Добірка наукової літератури з теми "4603 Computer vision and multimedia computation"

In this paper we present an improved support vector machines (SVMs) watermarking system for still images and video sequences. By a thorough study on feature selection for training SVM, the proposed system shows significant improvements on computation efficiency and robustness to various attacks. The improved algorithm is extended to be a scene-based video watermarking technique. In a given scene, the algorithm uses the first h' frames to train an embedding SVM, and uses the trained SVM to watermark the rest of the frames. In the extracting phrase, the detector uses only the center h frames of the first h' frames to train an extracting SVM. The final extracted watermark in a given scene is the average of watermarks extracted from the remaining frames. Watermarks are embedded in l longest scenes of a video such that it is computationally efficient and capable to resist possible frames swapping/deleting/duplicating attacks. Two collusion attacks, namely temporal frame averaging and watermark estimation remodulation, on video watermarking are discussed and examined. The proposed video watermarking algorithm is shown to be robust to compression and collusion attacks, and it is novel and practical for SVM-applications.

The present spreading out of the Internet of Things (IoT) originated the realization of millions of IoT devices connected to the Internet. With the increase of allied devices, the gigantic multimedia big data (MMBD) vision is also gaining eminence and has been broadly acknowledged. MMBD management offers computation, exploration, storage, and control to resolve the QoS issues for multimedia data communications. However, it becomes challenging for multimedia systems to tackle the diverse multimedia-enabled IoT settings including healthcare, traffic videos, automation, society parking images, and surveillance that produce a massive amount of big multimedia data to be processed and analyzed efficiently. There are several challenges in the existing structural design of the IoT-enabled data management systems to handle MMBD including high-volume storage and processing of data, data heterogeneity due to various multimedia sources, and intelligent decision-making. In this article, an architecture is proposed to process and store MMBD efficiently in an IoT-enabled environment. The proposed architecture is a layered architecture integrated with a parallel and distributed module to accomplish big data analytics for multimedia data. A preprocessing module is also integrated with the proposed architecture to prepare the MMBD and speed up the processing mechanism. The proposed system is realized and experimentally tested using real-time multimedia big data sets from athentic sources that discloses the effectiveness of the proposed architecture.

The use of gestures is one of the main forms of human machine interaction (HMI) in many fields, from advanced robotics industrial setups, to multimedia devices at home. Almost every gesture detection system uses computer vision as the fundamental technology, with the already well-known problems of image processing: changes in lighting conditions, partial occlusions, variations in color, among others. To solve all these potential issues, deep learning techniques have been proven to be very effective. This research proposes a hand gesture recognition system based on convolutional neural networks and color images that is robust against environmental variations, has a real time performance in embedded systems, and solves the principal problems presented in the previous paragraph. A new CNN network has been specifically designed with a small architecture in terms of number of layers and total number of neurons to be used in computationally limited devices. The obtained results achieve a percentage of success of 96.92% on average, a better score than those obtained by previous algorithms discussed in the state of the art.

The process of image retrieval presents an interesting tool for different domains related to computer vision such as multimedia retrieval, pattern recognition, medical imaging, video surveillance and movements analysis. Visual characteristics of images such as color, texture and shape are used to identify the content of images. However, the retrieving process becomes very challenging due to the hard management of large databases in terms of storage, computation complexity, temporal performance and similarity representation. In this paper, we propose a cloud-based platform in which we integrate several features extraction algorithms used for content-based image retrieval (CBIR) systems. Moreover, we propose an efficient combination of SIFT and SURF descriptors that allowed to extract and match image features and hence improve the process of image retrieval. The proposed algorithms have been implemented on the CPU and also adapted to fully exploit the power of GPUs. Our platform is presented with a responsive web solution that offers for users the possibility to exploit, test and evaluate image retrieval methods. The platform offers to users a simple-to-use access for different algorithms such as SIFT, SURF descriptors without the need to setup the environment or install anything while spending minimal efforts on preprocessing and configuring. On the other hand, our cloud-based CPU and GPU implementations are scalable, which means that they can be used even with large database of multimedia documents. The obtained results showed: 1. Precision improvement in terms of recall and precision; 2. Performance improvement in terms of computation time as a result of exploiting GPUs in parallel; 3. Reduction of energy consumption.

With the advance of semiconductor technology, the current mobile devices support multimodal input and multimedia output. In turn, human computer communication applications can be developed in mobile devices such as mobile phone and PDA. This paper addresses the research issues of face and eye detection on mobile devices. The major obstacles that we need to overcome are the relatively low processor speed, low storage memory and low image (CMOS senor) quality. To solve these problems, this paper proposes a novel and efficient method for face and eye detection. The proposed method is based on color information because the computation time is small. However, the color information is sensitive to the illumination changes. In view of this limitation, this paper proposes an adaptive Illumination Insensitive (AI2) Algorithm, which dynamically calculates the skin color region based on an image color distribution. Moreover, to solve the strong sunlight effect, which turns the skin color pixel into saturation, a dual-color-space model is also developed. Based on AI2algorithm and face boundary information, face region is located. The eye detection method is based on an average integral of density, projection techniques and Gabor filters. To quantitatively evaluate the performance of the face and eye detection, a new metric is proposed. 2158 head & shoulder images captured under uncontrolled indoor and outdoor lighting conditions are used for evaluation. The accuracy in face detection and eye detection are 98% and 97% respectively. Moreover, the average computation time of one image using Matlab code in Pentium III 700MHz computer is less than 15 seconds. The computational time will be reduced to tens hundreds of millisecond (ms) if low level programming language is used for implementation. The results are encouraging and show that the proposed method is suitable for mobile devices.

Purpose The following article is a “Q&A interview” conducted by Joanne Pransky of Industrial Robot Journal as a method to impart the combined technological, business and personal experience of a prominent, robotic industry PhD-turned entrepreneur regarding his pioneering efforts of bringing technological inventions to market. The paper aims to discuss these issues. Design/methodology/approach The interviewee is Dr James Kuffner, CEO at Toyota Research Institute Advanced Development (TRI-AD). Kuffner is a proven entrepreneur and inventor in robot and motion planning and cloud robotics. In this interview, Kuffner shares his personal and professional journey from conceptualization to commercial realization. Findings Dr Kuffner received BS, MS and PhD degrees from the Stanford University’s Department of Computer Science Robotics Laboratory. He was a Japan Society for the Promotion of Science (JSPS) Postdoctoral Research Fellow at the University of Tokyo where he worked on software and planning algorithms for humanoid robots. He joined the faculty at Carnegie Mellon University’s Robotics Institute in 2002 where he served until March 2018. Kuffner was a Research Scientist and Engineering Director at Google from 2009 to 2016. In January 2016, he joined TRI where he was appointed the Chief Technology Officer and Area Lead, Cloud Intelligence and is presently an Executive Advisor. He has been CEO of TRI-AD since April of 2018. Originality/value Dr Kuffner is perhaps best known as the co-inventor of the rapidly exploring random tree (RRT) algorithm, which has become a key standard benchmark for robot motion planning. He is also known for introducing the term “Cloud Robotics” in 2010 to describe how network-connected robots could take advantage of distributed computation and data stored in the cloud. Kuffner was part of the initial engineering team that built Google’s self-driving car. He was appointed Head of Google’s Robotics Division in 2014, which he co-founded with Andy Rubin to help realize the original Cloud Robotics concept. Kuffner also co-founded Motion Factory, where he was the Senior Software Engineer and a member of the engineering team to develop C++ based authoring tools for high-level graphic animation and interactive multimedia content. Motion Factory was acquired by SoftImage in 2000. In May 2007, Kuffner founded, and became the Director of Robot Autonomy where he coordinated research and software consulting for industrial and consumer robotics applications. In 2008, he assisted in the iOS development of Jibbigo, the first on-phone, real-time speech recognition, translation and speech synthesis application for the iPhone. Jibbigo was acquired by Facebook in 2013. Kuffner is one of the most highly cited authors in the field of robotics and motion planning, with over 15,000 citations. He has published over 125 technical papers and was issued more than 50 patents related to robotics and computer vision technology.

Introduction: The application of specific instructions significantly improves energy, performance, and code size of configurable processors. The design of these instructions is performed by the conversion of patterns related to application-specific operations into effective complex instructions. This research was presented at the icitkm Conference, University of Delhi, India in 2017.Methods: Static analysis was a prominent research method during late the 1980’s. However, end-to-end measurements consist of a standard approach in industrial settings. Both static analysis tools perform at a high-level in order to determine the program structure, which works on source code, or is executable in a disassembled binary. It is possible to work at a low-level if the real hardware timing information for the executable task has the desired features.Results: We experimented, tested and evaluated using a H.264 encoder application that uses nine cis, covering most of the computation intensive kernels. Multimedia applications are frequently subject to hard real time constraints in the field of computer vision. The H.264 encoder consists of complicated control flow with more number of decisions and nested loops. The parameters evaluated were different numbers of A partitions (300 slices on a Xilinx Virtex 7each), reconfiguration bandwidths, as well as relations of cpu frequency and fabric frequency fCPU/ffabric. ffabric remains constant at 100MHz, and we selected a multiplicity of its values for fCPU that resemble realistic units. Note that while we anticipate the wcet in seconds (wcetcycles/ f CPU) to be lower (better) with higher fCPU, the wcet cycles increase (at a constant ffabric) because hardware cis perform less computations on the reconfigurable fabric within one cpu cycle.Conclusions: The method is similar to tree hybridization and path-based methods which are less precise, and to the global ipet method, which is more precise. Optimization is evaluated with the Discrete Particle Swarm Optimization (dpso) algorithm for wcet. For several real-world applications involving embedded processors, the proposed technique develops improved instruction sets in comparison to native instruction sets.Originality: For wcet estimation, flow analysis, low-level analysis and calculation phases of the program need to be considered. Flow analysis phase or the high-level of analysis helps to extract the program’s dynamic behavior that gives information on functions being called, number of loop iteration, dependencies among if-statements, etc. This is due to the fact that the analysis is unaware of the execution path corresponding to the longest execution time.Limitations: This path is executed within a kernel iteration that relies upon the nature of mb, either i-mb or p-mb, determined by the motion estimation kernel, that is, its’ input depends on the i-mb and p-mb paths ,which also contain separate cis leading to the instability of the worst-case path, that is, adding more partitions to the current worst-case path can result in the other path becoming the worst case. The pipeline stalls for the reconfiguration delay and continues when entering the kernel once the reconfiguration process finishes.

We are very pleased and honored to have an opportunity to publish a new journal the "International Journal of Advanced Computational Intelligence" (JACI). The JACI is a new, bimonthly journal covering the field of computer science. This journal focuses on advanced computational intelligence, including the synergetic integration of neural networks, fuzzy logic and evolutionary computations, in order to assist in fostering the application of intelligent systems to industry. This new field is called computational intelligence or soft computing. It has already been studied by many researchers, but no single, integrated journal exists anywhere in the world. This new journal gives readers the state of art of the theory and application of Advanced Computational Intelligence. The Topics include, but are not limited to: Fuzzy Logic, Neural Networks, GA and Evolutionary Computation, Hybrid Systems, Network Systems, Multimedia, the Human Interface, Biologically-Inspired Evolutionary Systems, Artificial Life, Chaos, Fractal, Wavelet Analysis, Scientific Applications and Industrial Applications. The journal, JACI, is supported by many researchers and scientific organizations, e.g., the International Fuzzy Systems Association (IFSA), the Japan Society of Fuzzy Theory and Systems (SOFT), the Brazilian Society of Automatics (SBA) and The Society of Instrument and Control Engineers (SICE), and we are currently negotiating with the John von Neumann Computer Society (in Hungary). Our policy is to have world-wide communication with many societies and researchers in this field. We would appreciate it if those organizations and people who have an interest in co-sponsorship or have proposals for special issues in this journal, as well as paper submissions, could contact us. Finally our special thanks go to the editorial office of Fuji Technology Press Ltd., especially to its president, Mr. K. Hayashi, and to the editor, Mr. Y. Inoue, for their efforts in publishing this new journal. Lotti A. Zadeh The publication of the International Journal of Advanced Computational Intelligence (JACI) is an important milestone in the advancement of our understanding of how intelligent systems can be conceived, designed, built, and deployed. When one first hears of computational intelligence, a question that naturally arises is: What is the difference, if any, between computational intelligence (CI) and artificial intelligence (AI)? As one who has witnessed the births of both AI and CI, I should like to suggest an answer. As a branch of science and technology, artificial intelligence was born about four decades ago. From the outset, AI was based on classical logic and symbol manipulation. Numerical computations were not welcomed and probabilistic techniques were proscribed. Mainstream AI continued to evolve in this spirit, with symbol manipulation still occupying the center of the stage, but not to the degree that it did in the past. Today, probabilistic techniques and neurocomputing are not unwelcome, but the focus is on distributed intelligence, agents, man-machine interfaces, and networking. With the passage of time, it became increasing clear that symbol manipulation is quite limited in its ability to serve as a foundation for the design of intelligent systems, especially in the realms of robotics, computer vision, motion planning, speech recognition, handwriting recognition, fault diagnosis, planning, and related fields. The inability of mainstream AI to live up to expectations in these application areas has led in the mid-eighties to feelings of disenchantment and widespread questioning of the effectiveness of AI's armamentarium. It was at this point that the name computational intelligence was employed by Professor Nick Cercone of Simon Fraser University in British Columbia to start a new journal named Computational Intelligence -a journal that was, and still is, intended to provide a broader conceptual framework for the conception and design of intelligent systems than was provided by mainstream AI. Another important development took place. The concept of soft computing (SC) was introduced in 1990-91 to describe an association of computing methodologies centering on fuzzy logic (FL), neurocomputing (NC), genetic (or evolutionary) computing (GC), and probabilistic computing (PC). In essence, soft computing differs from traditional hard computing in that it is tolerant of imprecision, uncertainty and partial truth. The basic guiding principle of SC is: Exploit the tolerance for imprecision, uncertainty, and partial truth to achieve tractability, robustness, low solution cost, and better rapport with reality. More recently, the concept of computational intelligence had reemerged with a meaning that is substantially different from that which it had in the past. More specifically, in its new sense, CI, like AI, is concerned with the conception, design, and deployment of intelligent systems. However, unlike mainstream AI, CI methodology is based not on predicate logic and symbol manipulation but on the methodologies of soft computing and, more particularly, on fuzzy logic, neurocomputing, genetic(evolutionary) computing, and probabilistic computing. In this sense, computational intelligence and soft computing are closely linked but not identical. In basic ways, the importance of computational intelligence derives in large measure from the effectiveness of the techniques of fuzzy logic, neurocomputing, genetic (evolutionary) computing, and probabilistic computing in the conception and design of information/intelligent systems, as defined in the statements of the aims and scope of the new journal of Advanced Computational Intelligence. There is one important aspect of both computational intelligence and soft computing that should be stressed. The methodologies which lie at the center of CI and SC, namely, FL, NC, genetic (evolutionary) computing, and PC are for the most part complementary and synergistic, rather than competitive. Thus, in many applications, the effectiveness of FL, NC, GC, and PC can be enhanced by employing them in combination, rather than in isolation. Intelligent systems in which FL, NC, GC, and PC are used in combination are frequently referred to as hybrid intelligent systems. Such systems are likely to become the norm in the not distant future. The ubiquity of hybrid intelligent systems is likely to have a profound impact on the ways in which information/intelligent systems are conceived, designed, built, and interacted with. At this juncture, the most visible hybrid intelligent systems are so-called neurofuzzy systems, which are for the most part fuzzy-rule-based systems in which neural network techniques are employed for system identification, rule induction, and tuning. The concept of neurofuzzy systems was originated by Japanese scientists and engineers in the late eighties, and in recent years has found a wide variety of applications, especially in the realms of industrial control, consumer products, and financial engineering. Today, we are beginning to see a widening of the range of applications of computational intelligence centered on the use of neurofuzzy, fuzzy-genetic, neurogenetic, neurochaotic and neuro-fuzzy-genetic systems. The editors-in-chief of Advanced Computational Intelligence, Professors Fukuda and Hirota, have played and are continuing to play majors roles both nationally and internationally in the development of fuzzy logic, soft computing, and computational intelligence. They deserve our thanks and congratulations for conceiving the International Journal of Advanced Computational Intelligence and making it a reality. International in both spirit and practice, JACI is certain to make a major contribution in the years ahead to the advancement of the science and technology of man-made information/intelligence systems -- systems that are at the center of the information revolution, which is having a profound impact on the ways in which we live, communicate, and interact with the real world. Lotfi A. Zadeh Berkeley, CA, July 24, 1997

Image denoising is a fundamental problem in computer vision and multimedia computation. Non-local filters are effective for image denoising. But existing deep learning methods that use non-local computation structures are mostly designed for high-level tasks, and global self-attention is usually adopted. For the task of image denoising, they have high computational complexity, and have a lot of redundant computation of uncorrelated pixels. To solve this problem and combine the marvelous advantages of non-local filter and deep learning, we propose a Convolutional Unbiased Regional (CUR) transformer. Based on the prior that, for each pixel, its similar pixels are usually spatially close, our insights are that 1) we partition the image into non-overlapped windows and perform regional self-attention to reduce the search range of each pixel, and 2) we encourage pixels across different windows to communicate with each other. Based on our insights, the CUR transformer is cascaded by a series of convolutional regional self-attention (CRSA) blocks with U-style short connections. In each CRSA block, we use convolutional layers to extract the query, key, and value features, namely Q , K , and V , of the input feature. Then, we partition the Q , K , and V features into local non-overlapped windows, and perform regional self-attention within each window to obtain the output feature of this CRSA block. Among different CRSA blocks, we perform the unbiased window partition by changing the partition positions of the windows. Experimental results show that the CUR transformer outperforms the state-of-the-art methods significantly on four low-level vision tasks, including real and synthetic image denoising, JPEG compression artifact reduction, and low-light image enhancement.

Purpose Deep learning techniques are unavoidable in a variety of domains such as health care, computer vision, cyber-security and so on. These algorithms demand high data transfers but require bottlenecks in achieving the high speed and low latency synchronization while being implemented in the real hardware architectures. Though direct memory access controller (DMAC) has gained a brighter light of research for achieving bulk data transfers, existing direct memory access (DMA) systems continue to face the challenges of achieving high-speed communication. The purpose of this study is to develop an adaptive-configured DMA architecture for bulk data transfer with high throughput and less time-delayed computation. Design/methodology/approach The proposed methodology consists of a heterogeneous computing system integrated with specialized hardware and software. For the hardware, the authors propose an field programmable gate array (FPGA)-based DMAC, which transfers the data to the graphics processing unit (GPU) using PCI-Express. The workload characterization technique is designed using Python software and is implementable for the advanced risk machine Cortex architecture with a suitable communication interface. This module offloads the input streams of data to the FPGA and initiates the FPGA for the control flow of data to the GPU that can achieve efficient processing. Findings This paper presents an evaluation of a configurable workload-based DMA controller for collecting the data from the input devices and concurrently applying it to the GPU architecture, bypassing the hardware and software extraneous copies and bottlenecks via PCI Express. It also investigates the usage of adaptive DMA memory buffer allocation and workload characterization techniques. The proposed DMA architecture is compared with the other existing DMA architectures in which the performance of the proposed DMAC outperforms traditional DMA by achieving 96% throughput and 50% less latency synchronization. Originality/value The proposed gated recurrent unit has produced 95.6% accuracy in characterization of the workloads into heavy, medium and normal. The proposed model has outperformed the other algorithms and proves its strength for workload characterization.

Healthy vegetation are essential not just for environmental sustainability but also for the development of sustainable and liveable cities. It is undeniable that human activities are altering the vegetation landscape, with harmful implications for the climate. As a result, autonomous detection, health evaluation, and continual monitoring of the plants are required to ensure environmental sustainability. This thesis presents research on autonomous vegetation management using recent advances in deep learning. Currently, most towns do not have a system in place for detection and continual vegetation monitoring. On the one hand, a lack of public knowledge and political will could be a factor; on the other hand, no efficient and cost-effective technique of monitoring vegetation health has been established. Individual plants health condition data is essential since urban trees often develop as stand-alone objects. Manual annotation of these individual trees is a time-consuming, expensive, and inefficient operation that is normally done in person. As a result, skilled manual annotation cannot cover broad areas, and the data they create is out of date. However, autonomous vegetation management poses a number of challenges due to its multidisciplinary nature. It includes automated detection, health assessment, and monitoring of vegetation and trees by integrating techniques from computer vision, machine learning, and remote sensing. Other challenges include a lack of analysis-ready data and imaging diversity, as well as dealing with their dependence on weather variability. With a core focus on automation of vegetation management using deep learning and transfer learning, this thesis contributes novel techniques for Multi-view vegetation detection, robust calculation of vegetation index, and real- time vegetation health assessment using deep convolutional neural networks (CNNs) and deep learning frameworks. The thesis focuses on four general aspects: a) training CNN with possibly inaccurate labels and noisy image dataset; b) deriving semantic vegetation segmentation from the ordinal information contained in the image; c) retrieving semantic vegetation indexes from street-level imagery; and d) developing a vegetation health assessment and monitoring system. Firstly, it is essential to detect and segment the vegetation, and then calculate the pixel value of the semantic vegetation index. However, because the images in multi- sensory data are not identical, all image datasets must be registered before being fed into the model training. The dataset used for vegetation detection and segmentation was acquired from multi-sensors. The whole dataset was multi-temporal based; therefore, it was registered using deep affine features through a convolutional neural network. Secondly, after preparing the dataset, vegetation was segmented by using Deep CNN, a fully convolutional network, and U-net. Although the vegetation index interprets the health of a particular area’s vegetation when assessing small and large vegetation (trees, shrubs, grass, etc.), the health of large plants, such as trees, is determined by steam. In contrast, small plants’ leaves are evaluated to decide whether they are healthy or unhealthy. Therefore, initially, small plant health was assessed through their leaves by training a deep neural network and integrating that trained model into an internet of things (IoT) device such as AWS DeepLens. Another deep CNN was trained to assess the health of large plants and trees like Eucalyptus. This one could also tell which trees were healthy and which ones were unhealthy, as well as their geo-location. Thus, we may ultimately analyse the vegetation’s health in terms of the vegetation index throughout time on the basis of a semantic-based vegetation index and compute the index in a time-series fashion. This thesis shows that computer vision, deep learning and remote sensing approaches can be used to process street-level imagery in different places and cities, to help manage urban forests in new ways, such as biomass-surveillance and remote vegetation monitoring.

Internal density of the breast is a parameter that clearly affects the performance of segmentation and classification algorithms to define abnormality regions. Recent studies have shown that their sensitivity is significantly decreased as the density of the breast is increased. In this chapter, enhancement and segmentation process is applied to increase the computation and focus on mammographic parenchyma. This parenchyma is analyzed to discriminate tissue density according to BIRADS using Local Binary Pattern (LBP), Gray Level Co-Occurrence Matrix (GLCM), Fractal Dimension (FD), and feature fusion technique is applied to maximize and enhance the performance of the classifier rate. The different methods for computing tissue density parameter are reviewed, and the authors also present and exhaustively evaluate algorithms using computer vision techniques. The experimental results based on confusion matrix and kappa coefficient show a higher accuracy is obtained by automatic agreement classification.

It is well known that the careful selection of a set of features, with higher discrimination competence, may increase recognition performance. In general, the magnitude coefficients of some selected orders of ZMs and PZMs have been used as invariant image features. The authors have used a statistical method to estimate the discrimination strength of all the coefficients of ZMs and PZMs. For classification, only the coefficients with estimated higher discrimination strength are selected and are used in the feature vector. The performance of these selected Discriminative ZMs (DZMs) and Discriminative PZMs (DPZMs) features are compared to that of their corresponding conventional approaches on YALE, ORL, and FERET databases against illumination, expression, scale, and pose variations. In this chapter, an extension to these DZMs and DPZMs is presented by exploring the use of phase information along with the magnitude coefficients of these approaches. As the phase coefficients are computed in parallel to the magnitude, no additional time is spent on their computation. Further, DZMs and DPZMs are also combined with PCA and FLD. It is observed from the exhaustive experimentation that with the inclusion of phase features the recognition rate is improved by 2-8%, at reduced dimensions and with less computational complexity, than that of using the successive ZMs and PZMs features.

In this paper are presented solutions to develop algorithms for digital image processing focusing particularly on edge detection. Edge detection is one of the most important phases used in computer vision and image processing applications and also in human image understanding. In this chapter, implementation of classical edge detection algorithms it is presented and also implementation of algorithms based on the theory of Cellular Automata (CA). This work is totally related to the idea of understanding the impact of the inherently local information processing of CA on their ability to perform a managed computation at the global level. If a suitable encoding of a digital image is used, in some cases, it is possible to achieve better results in comparison with the solutions obtained by means of conventional approaches. The software application which is able to process images in order to detect edges using both conventional algorithms and CA based ones is written in C# programming language and experimental results are presented for images with different sizes and backgrounds.