset.2021.39217.
Full textAbstract:
Abstract: In this paper, we present a scheme to develop to complete OCR system for printed text English Alphabet of Uppercase of different font and of different sizes so that we can use this system in Banking, Corporate, Legal industry and so on. OCR system consists of different modules like preprocessing, segmentation, feature extraction and recognition. In preprocessing step it is expected to include image gray level conversion, binary conversion etc. After finding out the feature of the segmented characters artificial neural network and can be used for Character Recognition purpose. Efforts have been made to improve the performance of character recognition using artificial neural network techniques. The proposed OCR system is capable of accepting printed document images from a file and implemented using MATLAB R2014a version. Key words: OCR, Printed text, Barcode recognition
48
Kaur, Amrit Veer, and Amandeep Verma. "Hybrid Wavelet based Technique for Text Extraction from Images." International Journal of Advanced Research in Computer Science and Software Engineering 7, no. 9 (2017): 24. http://dx.doi.org/10.23956/ijarcsse.v7i9.406.
Full textAbstract:
This paper reviews the current state of the art in handwriting recognition research. The paper deals with issues such as hand-printed character and cursive handwritten word recognition. It describes recent achievements, difficulties, successes and challenges in all aspects of handwriting recognition.
49
Koponen, Jarmo, Keijo Haataja, and Pekka Toivanen. "Novel Deep Learning Application: Recognizing Inconsistent Characters on Pharmaceutical Packaging." F1000Research 12 (July 23, 2024): 427. http://dx.doi.org/10.12688/f1000research.131775.2.
Full textAbstract:
Background Machine vision faces significant challenges when applied to text recognition on cardboard packaging particularly due to multiple printing methods, irregular character shapes, and curved packaging surfaces. Methods This research introduces a novel deep learning application for recognizing binarized expiration date and batch code characters printed using multiple printing methods. The method, based on Region-based Convolutional Neural Networks (R-CNN), enables character recognition directly from in the images without the need for extracting handcrafted features. In detail, this approach performs character recognition by using the whole image as input, extracting and learning salient character features directly from the packaging surface images. Results The R-CNN model, with a precision of 91.1% and an F1 score of 80.9%, effectively recognizes manufacturing markings on pharmaceutical packages, with inconsistencies in the characters’ shapes. In a comparative experiment using the same dataset of images, the R-CNN model significantly outperformed Tesseract OCR, achieving much higher precision, recall, and F1 scores. Conclusions The results of this study reveal that the deep learning method outperforms the well-established optical character recognition method in recognizing text characters printed with different printing methods. Presented in this study, the deep learning method recognizes text characters with high precision. It is also suitable for recognizing text printed on curved surfaces, provided proper preprocessing is applied. The problem investigated in the study differs from previous research in the field, focusing on the recognition of texts printed with different printing methods. The research thus fills a gap in text recognition that existed in the research of the field. Furthermore, the study presents new ideas that will be utilized in our future research.
50
Rizvi, S. S. R., A. Sagheer, K. Adnan, and A. Muhammad. "Optical Character Recognition System for Nastalique Urdu-Like Script Languages Using Supervised Learning." International Journal of Pattern Recognition and Artificial Intelligence 33, no. 10 (2019): 1953004. http://dx.doi.org/10.1142/s0218001419530045.
Full textAbstract:
There are two main techniques to convert written or printed text into digital format. The first technique is to create an image of written/printed text, but images are large in size so they require huge memory space to store, as well as text in image form cannot be undergo further processes like edit, search, copy, etc. The second technique is to use an Optical Character Recognition (OCR) system. OCR’s can read documents and convert manual text documents into digital text and this digital text can be processed to extract knowledge. A huge amount of Urdu language’s data is available in handwritten or in printed form that needs to be converted into digital format for knowledge acquisition. Highly cursive, complex structure, bi-directionality, and compound in nature, etc. make the Urdu language too complex to obtain accurate OCR results. In this study, supervised learning-based OCR system is proposed for Nastalique Urdu language. The proposed system evaluations under a variety of experimental settings apprehend 98.4% training results and 97.3% test results, which is the highest recognition rate ever achieved by any Urdu language OCR system. The proposed system is simple to implement especially in software front of OCR system also the proposed technique is useful for printed text as well as handwritten text and it will help in developing more accurate Urdu OCR’s software systems in the future.