To see the other types of publications on this topic, follow the link: Reconstruction de pixel.
Journal articles on the topic 'Reconstruction de pixel'
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 'Reconstruction de pixel.'
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
Rymarczyk, Tomasz, and Grzegorz Kłosowski. "Identification of moisture inside walls in buildings using machine learning and ensemble methods." International Journal of Applied Electromagnetics and Mechanics 69, no. 3 (2022): 375–88. http://dx.doi.org/10.3233/jae-210176.
Full textAbstract:
According to the article, locating moisture within the walls of buildings using electrical impedance tomography is discussed in detail. The algorithmic approach, whose role is to convert the input measurements into images, received excellent attention during the development process. Numerous models have been trained to generate tomographic images based on individual pixels in a given image based on machine learning methods. An array of categorisation data was then generated, which enabled the development of a classification model to solve the problem of optimal model selection for a given point on the screen. It was achieved in this manner by developing a pixel-oriented ensemble model (POE), the goal of which is to provide tomographic reconstructions of at least the same quality as homogeneous algorithmic approaches. Artificial neural networks (ANN), linear regression (LR), and the long short-term memory network (LSTM) were employed in the current research to get homogeneous machine learning results. An image reconstruction algorithm such as the ANN or the LR reconstructs the image pixel by pixel, which means that a different prediction model is trained for each image pixel. In the case of LSTM, a single network is responsible for creating the entire image. Then, using the POE algorithm, the best reconstruction method was fitted to each pixel of the output image while considering the measurement scenario provided to the program. As a result, each measurement consequences in a unique assignment of reconstructive procedures to individual pixels, which is different for each measurement. It is the capacity to maximise the selection of a prediction model while considering both a given pixel and a specific measurement vector that distinguishes the provided POE concept from other approaches.
2
Mantripragada, Kiran, Phuong D. Dao, Yuhong He, and Faisal Z. Qureshi. "The effects of spectral dimensionality reduction on hyperspectral pixel classification: A case study." PLOS ONE 17, no. 7 (2022): e0269174. http://dx.doi.org/10.1371/journal.pone.0269174.
Full textAbstract:
This paper presents a systematic study of the effects of hyperspectral pixel dimensionality reduction on the pixel classification task. We use five dimensionality reduction methods—PCA, KPCA, ICA, AE, and DAE—to compress 301-dimensional hyperspectral pixels. Compressed pixels are subsequently used to perform pixel classifications. Pixel classification accuracies together with compression method, compression rates, and reconstruction errors provide a new lens to study the suitability of a compression method for the task of pixel classification. We use three high-resolution hyperspectral image datasets, representing three common landscape types (i.e. urban, transitional suburban, and forests) collected by the Remote Sensing and Spatial Ecosystem Modeling laboratory of the University of Toronto. We found that PCA, KPCA, and ICA post greater signal reconstruction capability; however, when compression rates are more than 90% these methods show lower classification scores. AE and DAE methods post better classification accuracy at 95% compression rate, however their performance drops as compression rate approaches 97%. Our results suggest that both the compression method and the compression rate are important considerations when designing a hyperspectral pixel classification pipeline.
3
Yuri, Hercilia Mejía-Melgarejo, Patricia Villarreal-Dulcey Ofelia, and Arguello-Fuentes Henry. "Adjustable spatial resolution of compressive spectral images sensed by multispectral filter array-based sensors." Revista Facultad de Ingeniería –redin-, no. 78 (March 19, 2016): 89–98. https://doi.org/10.17533/udea.redin.n78a12.
Full textAbstract:
Spectral imaging systems capture spectral and spatial information from a scene to produce a spectral data cube. Technical progress has allowed developing multispectral filter array (MSFA)-based sensors in order to expand the reconstruction of more bands than RGB cameras. However, reconstructing the spectral image with traditional methods following a least squares or demosaicing approach is unfeasible. Some works in the literature implement multispectral demosaicing for reconstructing images with specific spatio-spectral resolution depending on the number of pixels in the detector and the filter mosaic. Recently, compressive sensing technique has been developed that allows reconstructing signals with fewer measurements than the traditional methods by using the sparse representation of a signal. The selection of neighborhoods pixels in the MSFA-based sensor to calculate the spectral response of a single pixel in the reconstructed spectralimages could improve the reconstruction, based on exploiting the sparse representation of the spectral images. This paper proposes two models for spectral images reconstruction from the selection of MSFA-based sensor measurements neighborhoods using the principle of compressive sensing. The spatial resolution of the reconstructed spectral images is adjusted depending the size of the neighborhood. To verify the effectiveness of the reconstruction models simulated measurements for synthetic spectral images and real spectral images based on MSFA are used. Ensembles of random dichroic and random band pass filters are used. The two approaches with traditional scheme reconstructions of mosaic filters are compared. The proposed methods improve the quality (PSNR) of the image reconstruction up 7 dB for real spectral images.
4
Hirata, Christopher M., and Christopher Merchant. "Pixel Centroid Characterization with Laser Speckle and Application to the Nancy Grace Roman Space Telescope Detector Arrays." Publications of the Astronomical Society of the Pacific 134, no. 1041 (2022): 115001. http://dx.doi.org/10.1088/1538-3873/ac99fe.
Full textAbstract:
Abstract The Nancy Grace Roman Space Telescope will use its wide-field instrument to carry out a suite of sky surveys in the near-infrared. Several of the science objectives of these surveys, such as the measurement of the growth of cosmic structure using weak gravitational lensing, require exquisite control of instrument-related distortions of the images of astronomical objects. Roman will fly new large-format (4 × 4 k) Teledyne H4RG-10 infrared detector arrays. This paper investigates whether the pixel centroids are located on a regular grid by projecting laser speckle patterns through a double slit aperture onto a non-flight detector array. We develop a method to reconstruct the pixel centroid offsets from the stochastic speckle pattern. Due to the orientation of the test setup, only x-offsets are measured here. We test the method both on simulations, and by injecting artificial offsets into the real images. We use cross-correlations of the reconstructions from different speckle realizations to determine how much of the variance in the pixel offset maps is signal (fixed to the detector) and how much is noise. After performing this reconstruction on 64 × 64 pixel patches, and fitting out the best-fit linear mapping from pixel index to position, we find that there are residual centroid offsets in the x (column) direction from a regular grid of 0.0107 pixels rms (excluding shifts of an entire row relative to another, which our speckle patterns cannot constrain). This decreases to 0.0097 pix rms if we consider residuals from a quadratic rather than linear mapping. These rms offsets include both the physical pixel offsets, as well as any apparent offsets due to crosstalk and remaining systematic errors in the reconstruction. We comment on the advantages and disadvantages of speckle scene measurements as a tool for characterizing the pixel-level behavior in astronomical detectors.
5
Ahmed, Ansari Vaqar, and Uday Pandit Khot. "An Efficient Motion Vector Recovery and Reconstruction Method for Spatiotemporal Video Error Concealment." International Journal of Computer Vision and Image Processing 9, no. 4 (2019): 28–48. http://dx.doi.org/10.4018/ijcvip.2019100103.
Full textAbstract:
In this article, an efficient spatiotemporal video error concealment (EC) based on motion vector (MV) recovery and a pixel reconstruction (PR) method is proposed. The pixel-based motion vector with partition (PMVP) is modified by using Mahalanobis distance (MD) rather than Euclidean distance (ED) for recovering MVs, as MD uses standard deviation and covariance of available pixels. Further, the MD gives more accuracy for non-square cluster compared to ED. This modified pixel-based motion vector with partition (MPMVP) algorithm is further upgrade by two different strategies. First, by using voting priority of available MVs based on the probabilities of similar directions. Second, by considering separate horizontal and vertical directions of available MVs in voting priority. For pixel reconstruction, modified spiral pixel reconstruction (MSPR) algorithm based on directional edge recovery method using minimum and maximum Mahalanobis distance from available pixels of surrounding MBs is proposed. Mahalanobis distance approach is most optimized similarity measure technique compared to other distance measurement approach to obtained lost motion vectors. These proposed EC techniques are compared with existing EC techniques like, SPR EC using ED, PMVP based EC with ED, and MV Interpolation by Zhou's method for various packet loss rates (PLRs) as 3%, 7%, 16%, 20% and quantization parameters (QPs) as 20, 24, 28, 32, 36. For total average in PLR of 3%, 7%, 16% and 20%, MSPR is having better PSNR compared to PMVP by 2.516, 2.29, 2.06 and 2.02 dB, respectively; and compared to SPR by 0.796, 0.718, 0.643 and 0.631 dB, respectively.
6
Alanazi, Turki M., and Paolo Mercorelli. "Precision Denoising in Medical Imaging via Generative Adversarial Network-Aided Low-Noise Discriminator Technique." Mathematics 12, no. 23 (2024): 3705. http://dx.doi.org/10.3390/math12233705.
Full textAbstract:
Medical imaging is significant for accurate diagnosis, and here, noise often degrades image quality, thus making it challenging to identify important information. Denoising is a component of traditional image pre-processing that helps prevent incorrect disease diagnosis. Mitigating the noise becomes difficult if there are differences in the low-level segment features. Therefore, a Generative Adversarial Network (GAN)-aided Low-Noise Discriminator (LND) is introduced to improve the denoising effectiveness in medical images with a balanced image resolution with noise mitigation. The LND function is a key that distinguishes between high- and low-noise areas based on segmented features, which are also achieved by tuning the peak signal-to-noise ratio (PSNR). Considering the training sequences, the LND-identified intervals lessen the sequences to improve the changes in pixel reconstruction. The generator function in this method is responsible for increasing the PSNR improvements over the different pixels cumulatively. The proposed method successfully improves the pixel reconstruction by 11.05% and PSNR by 9.75%, with 9.75% less reconstruction time and 13.11% less extraction error for the higher pixel distribution ratios than other contemporary methods.
7
Irum, Isma, Muhammad Sharif, Mussarat Yasmin, Mudassar Raza, and Faisal Azam. "A Noise Adaptive Approach to Impulse Noise Detection and Reduction." Nepal Journal of Science and Technology 15, no. 1 (2015): 67–76. http://dx.doi.org/10.3126/njst.v15i1.12016.
Full textAbstract:
A noise adaptive filter has been proposed in this study aiming to estimate the original image pixel values in the presence of impulse noise in monochromatic images. The proposed filter approach is noise adaptive that as the percentage of noise density increases in the image, the size of neighborhood in filtering window is also increased. Proposed approach comprises of two stages, one is impulse noise detection and the other is impulse noise reduction or cancellation. First stage is based on median and mean distance and thresholding whereas the second stage is based on reconstruction of the image using the values of neighboring pixels of the pixel under consideration detected as contaminated pixel by first stage. Reconstruction is done by estimating reference values using uncorrupted pixels in the neighborhood of pixel under consideration. The proposed method has been compared to various existing methods by using peak signal to noise ratio (PSNR) for measuring the objective quality strength. To measure the impulse noise detection the method has also been compared with other existing methods using the ratio of mis etection (MD) and false detection (FD).DOI: http://dx.doi.org/10.3126/njst.v15i1.12016 Nepal Journal of Science and TechnologyVol. 15, No.1 (2014) 67-76
8
Tian, Y., W. Zhou, Q. Wang, et al. "A novel silicon pixel sensor for beam monitoring applications at heavy-ion accelerators." Journal of Instrumentation 19, no. 04 (2024): C04039. http://dx.doi.org/10.1088/1748-0221/19/04/c04039.
Full textAbstract:
Abstract This paper describes a silicon pixel sensor for non-interceptive real-time beam monitoring at heavy-ion accelerators. The total size of the sensor is 4 mm × 5 mm. It has 64 (row) × 120 (column) square pixels, each single of which is in the size of 40 μm × 40 μm. With the exposed sensing pad, this sensor can directly collect the charge in the media over the pixels. The in-pixel circuit mainly consists of a low-noise Charge Sensitive Amplifier (CSA) to establish the signal for the energy reconstruction and a discriminator with a Time-to-Amplitude Converter (TAC) for the Time of Arrival (TOA) measurement. The analog signal from each pixel is accessible through time-shared multiplexing over the entire pixel array. This paper will discuss the design of this IMPix-S1 sensor.
9
Šperl, Ondřej, and Jan Sýkora. "Reconstruction of concrete morphology using deep learning." Acta Polytechnica CTU Proceedings 49 (November 21, 2024): 85–91. https://doi.org/10.14311/app.2024.49.0085.
Full textAbstract:
In this contribution, the concrete morphology is reconstructed with a simple algorithm selecting a pixel value based on the small set of surrounding pixels. A deep neural network (DNN) is used as a classifier, and the authors focus on studying different DNN architectures. The performance of the proposed algorithm is evaluated on several statistical descriptors and the grain size distributioncurve.
10
Diógenes, A. N., L. O. E. Dos Santos, C. P. Fernandes, A. C. Moreira, and C. R. Apolloni. "POROUS MEDIA MICROSTRUCTURE RECONSTRUCTION USING PIXEL-BASED AND OBJECT-BASED SIMULATED ANNEALING – COMPARISON WITH OTHER RECONSTRUCTION METHODS." Revista de Engenharia Térmica 8, no. 2 (2009): 35. http://dx.doi.org/10.5380/reterm.v8i2.61896.
Full textAbstract:
In this contribution the issue of the stochastic reconstruction of particulatemedia from 2D photomicrographic images is addressed with particular reference to pore space connectivity. The reconstruction of porous bodies in 2D or 3D space was achieved by using simulated annealing techniques. Two methods were proposed to reconstruct a well connected pore space. The first, named PSA (Pixel-based Simulated Annealing), a pixel-movement based, three constraints were found to be necessary for the successful reconstruction of well connected pore space: the two-pointcorrelation function, the d3-4 distance transform distribution and the linealpath function for the pore phase. The second, named OSA (Object-based Simulated Annealing), only constrains the two-point correlation function. Following several researches which tried to reconstruct porous media using pixel-movement based simulated techniques, we propose a new parameter to add a microstructure descriptor, but we also propose a new technique, based in moving the microstructure grains (spheres) instead of the pixels. Both methods were applied to reconstruct reservoir rocks microstructures, and the 2D and 3D results were compared with microstructures reconstructed by truncated Gaussian methods. The PSA resulted in microstructures characterized by poor pore space connectivity, and by artificial patterns, while the OSA reconstructed microstructures with good pore space connectivity. These results indicate that the OSA method can reconstruct better microstructures than the present methods.
11
Li, L., L. Zhang, J. N. Dong, J. Liu, and M. Wang. "Characterization of a CMOS pixel sensor for charged particle tracking." Journal of Instrumentation 16, no. 12 (2021): P12016. http://dx.doi.org/10.1088/1748-0221/16/12/p12016.
Full textAbstract:
Abstract A prototype of the CMOS pixel sensor named Supix-1 has been fabricated and tested in order to investigate the feasibility of a pixelated tracker for a proposed Higgs factory, namely, the Circular Electron-Positron Collider (CEPC). The sensor, taped out with a 180 nm CMOS Image Sensor (CIS) process, consists of nine different pixel arrays varying in pixel pitches, diode sizes and geometries in order to study the particle detection performance of enlarged pixels. The test was carried out with a 55Fe radioactive source. Two soft X-ray peaks observed were used to calibrate the charge to voltage factor of the sensor. The pixel-wise equivalent noise charge, charge collection efficiency and signal-to-noise ratio were evaluated. A reconstruction method for clustering pixels of a signal has been developed and the cluster-wise performance was studied as well. The test results show that pixels with the area as large as of 21 × 84 μm have satisfactory noise level and charge collection performance, meeting general requirements for a pixel sensor. This contribution demonstrates that the CMOS pixel sensor with enlarged pitches, using the CIS technology, can be used in tracking for upcoming collider detectors akin to the CEPC.
12
Fager, R. S., K. V. Peddanarappagari, and G. N. Kumar. "Pixel-based reconstruction (PBR) promising simultaneous techniques for CT reconstructions." IEEE Transactions on Medical Imaging 12, no. 1 (1993): 4–9. http://dx.doi.org/10.1109/42.222660.
Full text
13
Pastuszak, Grzegorz. "Subsampling of 3D Pixel Blocks as a Video Compression Method for Analog Transmission." Electronics 12, no. 12 (2023): 2641. http://dx.doi.org/10.3390/electronics12122641.
Full textAbstract:
Hybrid digital–analog transmission of video signals enables flexibility in dividing video information into two parts to utilize the available bandwidth better. This study proposes a compression scheme to reduce the utilized bandwidth. The scheme uses different subsampling in three-dimensional (3D) blocks, where subsampling factors are selected to minimize reconstruction distortion. The study evaluates various methods for subsampling and reconstruction to find the best combination in terms of reconstruction quality and complexity. Results show that medium-quality reconstructions can be obtained for compression ratios of about 0.125–0.3 samples per pixel.
14
Ahmed, Ansari Vaqar, and Uday Pandit Khot. "An Efficient Generalized Error Concealment in Video Codec." International Journal of Computer Vision and Image Processing 10, no. 4 (2020): 1–28. http://dx.doi.org/10.4018/ijcvip.2020100101.
Full textAbstract:
Efficient error concealment (EC) predictor can recover more significant features or structures of entire lost MBs using a pre-transmission algorithm (PTA) with convolutional neural network (CNN) and fuzzy reasoning to select appropriate EC for reconstruction in generalized video-codec compression scheme such as H.264/H.265, etc. Here, the pixel-based motion vector with partition (PMVP) algorithm is modified by using Mahalanobis distance (MD) rather than Euclidean distance (ED) for better MVs recovery. This modified pixel-based motion vector with partition (MPMVP) algorithm is upgraded by two different strategies: one by using voting priority of available MVs based on the probabilities of similar directions and the second by considering separate horizontal and vertical directions of available MVs in voting priority. Similarly, a modified spiral pixel reconstruction (MSPR) algorithm based on directional edge recovery method using minimum and maximum MD from available pixels of surrounding MBs is proposed. The proposed PTA-based modified ECs gives 20.4%, 3.47%, and 6.66% increase in PSNR.
15
Wu, Wei, Luoqi Ge, Jiancheng Luo, Ruohong Huan, and Yingpin Yang. "A Spectral–Temporal Patch-Based Missing Area Reconstruction for Time-Series Images." Remote Sensing 10, no. 10 (2018): 1560. http://dx.doi.org/10.3390/rs10101560.
Full textAbstract:
Clouds, cloud shadows (CCS), and numerous other factors will cause a missing data problem in passive remote sensing images. A well-known reconstruction method is the selection of a similar pixel (with an additional clear reference image) from the remaining clear part of an image to replace the missing pixel. Due to the merit of filling the missing value using a pixel acquired on the same image with the same sensor and the same date, this method is suitable for time-series applications when a time-series profile-based similar measure is utilized for selecting the similar pixel. Since the similar pixel is independently selected, the improper reference pixel or various accuracies obtained by different land covers causes the problem of salt-and-pepper noise in the reconstructed part of an image. To overcome these problems, this paper presents a spectral–temporal patch (STP)-based missing area reconstruction method for time-series images. First, the STP, the pixels of which have similar spectral and temporal evolution characteristics, is extracted using multi-temporal image segmentation. However, some STP have Missing Observations (STPMO) in the time series, which should be reconstructed. Next, for an STPMO, the most similar STP is selected as the reference STP; then, the mean and standard deviation of the STPMO is predicted using a linear regression method with the reference STP. Finally, the textural information, which is denoted by the spatial configuration of color or intensities of neighboring pixels, is extracted from the clear temporal-adjacent STP and “injected” into the missing area to obtain synthetic cloud-free images. We performed an STP-based missing area reconstruction experiment in Jiangzhou, Chongzuo, Guangxi with time-series images acquired by wide field view (WFV) onboard Chinese Gao Fen 1 on 12 different dates. The results indicate that the proposed method can effectively recover the missing information without salt-and-pepper noise in the reconstructed area; also, the reconstructed part of the image is consistent with the clear part without a false edge. The results confirm that the spectral information from the remaining clear part of the same image and textural information from the temporal-adjacent image can create seamless time-series images.
16
Braach, Justus, Eric Buschmann, Dominik Dannheim, et al. "Performance of the FASTPIX Sub-Nanosecond CMOS Pixel Sensor Demonstrator." Instruments 6, no. 1 (2022): 13. http://dx.doi.org/10.3390/instruments6010013.
Full textAbstract:
Within the ATTRACT FASTPIX project, a monolithic pixel sensor demonstrator chip has been developed in a modified 180 nm CMOS imaging process, targeting sub-nanosecond timing measurements for single ionizing particles. It features a small collection electrode design on a 25 micron thick epitaxial layer and contains 32 mini matrices of 68 hexagonal pixels each, with pixel pitches ranging from 8.66 to 20 micron. Four pixels are transmitting an analog output signal and 64 are transmitting binary hit information. Various design variations are explored, aiming at accelerating the charge collection and making the timing of the charge collection more uniform over the pixel area. Signal treatment of the analog waveforms, as well as reconstruction of time and charge information, is carried out off-chip. This contribution introduces the design of the sensor and readout system and presents the first performance results for 10 μm and 20 μm pixel pitch achieved in measurements with particle beams.
17
Liang, Shi Guo, Ou Yang Yi, and Hui Wang. "Fast Multi-Layer 3D Reconstruction Algorithm." Advanced Materials Research 267 (June 2011): 827–30. http://dx.doi.org/10.4028/www.scientific.net/amr.267.827.
Full textAbstract:
A fast multi-layer 3d reconstruction algorithm is proposed to realize 3d body surface layer. Based on multi-layer surface reconstructing the shortest triangle line algorithm are proposed. In order to achieve more rapid reconstruction, a fast multi-layer 3D reconstruction algorithm is proposed. When the points on the layers having some errors, or have some offset, during the reconstruction of layered, it will automatically adjust for each pixel value of the selected layer, so that reconstruction process can be completed faster and more accurately . We give optimization method to realize fast reconstruction under real-time environmental.
18
Liu, Fei, Xiaoming Zhu, Pingfa Feng, and Long Zeng. "Anomaly Detection via Progressive Reconstruction and Hierarchical Feature Fusion." Sensors 23, no. 21 (2023): 8750. http://dx.doi.org/10.3390/s23218750.
Full textAbstract:
The main challenges in reconstruction-based anomaly detection include the breakdown of the generalization gap due to improved fitting capabilities and the overfitting problem arising from simulated defects. To overcome this, we propose a new method called PRFF-AD, which utilizes progressive reconstruction and hierarchical feature fusion. It consists of a reconstructive sub-network and a discriminative sub-network. The former achieves anomaly-free reconstruction while maintaining nominal patterns, and the latter locates defects based on pre- and post-reconstruction information. Given defective samples, we find that adopting a progressive reconstruction approach leads to higher-quality reconstructions without compromising the assumption of a generalization gap. Meanwhile, to alleviate the network’s overfitting of synthetic defects and address the issue of reconstruction errors, we fuse hierarchical features as guidance for discriminating defects. Moreover, with the help of an attention mechanism, the network achieves higher classification and localization accuracy. In addition, we construct a large dataset for packaging chips, named GTanoIC, with 1750 real non-defective samples and 470 real defective samples, and we provide their pixel-level annotations. Evaluation results demonstrate that our method outperforms other reconstruction-based methods on two challenging datasets: MVTec AD and GTanoIC.
19
Gustafson, Steven C., Gordon R. Little, John S. Loomis, and Todd S. Puterbaugh. "Optimal reconstruction of missing-pixel images." Applied Optics 31, no. 32 (1992): 6829. http://dx.doi.org/10.1364/ao.31.006829.
Full text
20
Wei, Ziran, Jianlin Zhang, Wei Du, and Zhiruo Wang. "Real-time single-pixel video imaging based on deep learning." International Journal of Emerging Technologies and Advanced Applications 1, no. 12 (2025): 1–5. https://doi.org/10.62677/ijetaa.2412130.
Full textAbstract:
The emergence of compressed sensing (CS) theory has enabled the development of single-pixel cameras that achieve high-resolution imaging using a single photodetector. However, traditional CS reconstruction algorithms require significant computational time and face an inherent trade-off between imaging resolution and frame rate, limiting current single-pixel cameras to static scene imaging. A key challenge lies in achieving real-time single-pixel imaging with both high frame rate and high resolution. This paper proposes a real-time single-pixel imaging technology based on deep learning. We design a deep convolutional neural network architecture incorporating residual networks to simulate the measurement and reconstruction process of CS-based single-pixel imaging. The network is trained on an image dataset and subsequently deployed for single-pixel imaging. The trained network can complete image reconstruction at a low sampling rate with minimal latency, enabling real-time single-pixel video capture at 128×128 resolution with 33 frames per second (fps) at a 4\% sampling rate. Furthermore, we implement a four-channel parallel signal processing method to achieve real-time single-pixel imaging video at 256×256 resolution at 33 fps.
21
Zhao, Wenjing, Lei Gao, Aiping Zhai, and Dong Wang. "Comparison of Common Algorithms for Single-Pixel Imaging via Compressed Sensing." Sensors 23, no. 10 (2023): 4678. http://dx.doi.org/10.3390/s23104678.
Full textAbstract:
Single-pixel imaging (SPI) uses a single-pixel detector instead of a detector array with a lot of pixels in traditional imaging techniques to realize two-dimensional or even multi-dimensional imaging. For SPI using compressed sensing, the target to be imaged is illuminated by a series of patterns with spatial resolution, and then the reflected or transmitted intensity is compressively sampled by the single-pixel detector to reconstruct the target image while breaking the limitation of the Nyquist sampling theorem. Recently, in the area of signal processing using compressed sensing, many measurement matrices as well as reconstruction algorithms have been proposed. It is necessary to explore the application of these methods in SPI. Therefore, this paper reviews the concept of compressive sensing SPI and summarizes the main measurement matrices and reconstruction algorithms in compressive sensing. Further, the performance of their applications in SPI through simulations and experiments is explored in detail, and then their advantages and disadvantages are summarized. Finally, the prospect of compressive sensing with SPI is discussed.
22
Kim, Youngjun, Jiyong Park, Jungsik Koo, Min-Chul Lee, and Myungjin Cho. "Optimum Pitch of Volumetric Computational Reconstruction in Integral Imaging." Electronics 13, no. 23 (2024): 4595. http://dx.doi.org/10.3390/electronics13234595.
Full textAbstract:
In this paper, we propose a method for how to find the optimum pitch of volumetric computational reconstruction (VCR) in integral imaging. In conventional VCR, the pixel shifts between elemental images are quantized due to pixel-based processing. As a result, quantization errors may occur during three-dimensional (3D) reconstruction in integral imaging. This may cause the degradation of the visual quality and depth resolution of the reconstructed 3D image. To overcome this problem, we propose a method to find the optimum pitch for VCR in integral imaging. To minimize the quantization error in VCR, the shifting pixels are defined as a natural number. Using this characteristic, we can find the optimum pitch of VCR in integral imaging. To demonstrate the feasibility of our method, we conducted simulations and optical experiments with performance metrics such as the peak-signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).
23
Gao, Han, Guifeng Zhang, Min Huang, et al. "Three-Dimensional Pulsed-Laser Imaging via Compressed Sensing Reconstruction Based on Proximal Momentum-Gradient Descent." Remote Sensing 16, no. 23 (2024): 4601. https://doi.org/10.3390/rs16234601.
Full textAbstract:
Compressed sensing (CS) is a promising approach to enhancing the spatial resolution of images obtained from few-pixel array sensors in three-dimensional (3D) laser imaging scenarios. However, traditional CS-based methods suffer from insufficient range resolutions and poor reconstruction quality at low CS sampling ratios. To solve the CS reconstruction problem under the time-of-flight (TOF)-based pulsed-laser imaging framework, a CS algorithm based on proximal momentum-gradient descent (PMGD) is proposed in this paper. To improve the accuracy of the range and intensity reconstructed from overlapping samples, the PMGD framework is developed by introducing an extra fidelity term based on a pulse shaping method, in which the reconstructed echo signal obtained from each sensor pixel can be refined during the iterative reconstruction process. Additionally, noise level estimation with the fast Johnson–Lindenstrauss transform is adopted, enabling the integration of a denoising neural network into PMGD to further enhance reconstruction accuracy. The simulation results obtained on real datasets demonstrate that the proposed method can yield more accurate reconstructions and significant improvements over the recently developed CS-based approaches.
24
Xu, Mingzhu, Rong Shang, Jing M. Chen, and Lingfang Zeng. "LACC2.0: Improving the LACC Algorithm for Reconstructing Satellite-Derived Time Series of Vegetation Biochemical Parameters." Remote Sensing 15, no. 13 (2023): 3277. http://dx.doi.org/10.3390/rs15133277.
Full textAbstract:
The locally adjusted cubic-spline capping (LACC) algorithm is well recognized for its effectiveness in the global time series reconstruction of vegetation biophysical and biochemical parameters. However, in its application, we often encounter issues, such as identifying positively biased outliers for vegetation biochemical parameters and reducing the influence of long consecutive gaps. In this study, we improved the LACC algorithm to address the above two issues by (1) incorporating a procedure to remove outliers and (2) integrating the spatial information of neighboring pixels for large data gap filling. To evaluate the performance of the new version of LACC (namely LACC2.0), leaf chlorophyll content (LCC) was taken as an example. A reference LCC curve was generated for each pixel of the global map as the true value for global evaluation, and a time series of LCC with real gaps in the original data for each pixel was created by adding Gaussian noises into observations for testing the effectiveness of time series reconstruction algorithms. Results showed that the percentage of pixels with an RMSE smaller than 5 μg/cm2 was improved from 81.2% in LACC to 96.4% in LACC2.0, demonstrating that LACC2.0 had the potential to provide a better reconstruction of global daily satellite-derived vegetation biochemical parameters. This finding highlights the significance of outlier removal and spatial-temporal fusion to enhance the accuracy and reliability of time series reconstruction.
25
Carvalho, Francelino Freitas, Carlos Augusto de Moraes Cruz, Greicy C. Marques, and Thiago Brito Bezerra. "A Novel Hybrid CMOS Pixel-Cluster for Local Light Angle, Polarization and Intensity Detection with Determination of Stokes Parameters." Journal of Integrated Circuits and Systems 13, no. 2 (2018): 1–10. http://dx.doi.org/10.29292/jics.v13i2.7.
Full textAbstract:
Detecting local light incident angle is a desirable feature for CMOS image sensors for 3D image reconstruction purposes and depth sensing. Advances in the CMOS technologies in the last years have enabled integrated solutions to perform such a job. However, it is still not viable to implement such a feature in regular CMOS image sensors due to the great number of pixels in a cluster to perform incident angle detection. In this paper, a hybrid cluster with only four pixels, instead of eight pixels of previous solutions, that is able to detect both local light intensity, incident angle and Stokes parameters. The technique to detect local incident angle is widely exploited in the literature. Three novelties are explored in this work, the first is the new paradigm in polarization cluster-pixel design, the second is the extended ability of metal shielded pixels to detect both the local light angle and intensity and the third is to determine the Stokes parameters through this sensor. SPICE simulation results show that the existing Quadrature Pixel Cluster - QPC and Polarization Pixel Cluster - PPC models are in accordance with experimental results presented in the literature, and thus it was possible to demonstrate similar behavior in the new proposed pixel cluster.
26
Yu, Zihan, Cheng Zhang, Derek Nowrouzezahrai, Zhao Dong, and Shuang Zhao. "Efficient Differentiation of Pixel Reconstruction Filters for Path-Space Differentiable Rendering." ACM Transactions on Graphics 41, no. 6 (2022): 1–16. http://dx.doi.org/10.1145/3550454.3555500.
Full textAbstract:
Pixel reconstruction filters play an important role in physics-based rendering and have been thoroughly studied. In physics-based differentiable rendering, however, the proper treatment of pixel filters remains largely under-explored. We present a new technique to efficiently differentiate pixel reconstruction filters based on the path-space formulation. Specifically, we formulate the pixel boundary integral that models discontinuities in pixel filters and introduce new antithetic sampling methods that support differentiable path sampling methods, such as adjoint particle tracing and bidirectional path tracing. We demonstrate both the need and efficacy of antithetic sampling when estimating this integral, and we evaluate its effectiveness across several differentiable- and inverse-rendering settings.
27
Henao-Londoño, J. C., J. C. Riaño-Rojas, J. B. Gómez-Mendoza, and E. Restrepo-Parra. "3D Stereo Reconstruction of SEM Images." Modern Applied Science 12, no. 12 (2018): 57. http://dx.doi.org/10.5539/mas.v12n12p57.
Full textAbstract:
In this work is proposed a new fully automated methodology using computer vision and dynamic programming to obtain a 3D reconstruction model of surfaces using scanning electron microscope (SEM) images based on stereovision. The horizontal stereo matching step is done with a robust and efficient algorithm based on semi-global matching. The cost function used in this study is very simple since the brightness and contrast change of corresponding pixels is negligible for the small tilt involved in stereo SEM. It is used a sum of absolute differences (SAD) over a variable pixel size window. Since it relies on dynamic programming, the matching algorithm uses an occlusion parameter which penalizes large depth discontinuities and, in practice, smooths the disparity map and the corresponding reconstructed surface. This step yields a disparity map, i.e. the differences between the horizontal coordinates of the matching points in the stereo images. The horizontal disparity map is finally converted into heights according to the SEM acquisition parameters: tilt angle, image magnification and pixel size. A validation test was first performed using as reference a microscopic grid with manufacturer specifications. Finally, with the 3D model are proposed some applications in materials science as roughness parameters estimation and wear measurements.
28
Liu, Feng Lin, Quan Kang, and Bing He. "Permissible Deviation of Rotation Center Based on Fan-Beam Projection ICT System." Advanced Materials Research 452-453 (January 2012): 21–30. http://dx.doi.org/10.4028/www.scientific.net/amr.452-453.21.
Full textAbstract:
For ICT wide fan-beam scanning, there is a geometrical supposition that the object rotation center and the radiation source center intersect the image reconstruction center. In practice, the existing intersection deviation has influence on the image reconstruction precision. The image reconstruction mathematical model for shifted rotation center was established, and the relationship between the deviation error and reconstructed image precision was studied by simulation. As a result, for 512×512 CT reconstructed image, there is no distinctive difference between the reference image and the reconstructed image with eccentricity 0.1 pixels; however, with 0.2 pixels or more, the difference is obvious. So, for 512×512 CT image, the maximum permissible deviation of the rotation center is within 0.1 pixel dimension.
29
Ma, Chenxi. "Uncertainty-Aware GAN for Single Image Super Resolution." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 5 (2024): 4071–79. http://dx.doi.org/10.1609/aaai.v38i5.28201.
Full textAbstract:
Generative adversarial network (GAN) has become a popular tool in the perceptual-oriented single image super-resolution (SISR) for its excellent capability to hallucinate details. However, the performance of most GAN-based SISR methods is impeded due to the limited discriminative ability of their discriminators. In specific, these discriminators only focus on the global image reconstruction quality and ignore the more fine-grained reconstruction quality for constraining the generator, as they predict the overall realness of an image instead of the pixel-level realness. Here, we first introduce the uncertainty into the GAN and propose an Uncertainty-aware GAN (UGAN) to regularize SISR solutions, where the challenging pixels with large reconstruction uncertainty and importance (e.g., texture and edge) are prioritized for optimization. The uncertainty-aware adversarial training strategy enables the discriminator to capture the pixel-level SR uncertainty, which constrains the generator to focus on image areas with high reconstruction difficulty, meanwhile, it improves the interpretability of the SR. To balance weights of multiple training losses, we introduce an uncertainty-aware loss weighting strategy to adaptively learn the optimal loss weights. Extensive experiments demonstrate the effectiveness of our approach in extracting the SR uncertainty and the superiority of the UGAN over the state-of-the-arts in terms of the reconstruction accuracy and perceptual quality.
30
Rizvi, Saad, Jie Cao, Kaiyu Zhang, and Qun Hao. "Improving Imaging Quality of Real-time Fourier Single-pixel Imaging via Deep Learning." Sensors 19, no. 19 (2019): 4190. http://dx.doi.org/10.3390/s19194190.
Full textAbstract:
Fourier single pixel imaging (FSPI) is well known for reconstructing high quality images but only at the cost of long imaging time. For real-time applications, FSPI relies on under-sampled reconstructions, failing to provide high quality images. In order to improve imaging quality of real-time FSPI, a fast image reconstruction framework based on deep learning (DL) is proposed. More specifically, a deep convolutional autoencoder network with symmetric skip connection architecture for real time 96 × 96 imaging at very low sampling rates (5–8%) is employed. The network is trained on a large image set and is able to reconstruct diverse images unseen during training. The promising experimental results show that the proposed FSPI coupled with DL (termed DL-FSPI) outperforms conventional FSPI in terms of image quality at very low sampling rates.
31
Zhao, Genping, Fei Li, Xiuwei Zhang, Kati Laakso, and Jonathan Cheung-Wai Chan. "Archetypal Analysis and Structured Sparse Representation for Hyperspectral Anomaly Detection." Remote Sensing 13, no. 20 (2021): 4102. http://dx.doi.org/10.3390/rs13204102.
Full textAbstract:
Hyperspectral images (HSIs) often contain pixels with mixed spectra, which makes it difficult to accurately separate the background signal from the anomaly target signal. To mitigate this problem, we present a method that applies spectral unmixing and structure sparse representation to accurately extract the pure background features and to establish a structured sparse representation model at a sub-pixel level by using the Archetypal Analysis (AA) scheme. Specifically, spectral unmixing with AA is used to unmix the spectral data to obtain representative background endmember signatures. Moreover the unmixing reconstruction error is utilized for the identification of the target. Structured sparse representation is also adopted for anomaly target detection by using the background endmember features from AA unmixing. Moreover, both the AA unmixing reconstruction error and the structured sparse representation reconstruction error are integrated together to enhance the anomaly target detection performance. The proposed method exploits background features at a sub-pixel level to improve the accuracy of anomaly target detection. Comparative experiments and analysis on public hyperspectral datasets show that the proposed algorithm potentially surpasses all the counterpart methods in anomaly target detection.
32
Rankin, John, Fabio Muleri, Alessandro Di Marco, et al. "Equalizing the Pixel Response of the Imaging Photoelectric Polarimeter Onboard the IXPE Mission." Astronomical Journal 165, no. 5 (2023): 186. http://dx.doi.org/10.3847/1538-3881/acc38e.
Full textAbstract:
Abstract The Gas Pixel Detector is a gas detector, sensitive to the polarization of X-rays, currently flying onboard the Imaging X-ray Polarimetry Explorer (IXPE)—the first observatory dedicated to X-ray polarimetry. It detects X-rays and their polarization by imaging the ionization tracks generated by photoelectrons absorbed in the sensitive volume, and then reconstructing the initial direction of the photoelectrons. The primary ionization charge is multiplied and ultimately collected on a finely pixellated ASIC specifically developed for X-ray polarimetry. The signal of individual pixels is processed independently and gain variations can be substantial, of the order of 20%. Such variations need to be equalized to correctly reconstruct the track shape, and therefore its polarization direction. The method to do such equalization is presented here and is based on the comparison between the mean charge of a pixel with respect to the other pixels for equivalent events. The method is shown to finely equalize the response of the detectors onboard IXPE, allowing a better track reconstruction and energy resolution, and can in principle be applied to any imaging detector based on tracks.
33
Yin, Zhye, Kedar Khare, and Bruno De Man. "Parametric boundary reconstruction algorithm for industrial CT metrology application." Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics 17, no. 2 (2009): 115–33. http://dx.doi.org/10.3233/xst-2009-021700217.
Full textAbstract:
High-energy X-ray computed tomography (CT) systems have been recently used to produce high-resolution images in various nondestructive testing and evaluation (NDT/NDE) applications. The accuracy of the dimensional information extracted from CT images is rapidly approaching the accuracy achieved with a coordinate measuring machine (CMM), the conventional approach to acquire the metrology information directly. On the other hand, CT systems generate the sinogram which is transformed mathematically to the pixel-based images. The dimensional information of the scanned object is extracted later by performing edge detection on reconstructed CT images. The dimensional accuracy of this approach is limited by the grid size of the pixel-based representation of CT images since the edge detection is performed on the pixel grid. Moreover, reconstructed CT images usually display various artifacts due to the underlying physical process and resulting object boundaries from the edge detection fail to represent the true boundaries of the scanned object. In this paper, a novel algorithm to reconstruct the boundaries of an object with uniform material composition and uniform density is presented. There are three major benefits in the proposed approach. First, since the boundary parameters are reconstructed instead of image pixels, the complexity of the reconstruction algorithm is significantly reduced. The iterative approach, which can be computationally intensive, will be practical with the parametric boundary reconstruction. Second, the object of interest in metrology can be represented more directly and accurately by the boundary parameters instead of the image pixels. By eliminating the extra edge detection step, the overall dimensional accuracy and process time can be improved. Third, since the parametric reconstruction approach shares the boundary representation with other conventional metrology modalities such as CMM, boundary information from other modalities can be directly incorporated as prior knowledge to improve the convergence of an iterative approach. In this paper, the feasibility of parametric boundary reconstruction algorithm is demonstrated with both simple and complex simulated objects. Finally, the proposed algorithm is applied to the experimental industrial CT system data.
34
Liang, Qi-Hang, Zi-Le Zhang, Xu-Kai Wang, Ya-Nan Zhao, and Su-Heng Zhang. "Single-pixel complex-amplitude imaging based on untrained complex-valued convolutional neural network." Optics Express 32, no. 17 (2024): 29656. http://dx.doi.org/10.1364/oe.532417.
Full textAbstract:
Single-pixel imaging is advancing rapidly in complex-amplitude imaging. However, reconstructing high-quality images demands significant acquisition and heavy computation, making the entire imaging process time-consuming. Here we propose what we believe to be a novel single-pixel complex-amplitude imaging (SCI) scheme using a complex-valued convolutional neural network for image reconstruction. The proposed sheme does not need to pre-train on any labeled data, and can quickly reconstruct high-quality complex-amplitude images with the randomly initialized network only under the constraints of the physical model. Simulation and experimental results show that the proposed scheme is effective and feasible, and can achieve a good balance between efficiency and quality. We believe that this work provides a new image reconstruction framework for SCI, and paves the way for its practical applications.
35
Jiang, Xinding, Ziyi Tong, Zhongyang Yu, et al. "Fourier Single-Pixel Imaging Based on Online Modulation Pattern Binarization." Photonics 10, no. 9 (2023): 963. http://dx.doi.org/10.3390/photonics10090963.
Full textAbstract:
Down-sampling Fourier single-pixel imaging is typically achieved by truncating the Fourier spectrum, where exclusively the low-frequency Fourier coefficients are extracted while discarding the high-frequency components. However, the truncation of the Fourier spectrum can lead to an undesired ringing effect in the reconstructed result. Moreover, the original Fourier single-pixel imaging necessitated grayscale Fourier basis patterns for illumination. This requirement limits imaging speed because digital micromirror devices (DMDs) generate grayscale patterns at a lower refresh rate. In order to solve the above problem, a fast and high-quality Fourier single-pixel imaging reconstruction method is proposed in the paper. In the method, the threshold binarization of the Fourier base pattern is performed online to improve the DMD refresh rate, and the reconstruction quality of Fourier single-pixel imaging at a low-sampling rate is improved by generating an adversarial network. This method enables fast reconstruction of target images with higher quality despite low-sampling rates. Compared with conventional Fourier single-pixel imaging, numerical simulation and experimentation demonstrate the effectiveness of the proposed method. Notably, this method is particularly significant for fast Fourier single-pixel imaging applications.
36
Kortelainen, Matti J., Martin Kwok, Taylor Childers, Alexei Strelchenko, and Yunsong Wang. "Porting CMS Heterogeneous Pixel Reconstruction to Kokkos." EPJ Web of Conferences 251 (2021): 03034. http://dx.doi.org/10.1051/epjconf/202125103034.
Full textAbstract:
Programming for a diverse set of compute accelerators in addition to the CPU is a challenge. Maintaining separate source code for each architecture would require lots of effort, and development of new algorithms would be daunting if it had to be repeated many times. Fortunately there are several portability technologies on the market such as Alpaka, Kokkos, and SYCL. These technologies aim to improve the developer’s productivity by making it possible to use the same source code for many different architectures. In this paper we use heterogeneous pixel reconstruction code from the CMS experiment at the CERNL LHC as a realistic use case of a GPU-targeting HEP reconstruction software, and report experience from prototyping a portable version of it using Kokkos. The development was done in a standalone program that attempts to model many of the complexities of a HEP data processing framework such as CMSSW. We also compare the achieved event processing throughput to the original CUDA code and a CPU version of it.
37
Liu, Ruifeng, Shupeng Zhao, Pei Zhang, Hong Gao, and Fuli Li. "Complex wavefront reconstruction with single-pixel detector." Applied Physics Letters 114, no. 16 (2019): 161901. http://dx.doi.org/10.1063/1.5087094.
Full text
38
Latorre-Carmona, Pedro, V. Javier Traver, J. Salvador Sánchez, and Enrique Tajahuerce. "Online reconstruction-free single-pixel image classification." Image and Vision Computing 86 (June 2019): 28–37. http://dx.doi.org/10.1016/j.imavis.2019.03.007.
Full text
39
Dmitriev, E. A., and V. V. Myasnikov. "Possibility estimation of 3D scene reconstruction from multiple images." Information Technology and Nanotechnology, no. 2391 (2019): 293–96. http://dx.doi.org/10.18287/1613-0073-2019-2391-293-296.
Full textAbstract:
This paper presents a pixel-by-pixel possibility estimation of 3D scene reconstruction from multiple images. This method estimates conjugate pairs number with convolutional neural networks for further 3D reconstruction using classic approach. We considered neural networks that showed good results in semantic segmentation problem. The efficiency criterion of an algorithm is the resulting estimation accuracy. We conducted all experiments on images from Unity 3d program. The results of experiments showed the effectiveness of our approach in 3D scene reconstruction problem.
40
Rueda-Chacón, Hoover Fabián, Cesar Augusto Vargas-García, and Henry Arguello-Fuentes. "Single-pixel optical sensing architecture for compressive hyperspectral imaging." Revista Facultad de Ingeniería Universidad de Antioquia, no. 73 (November 13, 2014): 134–43. http://dx.doi.org/10.17533/udea.redin.17312.
Full textAbstract:
Compressive hyperspectral imaging systems (CSI) capture the threedimensional (3D) information of a scene by measuring two-dimensional (2D) coded projections in a Focal Plane Array (FPA). These projections are then exploited by means of an optimization algorithm to obtain an estimation of the underlying 3D information. The quality of the reconstructions is highly dependent on the resolution of the FPA detector, which cost grows exponentially with the resolution. High-resolution low-cost reconstructions are thus desirable. This paper proposes a Single Pixel Compressive Hyperspectral Imaging Sensor (SPHIS) to capture and reconstruct hyperspectral images. This optical architecture relies on the use of multiple snapshots of two timevarying coded apertures and a dispersive element. Several simulations with two different databases show promising results as the reliable reconstruction of a hyperspectral image can be achieved by using as few as just the 30% of its voxels.
41
Freitas Carvalho, Francelino, Carlos Augusto de Moraes Cruz, Greicy Costa Marques, and Kayque Martins Cruz Damasceno. "Angular Light, Polarization and Stokes Parameters Information in a Hybrid Image Sensor with Division of Focal Plane." Sensors 20, no. 12 (2020): 3391. http://dx.doi.org/10.3390/s20123391.
Full textAbstract:
Targeting 3D image reconstruction and depth sensing, a desirable feature for complementary metal oxide semiconductor (CMOS) image sensors is the ability to detect local light incident angle and the light polarization. In the last years, advances in the CMOS technologies have enabled dedicated circuits to determine these parameters in an image sensor. However, due to the great number of pixels required in a cluster to enable such functionality, implementing such features in regular CMOS imagers is still not viable. The current state-of-the-art solutions require eight pixels in a cluster to detect local light intensity, incident angle and polarization. The technique to detect local incident angle is widely exploited in the literature, and the authors have shown in previous works that it is possible to perform the job with a cluster of only four pixels. In this work, the authors explore three novelties: a mean to determine three of four Stokes parameters, the new paradigm in polarization cluster-pixel design, and the extended ability to detect both the local light angle and intensity. The features of the proposed pixel cluster are demonstrated through simulation program with integrated circuit emphasis (SPICE) of the regular Quadrature Pixel Cluster and Polarization Pixel Cluster models, the results of which are compliant with experimental results presented in the literature.
42
Hong, Sungwook E., Sangnam Park, M. James Jee, Dongsu Bak, and Sangjun Cha. "Weak-lensing Mass Reconstruction of Galaxy Clusters with a Convolutional Neural Network." Astrophysical Journal 923, no. 2 (2021): 266. http://dx.doi.org/10.3847/1538-4357/ac3090.
Full textAbstract:
Abstract We introduce a novel method for reconstructing the projected matter distributions of galaxy clusters with weak-lensing (WL) data based on a convolutional neural network (CNN). Training data sets are generated with ray-tracing through cosmological simulations. We control the noise level of the galaxy shear catalog such that it mimics the typical properties of the existing ground-based WL observations of galaxy clusters. We find that the mass reconstruction by our multilayered CNN with the architecture of alternating convolution and trans-convolution filters significantly outperforms the traditional reconstruction methods. The CNN method provides better pixel-to-pixel correlations with the truth, restores more accurate positions of the mass peaks, and more efficiently suppresses artifacts near the field edges. In addition, the CNN mass reconstruction lifts the mass-sheet degeneracy when applied to our projected cluster mass estimation from sufficiently large fields. This implies that this CNN algorithm can be used to measure the cluster masses in a model-independent way for future wide-field WL surveys.
43
Russ, John C. "Automatic vs computer-assisted 3D reconstruction." Proceedings, annual meeting, Electron Microscopy Society of America 50, no. 2 (1992): 1050–51. http://dx.doi.org/10.1017/s0424820100129887.
Full textAbstract:
Images from light or electron microscopy of serial sections must be aligned and corrected for distortion before use in three-dimensional reconstruction. As computer rendering supplants physical modelling, algorithms are desired for automatic alignment and rectification, requiring rotation and rubber-sheeting or warping. A new image can be constructed from each digitized original with polynomial equations relating the pixel coordinates in the new image to those in the original. Interpolation between the pixel values is used to prevent aliasing of edges. Calculating the equation coefficients requires matching points in the serial sections, plus some external or a priori information about the cutting distortion. The difficulties in finding corresponding points suggest that human interaction may be needed to locate the proper matching points, while the computer carries out the more mundane but important tasks of pixel interpolation and rendering.Two approaches to automatic alignment have direct counterparts in the related problem of matching points in stereo pair images.
44
Liu, Ya-Li, Tao Liu, Bin Yan, Jeng-Shyang Pan, and Hong-Mei Yang. "Visual Cryptography Using Computation-Free Bit-Plane Reconstruction." Security and Communication Networks 2022 (June 26, 2022): 1–14. http://dx.doi.org/10.1155/2022/4617885.
Full textAbstract:
Visual cryptography (VC) using bit-plane decomposition improves the quality of the reconstructed image. The disadvantage of this scheme is that the decoder needs computation in order to reconstruct the secret image from its bit-planes. To solve this problem, we propose a no-computation bit-plane decomposition visual cryptography (NC-BPDVC). In NC-BPDVC, we convert the grayscale secret image into a multitone image by multilevel halftoning. Then, by exploring the difference between a digital pixel and a printed dot, we design different dot patterns to render a digital pixel. By doing so, we abandon the usual assumption that DPI (dots per inch) equals PPI (pixels per inch) during printing. By adopting the more realistic assumption that DPI can be larger than PPI as is supported by most printers, we use different patterns to render different tone levels. These patterns are carefully designed so that no computation is needed when one needs to reconstruct the multitone image from its bit-planes. Our algorithm is tested on a batch of twenty standard grayscale images. The experimental results confirm the correctness and advantages of the proposed scheme. Compared with the ordinary bit-plane decomposition VC, NC-BPDVC does not need computation. The security of the proposed algorithm is also analyzed and verified.
45
Rymarczyk, Tomasz, Edward Kozłowski, Grzegorz Kłosowski, and Konrad Niderla. "Logistic Regression for Machine Learning in Process Tomography." Sensors 19, no. 15 (2019): 3400. http://dx.doi.org/10.3390/s19153400.
Full textAbstract:
The main goal of the research presented in this paper was to develop a refined machine learning algorithm for industrial tomography applications. The article presents algorithms based on logistic regression in relation to image reconstruction using electrical impedance tomography (EIT) and ultrasound transmission tomography (UST). The test object was a tank filled with water in which reconstructed objects were placed. For both EIT and UST, a novel approach was used in which each pixel of the output image was reconstructed by a separately trained prediction system. Therefore, it was necessary to use many predictive systems whose number corresponds to the number of pixels of the output image. Thanks to this approach the under-completed problem was changed to an over-completed one. To reduce the number of predictors in logistic regression by removing irrelevant and mutually correlated entries, the elastic net method was used. The developed algorithm that reconstructs images pixel-by-pixel is insensitive to the shape, number and position of the reconstructed objects. In order to assess the quality of mappings obtained thanks to the new algorithm, appropriate metrics were used: compatibility ratio (CR) and relative error (RE). The obtained results enabled the assessment of the usefulness of logistic regression in the reconstruction of EIT and UST images.
46
Feng, Jia, Qianxi Li, Jiawei Dong, Qing Zhao, and Hao Wang. "Single-Pixel Imaging Based on Enhanced Multi-Network Prior." Applied Sciences 15, no. 14 (2025): 7717. https://doi.org/10.3390/app15147717.
Full textAbstract:
Single-pixel imaging (SPI) is a significant branch of computational imaging. Owing to the high sensitivity, low cost, and wide spectrum, it acquires extensive applications across various domains. Nevertheless, multiple measurements and long reconstruction time constrain its application. The application of neural networks has significantly improved the quality of reconstruction, but there is still a huge space for improvement in performance. SAE and Unet have different advantages in the field of SPI. However, there is no method that combines the advantages of these two networks for SPI reconstruction. Therefore, we propose the EMNP-SPI method for SPI reconstruction using SAE and Unet networks. The SAE makes use of the measurement dimension information and uses the group inverse to obtain the decoding matrix to enhance its generalization. The Unet uses different size convolution kernels and attention mechanisms to enhance feature extraction capabilities. Simulations and experiments confirm that our proposed enhanced multi-network prior method can significantly improve the quality of image reconstruction at low measurement rates.
47
Sun, Ying, and Guang Lin Gao. "Study on Reconstruction Techniques of Landscape Image." Advanced Materials Research 1006-1007 (August 2014): 797–801. http://dx.doi.org/10.4028/www.scientific.net/amr.1006-1007.797.
Full textAbstract:
The depth map is a basic diagram of the intrinsic; each pixel value represents the scene graph the elevation position of the object point. In this paper, the analysis methods for target classification elevation map. Figure elevation are visible depth image, the depth of the image is the distance from each point in the scene to the image capture device values of the image as an image pixel value.
48
Chen, Haozhen, Hancui Zhang, Bo Zou, and Long Wu. "Hybrid Self-Attention Transformer U-Net for Fourier Single-Pixel Imaging Reconstruction at Low Sampling Rates." Photonics 12, no. 6 (2025): 568. https://doi.org/10.3390/photonics12060568.
Full textAbstract:
Fourier Single-Pixel Imaging exhibits significant advantages over conventional imaging techniques, including high interference resistance, broad spectral adaptability, nonlocal imaging capability, and long-range detection. However, in practical applications, FSPI relies on undersampling reconstruction, which inevitably leads to ringing artifacts that degrade image quality. To enhance reconstruction performance, a Transformer-based FSPI reconstruction network is proposed. The network adopts a U-shaped architecture, composed of multiple Hybrid Self-Attention Transformer Modules and Feature Fusion Modules. The experimental results demonstrate that the proposed network achieves high-quality reconstruction at low sampling rates and outperforms traditional reconstruction methods and convolutional network-based approaches in terms of both visual appearance and image quality metrics. This method holds significant potential for high-speed single-pixel imaging applications, enabling the reconstruction of high-quality images at extremely low sampling rates.
49
Wang, Qingyu, Dihua Wu, Wei Liu, et al. "PlantStereo: A High Quality Stereo Matching Dataset for Plant Reconstruction." Agriculture 13, no. 2 (2023): 330. http://dx.doi.org/10.3390/agriculture13020330.
Full textAbstract:
Stereo matching is a depth perception method for plant phenotyping with high throughput. In recent years, the accuracy and real-time performance of the stereo matching models have been greatly improved. While the training process relies on specialized large-scale datasets, in this research, we aim to address the issue in building stereo matching datasets. A semi-automatic method was proposed to acquire the ground truth, including camera calibration, image registration, and disparity image generation. On the basis of this method, spinach, tomato, pepper, and pumpkin were considered for experiment, and a dataset named PlantStereo was built for reconstruction. Taking data size, disparity accuracy, disparity density, and data type into consideration, PlantStereo outperforms other representative stereo matching datasets. Experimental results showed that, compared with the disparity accuracy at pixel level, the disparity accuracy at sub-pixel level can remarkably improve the matching accuracy. More specifically, for PSMNet, the EPE and bad-3 error decreased 0.30 pixels and 2.13%, respectively. For GwcNet, the EPE and bad-3 error decreased 0.08 pixels and 0.42%, respectively. In addition, the proposed workflow based on stereo matching can achieve competitive results compared with other depth perception methods, such as Time-of-Flight (ToF) and structured light, when considering depth error (2.5 mm at 0.7 m), real-time performance (50 fps at 1046 × 606), and cost. The proposed method can be adopted to build stereo matching datasets, and the workflow can be used for depth perception in plant phenotyping.
50
Rymarczyk, Tomasz, Grzegorz Kłosowski, Anna Hoła, et al. "Historical Buildings Dampness Analysis Using Electrical Tomography and Machine Learning Algorithms." Energies 14, no. 5 (2021): 1307. http://dx.doi.org/10.3390/en14051307.
Full textAbstract:
The article deals with the problem of detecting moisture in the walls of historical buildings. As part of the presented research, the following four methods based on mathematical modeling and machine learning were compared: total variation, least-angle regression, elastic net, and artificial neural networks. Based on the simulation data, the systems for the reconstruction of “pixel by pixel” tomographic images were trained. In order to test the reconstructive algorithms obtained during the research, images were generated based on real measurements and simulation cases. The method comparison was performed on the basis of three indicators: mean square error, relative image error, and image correlation coefficient. The above indicators were applied to four selected variants that corresponded to various parts of the walls. The variants differed in the dimensions of the tested wall sections, the number of electrodes used, and the resolution of the 3D image meshes. In all analyzed variants, the best results were obtained using the elastic net algorithm. In addition, all machine learning methods generated better tomographic reconstructions than the classic Total Variation method.