Problem Of Image Compression Research Articles

Vector quantization-driven image compression through multi-objective evolutionary algorithms

In recent years, information consumption among the population has increased, especially through the widespread use of digital images and videos. Consequently, the demand for efficient compression methods has escalated, aiming to facilitate both data storage and transmission while adapting to the unique requirements of diverse problems. The image compression problem has been explored in several works through the lens of vector quantization (VQ) by adopting a single-objective approach to achieve optimal quality results but with a fixed compression level. In contrast, this investigation introduces a groundbreaking multi-objective compression approach that simultaneously optimizes image quality and compression level. This is achieved by selecting the most representative information to construct an adequate codebook while minimizing its size. The proposed method was evaluated on a curated selection of well-known public domain images, using different types of multi-objective evolutionary algorithms, including Pareto-, indicator- and decomposition-based approaches. The compressed images produced were assessed through the application of established quality indicators drawn from the expansive realm of image processing literature, ensuring the reliability and validity of our findings. The results demonstrate the proposed method’s ability to adapt to the intrinsic characteristics of each image, removing the maximum amount of redundant information presented. Furthermore, the multi-objective nature of the proposed approach allows us to obtain solutions with different levels of trade-off between quality and compression, opening up new possibilities in the field and demonstrating the potential to address the evolving challenges posed by the escalating volume of information in the digital landscape.

ДОСЛІДЖЕННЯ МЕТОДУ ФРАКТАЛЬНОГО СТИСНЕННЯ ЗОБРАЖЕНЬ З МЕТОЮ ПОКРАЩЕННЯ ЯКОСТІ СТИСНЕННЯ

The development of the Internet, along with the availability of increasingly powerful computers and other digital devices, cameras, scanners and printers, has led to the wide-spread use of digital images. In this regard, interest in improving data compression algo-rithms, such as images, is growing. Data compression is important for both transfer speed and storage efficiency. In addition to many commercial uses, compression technologies are also of interest in the military industry, such as applications for processing telemetry data from missile inter-ceptors or for archiving terrain image data for defense simulations. Solving the problem of image compression, or, more generally, image coding, has used advances and stimulated the development of many fields of engineering and math-ematics. The article examines fractal image compression — a data compression method based on the use of self-similar patterns in an image. This method allows you to achieve a high degree of compression while preserving image details. Fractal image compression is a unique and efficient approach to data compression based on the mathematical theory of fractals. Nowadays, it has important applications and advantages that make it a valuable tool in image processing. The main advantages include: 1. Preservation of details during compression. One of the key advantages of fractal compression is its ability to preserve a high degree of image detail in a relatively small amount of storage. This is especially important in situations where image quality must be preserved with limited storage and data transfer resources. 2. Efficiency of transmission through the network. Fractal compression allows for compact images, making it suitable for image transmission over a low-bandwidth network. This is especially true for mobile devices, the Internet of Things, and other scenarios where high bandwidth is not always available. 3. Adaptive compression for different resolutions. Fractal compression allows you to adapt the level of compression depending on the resolution and details of the image. This means that it can be used to compress various image sizes without significant loss of quality. 4. Data archiving and storage. Fractal compression can be useful for archiving and long-term storage of images, as it allows you to effectively reduce the amount of data without losing important information. This is especially important for libraries, archives, research databases and other data repositories. Fractal image compression remains a relevant and valuable tool in today's envi-ronment, thanks to its ability to efficiently compress, preserve details, and adapt to dif-ferent usage scenarios. Therefore, the study of its efficiency, the optimization of the soft-ware code to obtain a faster and better compression result, is an urgent task.

QARV: Quantization-Aware ResNet VAE for Lossy Image Compression.

This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications. We start by reviewing the framework of variational autoencoders (VAEs), a powerful class of generative probabilistic models that has a deep connection to lossy compression. Based on VAEs, we develop a new scheme for lossy image compression, which we name quantization-aware ResNet VAE (QARV). Our method incorporates a hierarchical VAE architecture integrated with test-time quantization and quantization-aware training, without which efficient entropy coding would not be possible. In addition, we design the neural network architecture of QARV specifically for fast decoding and propose an adaptive normalization operation for variable-rate compression. Extensive experiments are conducted, and results show that QARV achieves variable-rate compression, high-speed decoding, and better rate-distortion performance than existing baseline methods.

Rethinking Semantic Image Compression: Scalable Representation With Cross-Modality Transfer

This article proposes the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">scalable cross-modality compression</i> (SCMC) paradigm, in which the image compression problem is further cast into a representation task by hierarchically sketching the image with different modalities. Herein, we adopt the conceptual organization philosophy to model the overwhelmingly complicated visual patterns, based upon the semantic, structure, and signal level representation accounting for different tasks. The SCMC paradigm that incorporates the representation at different granularities supports diverse application scenarios, such as high-level semantic communication and low-level image reconstruction. The decoder, which enables the recovery of the visual information, benefits from the scalable coding based upon the semantic, structure, and signal layers. Qualitative and quantitative results demonstrate that the SCMC can convey accurate semantic and perceptual information of images, especially at low bitrates, and promising rate-distortion performance has been achieved compared to state-of-the-art methods. The code will be available online https://github.com/ppingzhang/SCMC.

Learning-driven lossy image compression: A comprehensive survey

In the field of image processing and computer vision (CV), machine learning (ML) architectures are widely used. Image compression problems can be solved using convolutional neural networks (CNNs). As a result of bandwidth and memory constraints, compression of images is a necessity. There are three types of information found in images: useful, redundant, and irrelevant. In this survey, we will discuss how ML is used to compress lossy images. Firstly, we describe the background of lossy image compression. Next, we classify ML-based image compression frameworks into subgroups based on their architectures. Auto-encoders (AEs), variational auto-encoders (VAEs), CNNs, recurrent neural networks (RNNs), long short-term memories (LSTMs), gated recurrent units (GRUs), generative adversarial networks (GANs), transformers, principal component analysis (PCA) and fuzzy means clustering are among these subgroups. By analyzing learning-driven image compression frameworks, we present pros and cons of each subgroup. Lastly, we outline several research gaps and future research directions in the field of ML-based image compression.

NEURAL NETWORKS TRAINING BASED ON RANDOM SEARCH

The paper deals with a state-of-art problem, associated with neural networks training. Training algorithm (with special parallelization procedure) implementing the annealing method is proposed. The training efficiency is demonstrated by the example of a neural network architecture focused on parallel data processing. For the color image compression problem, it is shown that the proposed algorithm significantly outperforms gradient&#x0D; methods in terms of efficiency. The results obtained make it possible to improve the neural networks training quality in general, and can be used to solve a wide class of applied problems.

High-performance compression-based brain tumor detection using lightweight optimal deep neural network

Medical image-processing plays a vital role in the brain tumor detection and diagnosis process for supporting the automation of computerized based analysis. Magnetic Resonance Image (MRI) is widely considered an imaging modality used for the diagnosis of brain tumors. The primary concern of this research is to detect and reduce the affected tumor region from MRI images and segmentation. But it is a tedious and more challenging task. Most brain tumors are diagnosed after symptoms appear. Brain tumor is a life-threatening problem and hampers the normal functioning of the human body. The noise interference is the major problem in image compression. To overcome these kinds of issues computerized technology is proposed. In this research, to reduce the complexity and improve the performance of detecting the brain tumor in the medical image segmentation process, an optimal threshold segmentation approach is introduced. In this proposed approach, a Lightweight optimal Deep Learning Technique and an effectual compression standard technique are proposed to improve the quality of an image and accuracy level. Using this proposed approach accurate classification is done by minimizing the error. This paper combines the Whale optimization algorithm (WOA) and the Black Widow Optimization algorithm (BWO) to detect the tumor. This hybrid technique is used to detect the severity of the brain tumor. The analytical results of the suggested method have been calculated and verified for quality and performance analysis on MRI images, relying on dice coefficient, specificity, accuracy, structural similarity index, and sensitivity. This research showed that our approach is better than the previous research according to the quality standards and accuracy. The accuracy of our proposed work is greater than the other techniques.

Successive learned image compression: Comprehensive analysis of instability

Recently, learned image compression relying on deep learning has shown remarkable improvement compared to conventional image compression. While the existing studies on learned image compression focus only on single-step compression, this paper addresses the problem of successive image compression (SIC), which refers to repeated application of encoding and decoding an image. It can be commonly involved in the processes of image sharing, editing, and re-distribution, but the performance of learned image compression during SIC has not been studied in literature. Thus, we provide comprehensive analysis of successive learned image compression in three aspects. First, we newly introduce the issue of instability of learned compression methods during SIC, and analyze its causes and affecting factors. Second, we provide SIC benchmarking studies for the state-of-the-art learned compression methods, based on which we compare different methods and investigate the components affecting the instability in detail. Finally, we propose two methods to mitigate the issue of instability of learned methods during SIC.

A Benchmark Evaluation of Adaptive Image Compression for Multi Picture Object Stereoscopic Images.

A stereopair consists of two pictures related to the same subject taken by two different points of view. Since the two images contain a high amount of redundant information, new compression approaches and data formats are continuously proposed, which aim to reduce the space needed to store a stereoscopic image while preserving its quality. A standard for multi-picture image encoding is represented by the MPO format (Multi-Picture Object). The classic stereoscopic image compression approaches compute a disparity map between the two views, which is stored with one of the two views together with a residual image. An alternative approach, named adaptive stereoscopic image compression, encodes just the two views independently with different quality factors. Then, the redundancy between the two views is exploited to enhance the low quality image. In this paper, the problem of stereoscopic image compression is presented, with a focus on the adaptive stereoscopic compression approach, which allows us to obtain a standardized format of the compressed data. The paper presents a benchmark evaluation on large and standardized datasets including 60 stereopairs that differ by resolution and acquisition technique. The method is evaluated by varying the amount of compression, as well as the matching and optimization methods resulting in 16 different settings. The adaptive approach is also compared with other MPO-compliant methods. The paper also presents an Human Visual System (HVS)-based assessment experiment which involved 116 people in order to verify the perceived quality of the decoded images.

A Novel Multilevel Lossy Compression Algorithm for Grayscale Images Inspired by the Synthesization of Biological Protein Sequences

Enormous number of images are generated daily in all areas of life, including social media, medical and navigation images. Moreover, the development of smart phones among other specialized media-capturing devices has witnessed great advances during the last decade. Consequently, the storage, transmission, and analysis of images become essential and frequent tasks. Thus, various research efforts tried to address the image compression problem from different computational perspectives. This article presents a novel multilevel lossy compression algorithm for grayscale images, namely Image-as-Protein ( IaP ), that is inspired by the translation of DNA sequences into protein sequences that occurs inside live beings. Because of the high similarity of the resulting textual protein sequence, it can be tackled by general text compression techniques with competitive compression ratios. Various qualitative comparisons and quantitative measures such as BPP , SSIM and PSNR have been carried out on multiple grayscale image benchmark datasets. The experimental results showed that the proposed algorithm is promising compared to the famous JPEG lossy image compression standard.

Умови рiвномiрної збiжностi вейвлет розкладiв випадкових процесiв iз просторiв Fψ(Ω)

Ця стаття присвячена знаходженню умов рiвномiрної збiжностi з ймовiрнiстю одиниця вейвлет розкладiв класу випадкових процесiв iз просторiв Fψ(Ω). Вивчення загальних властивостей таких випадкових процесiв, отримання оцiнок розподiлу функцiоналiв вiд процесiв з тих чи iнших просторiв випадкових величин, встановлення умов рiвномiрної збiжностi випадкових функцiональних рядiв є одними iз поширених задач теорiї випадкових процесiв. Вейвлет аналiз є достатньо молодою галуззю математики з багатьма цiкавими проблемами й задачами. Однак дану теорiю, зокрема вейвлет розклади функцiй, на даний час широко використовують як у теорiї випадкових процесiв, так i у рiзних областях науки. Наприклад, вейвлет аналiз активно застосовується для фiльтрацiї i попередньої обробки даних, аналiзу стану i прогнозування ситуацiї на фондових ринках, розпiзнавання образiв, при обробцi i синтезi рiзних сигналiв, зокрема при обробцi мовних сигналiв, бiомедичних сигналiв, для розв’язання завдань стиснення i обробки зображень, при навчаннi нейромереж i в багатьох iнших випадках. Тому є актуальною задача знаходження умов рiвномiрної збiжностi вейвлет розкладiв класу випадкових процесiв iз просторiв Fψ(Ω). У данiй роботi ми зосереджуємося на основних властивостях просторiв Fψ(Ω) та деяких елементах теорiї вейвлетiв. На початку статтi наведено основнi означення, теореми, приклади випадкових величин з просторiв Fψ(Ω) та поняття i властивостi мажоруючої характеристики цього простору. Далi подано необхiднi вiдомостi з вейвлет аналiзу, зокрема: означення f-, m-вейвлетiв та умови S, а також умови розкладу функцiй по цим базисам. Також наведено умови рiвномiрної збiжностi з iмовiрнiстю одиниця вейвлет розкладiв деяких функцiй. Основним результатом статтi є умови рiвномiрної збiжностi вейвлет розкладiв випадкових процесiв iз просторiв Fψ(Ω). Данi умови базуються на оцiнках розподiлу супремуму на R випадкових процесiв iз просторiв Fψ(Ω) та рiвномiрної неперервностi сепарабельного вимiрного випадкового процесу X = {X(t), t ∈ R} з простору Fψ(Ω) на деякому вiдрiзку. Також, наведено приклади функцiй, для яких виконується одна iз умов теореми про оцiнку мажоруючої характеристики κ(n) простору Fψ(Ω)

Learning-Based Hyperspectral Imagery Compression through Generative Neural Networks

Hyperspectral images (HSIs), which obtain abundant spectral information for narrow spectral bands (no wider than 10 nm), have greatly improved our ability to qualitatively and quantitatively sense the Earth. Since HSIs are collected by high-resolution instruments over a very large number of wavelengths, the data generated by such sensors is enormous, and the amount of data continues to grow, HSI compression technique will play more crucial role in this trend. The classical method for HSI compression is through compression and reconstruction methods such as three-dimensional wavelet-based techniques or the principle component analysis (PCA) transform. In this paper, we provide an alternative approach for HSI compression via a generative neural network (GNN), which learns the probability distribution of the real data from a random latent code. This is achieved by defining a family of densities and finding the one minimizing the distance between this family and the real data distribution. Then, the well-trained neural network is a representation of the HSI, and the compression ratio is determined by the complexity of the GNN. Moreover, the latent code can be encrypted by embedding a digit with a random distribution, which makes the code confidential. Experimental examples are presented to demonstrate the potential of the GNN to solve image compression problems in the field of HSI. Compared with other algorithms, it has better performance at high compression ratio, and there is still much room left for improvements along with the fast development of deep-learning techniques.

Development of a method for compressing images on the basis of JPEG algorithm

The problem of image optimization, namely the reduction of the physical size of the image by minimizing image quality as little as possible, is considered. The object of research are methods for processing and compressing images. When analyzing the methods, one of the biggest problems was discovered, which consists in the fact that when solving the problem of image processing and compression, the studied methods allow to achieve the slightest loss in quality, but as a result, the compression ratio is significantly reduced. To overcome this problem, it was decided to develop a modification of the JPEG compression algorithm. The proposed modification consists in additional quantization of the spectrum after a discrete cosine transform, and then the resulting spectrum is fed to a Huffman encoder, which makes compression even more efficient. A method is obtained for solving the image optimization problem, which allows one to obtain an image with a smaller size and a large compression ratio while maintaining optimal quality. This is due to the fact that the proposed method has a number of features, as the original color image can have 24 bits per point, in particular, the ability to set the compression ratio. Thanks to this, it is possible to obtain a signal-to-noise ratio of 54.2 dB at a quality factor of zero. Compared with the well-known LZW algorithm, which is much better, as a result of which it allows to get a processed image with a much smaller physical size. The assessment of image quality, depending on the parameters of the task. It is shown that for problems of small and medium dimensions, the developed method provides minimal quality loss. The results of solving the problem for a specific example demonstrate the advantage of the developed method over existing ones. The results can be successfully applied to solve the problem of optimizing image size while maintaining maximum quality

Automatic filter coefficient calculation in lifting scheme wavelet transform for lossless image compression

In this paper, a new method for automatic filter coefficient calculation in lifting scheme wavelet transform for image lossless compression is proposed. Actually, there is no specific rule for setting filter coefficients (a, b). Therefore, this work proposes an automatic method to calculate the filter coefficients depending on the spectral analysis of each image. Also, filter coefficients are determined for five decomposition levels and for each quadrant through applying the discrete wavelet transform in the lossless image compression problem. Spectral patterns are computed and fixed into small length vectors for building different wavelet decomposition levels; these vectors are automatically computed using a 1-NN classifier. Experimental results over standard images show that calculating the wavelet filter coefficients using the proposed method generates higher compression rates (in entropy and bitstream values) against standard wavelet and linear prediction filters.

An Image Compression Method for Video Surveillance System in Underground Mines Based on Residual Networks and Discrete Wavelet Transform

Video surveillance systems play an important role in underground mines. Providing clear surveillance images is the fundamental basis for safe mining and disaster alarming. It is of significance to investigate image compression methods since the underground wireless channels only allow low transmission bandwidth. In this paper, we propose a new image compression method based on residual networks and discrete wavelet transform (DWT) to solve the image compression problem. The residual networks are used to compose the codec network. Further, we propose a novel loss function named discrete wavelet similarity (DW-SSIM) loss to train the network. Because the information of edges in the image is exposed through DWT coefficients, the proposed network can learn to preserve the edges better. Experiments show that the proposed method has an edge over the methods being compared in regards to the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), particularly at low compression ratios. Tests on noise-contaminated images also demonstrate the noise robustness of the proposed method. Our main contribution is that the proposed method is able to compress images at relatively low compression ratios while still preserving sharp edges, which suits the harsh wireless communication environment in underground mines.

New Artificial Neural Network Models for Bio Medical Image Compression

This article presents an image compression method using feed-forward back-propagation neural networks (NNs). Marked progress has been made in the area of image compression in the last decade. Image compression removing redundant information in image data is a solution for storage and data transmission problems for huge amounts of data. NNs offer the potential for providing a novel solution to the problem of image compression by its ability to generate an internal data representation. A comparison among various feed-forward back-propagation training algorithms was presented with different compression ratios and different block sizes. The learning methods, the Levenberg Marquardt (LM) algorithm and the Gradient Descent (GD) have been used to perform the training of the network architecture and finally, the performance is evaluated in terms of MSE and PSNR using medical images. The decompressed results obtained using these two algorithms are computed in terms of PSNR and MSE along with performance plots and regression plots from which it can be observed that the LM algorithm gives more accurate results than the GD algorithm.

A fast ELM-based machine compression scheme for underwater image transmission on a low-bandwidth acoustic channel

PurposeThis paper aims to propose a fast machine compression scheme, which can solve the problem of low-bandwidth transmission for underwater images.Design/methodology/approachThis fast machine compression scheme mainly consists of three stages. Firstly, raw images are fed into the image pre-processing module, which is specially designed for underwater color images. Secondly, a divide-and-conquer (D&C) image compression framework is developed to divide the problem of image compression into a manageable size. And extreme learning machine (ELM) is introduced to substitute for principal component analysis (PCA), which is a traditional transform-based lossy compression algorithm. The execution time of ELM is very short, thus the authors can compress the images at a much faster speed. Finally, underwater color images can be recovered from the compressed images.FindingsExperiment results show that the proposed scheme can not only compress the images at a much faster speed but also maintain the acceptable perceptual quality of reconstructed images.Originality/valueThis paper proposes a fast machine compression scheme, which combines the traditional PCA compression algorithm with the ELM algorithm. Moreover, a pre-processing module and a D&C image compression framework are specially designed for underwater images.

High noise astronomical image denoising via 2G-bandelet denoising compressed sensing

In deep space exploration, high resolution astronomical image captured is often contaminated by various cosmic noise signals during its shooting and long distance transmission, which has brought inconvenience to astronomical image analysis. The famous compressed sensing (CS) proposed by Candes et al. can successfully solve the problem of high resolution astronomical image compression and low noise reconstruction. In this paper, we further concern how to reconstruct a high quality image from a high resolution and high noise astronomical image. A 2G-bandelet denoising compressed sensing (BDCS) is first proposed based on the advantage of CS in image denoising and the superior ability of 2G-bandelet in sparse representation of astronomical images, then iterative bandelet thresholding (IBT-BTCS) algorithm based on BDCS is proposed for high resolution and high noise astronomical image reconstruction. Firstly, an iterative bandelet thresholding method is designed to obtain optimal approximation of original image; Secondly, to further improve the reconstructed image quality, group sparse total variation with stepsize constraints (GSTV-SC) method is proposed to adjust the reconstructed astronomical image in each iteration. The simulation results show that the proposed algorithm can quickly reconstruct a high quality astronomical image only using a few observations, preserve more astronomical image details and effectively solve high noise astronomical image denoising problem.

Image Compression Based on Block SVD Power Method

Abstract In recent years, the important and fast growth in the development and demand of multimedia products is contributing to an insufficiency in the bandwidth of devices and network storage memory. Consequently, the theory of data compression becomes more significant for reducing data redundancy in order to allow more transfer and storage of data. In this context, this paper addresses the problem of lossy image compression. Indeed, this new proposed method is based on the block singular value decomposition (SVD) power method that overcomes the disadvantages of MATLAB’s SVD function in order to make a lossy image compression. The experimental results show that the proposed algorithm has better compression performance compared with the existing compression algorithms that use MATLAB’s SVD function. In addition, the proposed approach is simple in terms of implementation and can provide different degrees of error resilience, which gives, in a short execution time, a better image compression.

DISCRETE ATOMIC COMPRESSION OF DIGITAL IMAGES: ALMOST LOSSLESS COMPRESSION

In this paper, we consider the problem of digital image compression with high requirements to the quality of the result. Obviously, lossless compression algorithms can be applied. Since lossy compression provides a higher compression ratio and, hence, higher memory savings than lossless compression, we propose to use lossy algorithms with settings that provide the smallest loss of quality. The subject matter of this paper is almost lossless compression of full color 24-bit digital images using the discrete atomic compression (DAC) that is an algorithm based on the discrete atomic transform. The goal is to investigate the compression ratio and the quality loss indicators such as uniform (U), root mean square (RMS) and peak signal to noise ratio (PSNR) metrics. We also study the distribution of the difference between pixels of the original image and the corresponding pixels of the reconstructed image. In this research, the classic test images and the classic aerial images are considered. U-metric, which is highly dependent on even minor local changes, is considered as the major metric of quality loss. We solve the following tasks: to evaluate memory savings and loss of quality for each test image. We use the methods of digital image processing, atomic function theory, and approximation theory. The computer program "Discrete Atomic Compression: User Kit" with the mode "Almost Lossless Compression" is used to obtain results of the DAC processing of test images. We obtain the following results: 1) the difference between the smallest and the largest loss of quality is minor; 2) loss of quality is quite stable and predictable; 3) the compression ratio depends on the smoothness of the color change (the smallest and the largest values are obtained when processing the test images with the largest and the smallest number of small details in the image, respectively); 4) DAC provides 59 percent of memory savings; 5) ZIP-compression of DAC-files, which contain images compressed by DAC, is efficient. Conclusions: 1) the almost lossless compression mode of DAC provides sufficiently stable values of the considered quality loss metrics; 2) DAC provides relatively high compression ratio; 3) there is a possibility of further optimization of the DAC algorithm; 4) further research and development of this algorithm are promising.