Lossy Image Compression Research Articles

Two-channel 3D range geometry compression with primitive depth modification

Modern computing and imaging technologies have allowed for many recent advances to be made in the field of 3D range imaging: range data can now be acquired at speeds much faster than real-time, with sub-millimeter precision. However, these benefits come at the cost of an increased quantity of data being generated by 3D range imaging systems, potentially limiting the number of applications that can take advantage of this technology. One common approach to the compression of 3D range data is to encode it within the three color channels of a traditional 24-bit RGB image. This paper presents a novel method for the modification and compression of 3D range data such that the original depth information can be stored within, and recovered from, only two channels of a traditional 2D RGB image. Storage within a traditional image format allows for further compression to be realized via lossless or lossy image compression techniques. For example, when JPEG 80 is used to store the encoded output image, this method achieves an 18.2% reduction in file size when compared to a similar three-channel, image-base compression method, with only a corresponding 0.17% reduction in global reconstruction accuracy.

Dual-Tree Complex Wavelet Transform-Based Direction Correlation for Face Forgery Detection

With the rapid development of face synthesis techniques, things are going from bad to worse as high-quality fake face images are unnoticeable by human eyes, which has brought serious public confidence and security problems. Thus, effective detection of face image forgeries is in urgent need. We observe that some subtle artificial artifacts in spatial domain can be easily recognized in transformation domain, and most facial features have an inherent directional correlation, and generative models would ruffle this kind of distribution pattern. Inspired by this, we propose a two-stream dual-tree complex wavelet-based face forgery network (DCWNet) to expose face image forgeries. Specifically, dual-tree complex wavelet transform is exploited to obtain six directional features (±75°, ±45°, ±15°) of different frequency components from original images, and a direction correlation extraction (DCE) block is presented to capture the direction correlation. Then, the direction pattern-aware clues and the original image are taken as two complementary network inputs. We also explore how specific frequency components work in face forgery detection and propose a new multiscale channel attention mechanism for features fusion. The experimental results prove that the proposed DCWNet outperforms the state-of-the-art methods in open datasets such as FaceForensics++ and achieves high robustness against lossy image compression.

An entropy minimization histogram mergence scheme and its application in image compression

In this paper, we propose an entropy minimization histogram mergence (EMHM) scheme that can significantly reduce the number of grayscales with nonzero pixel populations (GSNPP) without visible loss to image quality. We proved in theory that the entropy of an image is reduced after histogram mergence and that the reduction in entropy is maximized using our EMHM. The reduction in image entropy is good for entropy encoding considering that the minimum average code word length per source symbol is the entropy of the source signal according to Shannon’s first theorem. Extensive experimental results show that our EMHM can significantly reduce the code length of entropy coding, such as Huffman, Shannon, and arithmetic coding, by over 20% while preserving the image subjective and objective quality very well. Moreover, the performance of some classic lossy image compression techniques, such as the Joint Photographic Experts Group (JPEG), JPEG2000, and Better Portable Graphics (BPG), can be improved by preprocessing images using our EMHM.

Lossy Image Compression Techniques

In recent years, domain image processing plays a most significant role in realtime applications. Due to reserved bandwidth and capacity, images are needed to be compressed, enhance, and noise-free to reduce the storage space as well as the transmission time. Compression overcomes the problem such as insufficient bandwidth of network and storage of memory device. Nowadays, many techniques are used to compress an image with a good quality. In this paper, I briefly discuss the concept of image compression and review the techniques which are used in loss image compression. This technique losses some data by using transform codes. Two codes are used to compress an image such as wavelet and fractal. The techniques scalar and vector quantization are used to quantize an input and partition into sub-images. I briefly discussed about the 2D-Discrete wavelet transform codes with examples which were done by Mat lab software.

Multi-scale network (MsSG-CNN) for joint image and saliency map learning-based compression

Lossy image compression is likely to produce blurred images which leads to erroneous image-level understanding. The human visual system (HVS) is focused on the area of interest present in the image. Motivated by this fact, we propose a compression-decompression algorithm focusing on the important content present in different parts of the image. Using the concept of the Guided Grad-CAM (Gradient-weighted Class Activation Mapping) technique to produce heat maps with the help of a heat map generator trained on ResNet-50, a saliency-guided encoding–decoding algorithm is developed. A wider multi-scale saliency guided convolutional neural network (MsSG-CNN) is designed, in which the notion of convolution with different size filters helps to obtain unique but different features. The feature extraction followed by multilevel fusion of features helps deep neural network (DNN) to capture contextual information and obtain high quality, good resolution, visually pleasing images with fine details. The proposed algorithm is tested on the Kodak benchmark dataset, CLIC 2019 challenging dataset, and FDDB facial images dataset. At low bit rates, the MS-SSIM of the proposed algorithm is found to be superior to JPEG, JPEG2000, BPG, WebP, and Minnen’s approaches with approximately up to 60%, 24.80%, 11.43%, 23.08% & 75% gains respectively, which is quite a significant improvement, when tested on the Kodak dataset. Similarly, at high bit rates, the improvement in MS-SSIM is approximately up to 41.67%, 37.30%, 23.90% 34.21% & 13.33% when compared with JPEG, JPEG2000, BPG, WebP, and Minnen’s approaches respectively. The improvement in PSNR at low and high bit rates is approximately up to 11.32%, 5%, 5.26% and 5.6%, 10.29%, 8.7% as compared to JPEG, Balle’s, and Lee’s algorithms respectively. The PSNR-HVS has been improved by approximately up to 27.27%, 19.15%, and 28.33%, 28% as compared to JPEG and Toderici’s algorithms respectively at low and high bit-rates. A similar type of improvement is obtained with FDDB and CLIC 2019 datasets also, which is discussed in the paper.

Image compression based on octave convolution and semantic segmentation

Lossy image compression based on deep learning usually contains stacking convolutional layers, pooling layers, and nonlinear functions. However, the feature map is obtained by the convolutional layer, which has a lot of redundancy, so we use octave convolution instead of vanilla convolution to improve compression efficiency. The feature map can be divided into high-frequency and low-frequency information. We use octave convolution to design an automatic codec to decompose the feature map into high-frequency and low-frequency information, which effectively improves the quality of the generated image. First, the semantic segmentation map of the input image is obtained by pre-training SegNet. The ComNet uses the original image and the semantic segmentation map to generate a low-dimensional representation, and the GenNet network utilizes the low-dimensional representation and the semantic segmentation map to estimate images. Then, the residuals between the reconstructed image and the original image are encoded. Finally, the reconstructed image and the decoded residual image are used to obtain the final high-quality reconstruction. Experimental results show that our method outperforms the existing image coding standards in terms of PSNR and MS-SSIM at different bit rates, and the reconstruction of images with complex textures and semantics has more obvious advantages.

Lossy image compression based on efficient multiplier-less 8-points DCT

Lossy image compression based on efficient multiplier-less 8-points DCT

Adaptive color space model based on dominant colors for image and video compression performance improvement

This paper describes the use of some color spaces in JPEG image compression algorithm and their impact in terms of image quality and compression ratio, and then proposes adaptive color space models (ACSM) to improve the performance of lossy image compression algorithm. The proposed ACSM consists of, dominant color analysis algorithm and YCoCg color space family. The YCoCg color space family is composed of three color spaces, which are YCcCr, YCpCg and YCyCb. The dominant colors analysis algorithm is developed which enables to automatically select one of the three color space models based on the suitability of the dominant colors contained in an image. The experimental results using sixty test images, which have varying colors, shapes and textures, show that the proposed adaptive color space model provides improved performance of 3 % to 10 % better than YCbCr, YDbDr, YCoCg and YCgCo-R color spaces family. In addition, the YCoCg color space family is a discrete transformation so its digital electronic implementation requires only two adders and two subtractors, both for forward and inverse conversions.

Compression of Monochromatic and Multicolored Image with Neural Network

Nowadays we have so much images provided by different types of machines, while we need to store them or transfer to other devices or via internet, we need to compress them because the images usually have large amount of size. Compressing them reduces time for transferring files. The compression can be done with different methods and software in order to reduce their capacity expressed in megabytes as much as tens of hundreds of gigabytes for more files. It is well known that the speed of information transmission depends mainly on its quantity or the capacity of the information package. Image compression is a very important task for data transfer and data storage, especially nowadays because of the development of many image acquisition devices. If there is no compression technique used on these data, they may occupy immense space of memory, or render difficult data transmission. Artificial Neural Networks (ANN) have demonstrated good capacities for lossy image compression. The ANN algorithm we investigate is BEP-SOFM, which uses a Backward Error Propagation algorithm to quickly obtain the initial weights, and then these weights are used to speed up the training time required by the Self-Organizing Feature Map algorithm. In order to obtain these initial weights with the BEP algorithm, we analyze the hierarchical approach, which consists in preparing the image to compress using the quadtree data structure by segmenting the image into blocks of different sizes. Small blocks are used to represent image areas with large-scale details, while the larger ones represent the areas that have a small number of observed details. Tests demonstrate that the approach of quadtree segmentation quickly leads to the initial weights using the BEP algorithm.

Approximate calculation of 8-point DCT for various scenarios of practical applications

In this paper, based on the parametric model of the matrix of discrete cosine transform (DCT), and using an exhaustive search of the parameters’ space, we seek for the best approximations of 8-point DCT at the given computational complexities by taking into account three different scenarios of practical usage. The possible parameter values are selected in such a way that the resulting transforms are only multiplierless approximations, i.e., only additions and bit-shift operations are required. The considered usage scenarios include such cases where approximation of DCT is used: (i) at the data compression stage, (ii) at the decompression stage, and (iii) both at the compression and decompression stages. The obtained results in effectiveness of generated approximations are compared with results of popular known approximations of 8-point DCT of the same class (i.e., multiplierless approximations). In addition, we perform a series of experiments in lossy compression of natural images using popular JPEG standard. The obtained results are presented and discussed. It should be noted, that in the overwhelming number of cases the generated approximations are better than the known ones, e.g., in asymmetric scenarios even by more than 3 dB starting from entropy of 2 bits per pixel. In the last part of the paper, we investigate the possibility of hardware implementation of generated approximations in Field-Programmable Gate Array (FPGA) circuits. The results in the form of resource and energy consumption are presented and commented. The experiment outcomes confirm the assumption that the considered class of transformations is characterized by low resource utilization.

Transcoding authenticity: preserving unreleased gaming software outside of memory institutions

PurposeThis paper aims to introduce new criteria for evaluating authenticity in digital preservation, particularly in cases related to unreleased software projects and preservation work that occurs in non-institutional settings.Design/methodology/approachInterpretive visual and formal analysis of image files is performed on three overlapping preservation efforts to understand the ways that self-appointed preservationists reframe content in varied settings. The unreleased mid-1990s console game Sonic X-Treme is used as a case study because assets from the development process have been widely preserved among former developers and enthusiasts alike.FindingsThe findings indicate that non-professional preservationists transcode original production files into a variety of formats, ranging from lossy compressed images to contemporary three-dimensional (3D) modeling files. Materials are presented in settings that range from colorful webpages mimicking the appearance of commercial software to browsable file systems. These results show that non-institutional preservation practices embody notions of authenticity that diverge significantly from those of professional archivists.Research limitations/implicationsThe study is limited by its focus on a single case study, but helps to facilitate ongoing research concerning preservation of unreleased projects insofar as it surveys the current status of existing projects.Originality/valueExisting studies within preservation literature have established the need for increased attention paid to unfinished digital works. This study introduces new data and interpretative findings that outline such preservation efforts as they already occur in non-institutional settings.

Image Compression Techniques Using Linear Algebra with SVD Algorithm

In recent days, the data are transformed in the form of multimedia data such as images, graphics, audio and video. Multimedia data require a huge amount of storage capacity and transmission bandwidth. Consequently, data compression is used for reducing the data redundancy and serves more storage of data. In this paper, addresses the problem (demerits) of the lossy compression of images. This proposed method is deals on SVD Power Method that overcomes the demerits of Python SVD function. In our experimental result shows superiority of proposed compression method over those of Python SVD function and some various compression techniques. In addition, the proposed method also provides different degrees of error flexibility, which give minimum of execution of time and a better image compression.

Convolution Neural Network based lossy compression of hyperspectral images

The large size of hyperspectral imaging poses a significant threat to its potential use in real life due to the abundant information stored in it. The use of deep learning for such data processing is visible in recent applications. In this work, we propose a lossy hyperspectral image compression algorithm based on the concept of autoencoders. It uses a combination of the convolution layer and max-pooling layer to reduce the dimensions of the input image and generate a compressed image. The original image with some loss of information is reconstructed using transpose convolution layer that uses reverse of the procedure used by the encoder. The compressed image has been entropy coded using an adaptive arithmetic coder for transmission or storage application. The method provides an improvement of 28% in PSNR with 21 times increment in the compression ratio. The effect of compression on classification has also been evaluated in the experiment using state of art classification algorithm. Negligible difference in classification accuracy was obtained that proves the effectiveness of the proposed algorithm.

VQ-oriented data hiding based on adjustable error compensation strategy

Nowadays, we greatly depend on Internet mass transmission, of all kinds of data, including critical information among them. Therefore, secure communication is an important topic. Data hiding can embed critical information into carriers, such as images, videos, and so on. Efficiently embedding information into images is the goal of this research. Image steganography techniques utilise a cover image to hide secret data and produce a stego-image by modifying pixel values. After modification, the stego-image is distorted with respect to the cover image. Vector quantisation (VQ) is a lossy image compression technique. The image recovered from the VQ compressed code has distortion compared to the original image. Based on the VQ image, we can hide secret data by modifying the pixel value in a way that the distortion is compensated. The embedding rate of the proposed scheme is adjustable. Experimental results show that our scheme can achieve a high embedding rate in comparison with related works. For low-quality VQ images, embedding can improve the visual quality of the stego-image at the same time.

Singular vector sparse reconstruction for image compression

Generally, more than half of smaller singular values and corresponding singular vectors should be abandoned to achieve the image compression function for the compression method based on singular value decomposition (SVD). Although these discarded parts contain some noise and fuzzy factors, they also contain some detailed information to boost image reconstruction. To overcome this problem, we present a novel lossy image compression method named singular vector sparse reconstruction (SVSR) keeping the sparse representation data of more singular vector to boost the performance of SVD based image compression method in compression ratio and reconstruction quality. Specifically, we treat the singular vector as a signal and express it sparsely through sparse sampling based on the analysis of the characteristics of the singular vector. In particular, the compression ratio of the proposed method is about 70% higher than that of the traditional SVD method. Evaluation on several image data and the experimental results with different image compression algorithms clearly demonstrate the advantages of our proposed SVSR algorithm in compression ratio and reconstruction quality.

Variable-length image compression based on controllable learning network

While neural-network-based lossy image compression methods have shown impressive performance, most of them output a fixed-length coding using a trained-specific network. However, it is essential to support the variable-length compression or meet a target rate with a high-coding performance in practice. This paper steps forward the neural-network-based image compression method, making it possible for a single network model to generate variable compression rates. Our network model combines an auto-encoder (AE) and a generative adversarial network (GAN) for generative compression. We introduce a noise interference mechanism to train the feature representation produced by the encoder, making the feature nodes training controllable and distributed from top to bottom according to their importance in feature expression. Based on this importance distribution, the latent nodes are quantized into bits and the variable-length compression can be achieved by discarding bits of those less-important feature nodes to meet the compression target. We propose several noise interference methods, and the experiments confirm the feasibility of method Random-add and Dropout in controllable learning. Further experiments illustrate that our compression method can not only achieve variable-length compression but also can recover high-quality compressed images at extremely low bit rates, outperforming that with a fixed rate.

Reduced-Complexity End-to-End Variational Autoencoder for on Board Satellite Image Compression

Recently, convolutional neural networks have been successfully applied to lossy image compression. End-to-end optimized autoencoders, possibly variational, are able to dramatically outperform traditional transform coding schemes in terms of rate-distortion trade-off; however, this is at the cost of a higher computational complexity. An intensive training step on huge databases allows autoencoders to learn jointly the image representation and its probability distribution, possibly using a non-parametric density model or a hyperprior auxiliary autoencoder to eliminate the need for prior knowledge. However, in the context of on board satellite compression, time and memory complexities are submitted to strong constraints. The aim of this paper is to design a complexity-reduced variational autoencoder in order to meet these constraints while maintaining the performance. Apart from a network dimension reduction that systematically targets each parameter of the analysis and synthesis transforms, we propose a simplified entropy model that preserves the adaptability to the input image. Indeed, a statistical analysis performed on satellite images shows that the Laplacian distribution fits most features of their representation. A complex non parametric distribution fitting or a cumbersome hyperprior auxiliary autoencoder can thus be replaced by a simple parametric estimation. The proposed complexity-reduced autoencoder outperforms the Consultative Committee for Space Data Systems standard (CCSDS 122.0-B) while maintaining a competitive performance, in terms of rate-distortion trade-off, in comparison with the state-of-the-art learned image compression schemes.

Two-Channel 3D Range Geometry Compression with Virtual Plane Encoding

Modern computing and imaging technologies have allowed for many recent advances to be made in the field of 3D range imaging: range data can now be acquired at speeds much faster than real-time, with sub-millimeter precision. However, these benefits come at the cost of an increased quantity of data being generated by 3D range imaging systems, potentially limiting the number of applications that can take advantage of this technology. One common approach to the compression of 3D range data is to encode it within the three color channels of a traditional 24-bit RGB image. This paper presents a novel method for the modification and compression of 3D range data such that the original depth information can be stored within, and recovered from, only two channels of a traditional 2D RGB image. Storage within a traditional image format allows for further compression to be realized via lossless or lossy image compression techniques. For example, when JPEG 80 was used to store the encoded output image, this method was able to achieve an 18.2% reduction in file size when compared to a similar three-channel, image-base compression method, with only a corresponding 0.17% reduction in global reconstruction accuracy.

Hybrid Encoding Scheme for AMBTC Compressed Images Using Ternary Representation Technique

Absolute moment block truncated coding (AMBTC) is a lossy image compression technique aiming at low computational cost, and has been widely studied. Previous studies have investigated the performance improvement of AMBTC; however, they often over describe the details of image blocks during encoding, causing an increase in bitrate. In this paper, we propose an efficient method to improve the compression performance by classifying image blocks into flat, smooth, and complex blocks according to their complexity. Flat blocks are encoded by their block means, while smooth blocks are encoded by a pair of adjusted quantized values and an index pointing to one of the k representative bitmaps. Complex blocks are encoded by three quantized values and a ternary map obtained by a clustering algorithm. Ternary indicators are used to specify the encoding cases. In our method, the details of most blocks can be retained without significantly increasing the bitrate. Experimental results show that, compared with prior works, the proposed method achieves higher image quality at a better compression ratio for all of the test images.

Learning End-to-End Lossy Image Compression: A Benchmark.

Image compression is one of the most fundamental techniques and commonly used applications in the image and video processing field. Earlier methods built a well-designed pipeline, and efforts were made to improve all modules of the pipeline by handcrafted tuning. Later, tremendous contributions were made, especially when data-driven methods revitalized the domain with their excellent modeling capacities and flexibility in incorporating newly designed modules and constraints. Despite great progress, a systematic benchmark and comprehensive analysis of end-to-end learned image compression methods are lacking. In this paper, we first conduct a comprehensive literature survey of learned image compression methods. The literature is organized based on several aspects to jointly optimize the rate-distortion performance with a neural network, i.e., network architecture, entropy model and rate control. We describe milestones in cutting-edge learned image-compression methods, review a broad range of existing works, and provide insights into their historical development routes. With this survey, the main challenges of image compression methods are revealed, along with opportunities to address the related issues with recent advanced learning methods. This analysis provides an opportunity to take a further step towards higher-efficiency image compression. By introducing a coarse-to-fine hyperprior model for entropy estimation and signal reconstruction, we achieve improved rate-distortion performance, especially on high-resolution images. Extensive benchmark experiments demonstrate the superiority of our model in rate-distortion performance and time complexity on multi-core CPUs and GPUs.