Lossy Image Compression Technique Research Articles

Denoising Diffusion Models on Model-Based Latent Space

With the recent advancements in the field of diffusion generative models, it has been shown that defining the generative process in the latent space of a powerful pretrained autoencoder can offer substantial advantages. This approach, by abstracting away imperceptible image details and introducing substantial spatial compression, renders the learning of the generative process more manageable while significantly reducing computational and memory demands. In this work, we propose to replace autoencoder coding with a model-based coding scheme based on traditional lossy image compression techniques; this choice not only further diminishes computational expenses but also allows us to probe the boundaries of latent-space image generation. Our objectives culminate in the proposal of a valuable approximation for training continuous diffusion models within a discrete space, accompanied by enhancements to the generative model for categorical values. Beyond the good results obtained for the problem at hand, we believe that the proposed work holds promise for enhancing the adaptability of generative diffusion models across diverse data types beyond the realm of imagery.

FitDepth: fast and lite 16-bit depth image compression algorithm

This article presents a fast parallel lossless technique and a lossy image compression technique for 16-bit single-channel images. Nowadays, such techniques are “a must” in robotics and other areas where several depth cameras are used. Since many of these algorithms need to be run in low-profile hardware, as embedded systems, they should be very fast and customizable. The proposal is based on the consideration of depth images as surfaces, so the idea is to split the image into a set of polynomial functions that each describes a part of the surface. The developed algorithm herein proposed can achieve a similar—or better—compression rate and especially higher speed rates than the existing techniques. It also has the potential of being fully parallelizable and to run on several cores. This feature, compared to other approaches, makes it useful for handling and streaming multiple cameras simultaneously. The algorithm is assessed in different situations and hardware. Its implementation is rather simple and is carried out with LIDAR captured images. Therefore, this work is accompanied by an open implementation in C++.

Optimized Block-Based Lossy Image Compression Technique for Wireless Sensor Networks

Optimized Block-Based Lossy Image Compression Technique for Wireless Sensor Networks

Comparison of lossy image compression techniques

Comparison of lossy image compression techniques

Comparison of lossy image compression techniques

Comparison of lossy image compression techniques

Iris Image Compression Using Deep Convolutional Neural Networks.

Compression is a way of encoding digital data so that it takes up less storage and requires less network bandwidth to be transmitted, which is currently an imperative need for iris recognition systems due to the large amounts of data involved, while deep neural networks trained as image auto-encoders have recently emerged a promising direction for advancing the state-of-the-art in image compression, yet the generalizability of these schemes to preserve the unique biometric traits has been questioned when utilized in the corresponding recognition systems. For the first time, we thoroughly investigate the compression effectiveness of DSSLIC, a deep-learning-based image compression model specifically well suited for iris data compression, along with an additional deep-learning based lossy image compression technique. In particular, we relate Full-Reference image quality as measured in terms of Multi-scale Structural Similarity Index (MS-SSIM) and Local Feature Based Visual Security (LFBVS), as well as No-Reference images quality as measured in terms of the Blind Reference-less Image Spatial Quality Evaluator (BRISQUE), to the recognition scores as obtained by a set of concrete recognition systems. We further compare the DSSLIC model performance against several state-of-the-art (non-learning-based) lossy image compression techniques including: the ISO standard JPEG2000, JPEG, H.265 derivate BPG, HEVC, VCC, and AV1 to figure out the most suited compression algorithm which can be used for this purpose. The experimental results show superior compression and promising recognition performance of the model over all other techniques on different iris databases.

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.

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.

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.

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.

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.

New Quality Metric for Compressed Images

The field of image processing has several applications in our daily life. The image quality can be affected by a wide variety of deformations during image acquisition, transmission, compression, etc. Image compression is one of the applications where the quality of the image plays an important role since it can be used to evaluate the performance of various image compression techniques. Many image quality assessment metrics have been proposed. This paper proposes a new metric to assess the quality of compressed images. The principle idea of this metric is to estimate the amount of lost information during image compression process using three components: error magnitude, error location and error distribution. We denote this metric as MLD, which combines the objective assessment (error magnitude) and the subjective assessment (error location and error distribution). First, the metric is used to estimate the quality of compressed images using the JPEG algorithm as this is a standard lossy image compression technique. Then, the metric is used to estimate the quality of compressed images using other compression techniques. The results illustrate that the proposed quality metric is correlated with the subjective assessment better than other well-known objective quality metrics such as SSIM, MSE and PSNR. Moreover, using the proposed metric the JPEG2000 algorithm produces better quality results as compared to the JPEG algorithm especially for higher compression ratios

Lossless Hybrid Coding technique based on Quasi Fractal & Oscillation Concept Method for Medical Image Compression

The Image compression is the most important entity in various fields. Image compression plays vital role in many applications. Out of which biomedical is one of the challenging applications. In medical research, everyday there is fast development and advancement. Medical researchers are thinking about digital storage of data hence medical image compression has a crucial role in hospitals. Here Morphological filter & adaptive threshold are used for refinement and used Quasi Fractal & Oscillation concept for developing new hybrid algorithm. Oscillation concept is lossy image compression technique hence applied on Non-ROI. Quasi fractal is lossless image compression technique applied on ROI. The experimental results shows that better CR with acceptable PSNR has been achieved using hybrid technique based on Morphological band pass filter and Adaptive thresholding for ROI. Here, innovative hybrid technique gives the CR 24.61 which improves a lot than hybrid method using BTC-SPIHT is 5.65. Especially PSNR is also retained and bit improved i.e. 33.51. This hybrid technique gives better quality of an image.

CUDA implementation of fractal image compression

Fractal coding is a lossy image compression technique, which encodes the image in a way that would require less storage space using the self-similar nature of the image. The main drawback of fractal compression is the high encoding time. This is due to the hard task of finding all fractals during the partition step and the search for the best match of fractals. Lately, GPUs (Graphical Processing Unit) have been exploited to implement fractal image compression algorithms due to their high computational power. The prime aim of this paper is to design and implement a parallel version of the Fisher classification scheme using CUDA to exploit the computational power available in the GPUs. Fisher classification scheme is used to reduce the encoding time of fractal images by limiting the search for the best match of fractals. Encoding time, compression ratio and peak signal-to-noise ratio was used as metrics to assess the correctness and the performance of the developed algorithm. Eight images with different sizes (512 × 512, 1024 × 1024 and 2048 × 2048) have been used for the experiments. The conducted experiments showed that a speedup of 6.4 × was achieved in some images using NVIDIA GeForce GT 660 M GPU.

Optimization of Image Compression algorithms using DWT- DCT method

Information is generated at very high speed in today’s Digital Era. Images have vast share in Information generated, so it’s important to reduce the image file size for storage and effective communication. Image compression technique helps in reducing storage and bandwidth requirement for transmission. Optimization of Image compression algorithms is the basic crux of this paper. DCT is most popularly used lossy image compression technique. It has disadvantage that at higher compression ratio the quality of image is lost. DCT is applied to set of images, followed by DWT. The resultant compression metrics are calculated and visual quality of image is analyzed. Experimental analysis shows reduction in storage space requirement and effective optimization using different methodology.

Event Image Archive using Codebook Generation

Objective: To develop a system that aims at optimal storage for voluminous image data sets that are acquired during various events, by generating codebook for image clusters by exploiting the fact that these images are generally multiple shots of similar scenes at frequent intervals. Methods: Images taken during the events on various occasions in organizations are increasing exponentially and pose tremendous challenge in terms of storage and retrieval. The volume, veracity and variety of features present in image data induce complexity in computation. Optimal storage and efficient tagging will ease the retrieval process of these image data. Among various lossy image compression techniques, vector quantization yields desirable compression ratio in many applications and is one of the efficient approaches for image compression. In this research work, vector quantization technique is explored to optimize the storage space required to maintain an archive of event image data set, by generating code book for a cluster of images. Findings: The similarity in the images that are acquired during a short span of time induces redundancy. This fact has been exploited by organizing the image data set into clusters that are similar. For each cluster, vector quantization technique is used to generate code book. The codebook generated has been used to encode the image by creating an index table for each image. The codebook of the cluster and the index table of each image is further used for decoding. The compression ratio and the peak signal to noise ratio of this method are above eighty percent and thirty DB respectively. Applications: The codebook generation technique described in this work could be applied for creating image archives. Archival images are generally voluminous and consume huge storage space. The code book generated for image clusters would reduce the storage requirement. This work also finds its application in transmitting video and image clusters in a network.

COMPARATIVE ANALYSIS: PCA AND JPEG

This paper mainly address the image compression by using Principal component analysis (PCA) and JPEG. Image compression is the method of converting data file into smaller compact files for efficiency of storage and transmission. The main objective of compression of image is to reduce redundancy of bits in the image in order to store and transmit data in an effective way. Image compression techniques deal with the problem of reduction in size of the file which results in efficient storage of image and bandwidth to transmit it. Image Compression helps in storage of more information in a given memory space.PCA is mathematical tool which is used for reducing the dimensionality of data .PCA extracts major variation in the data sets while removing other insignificant components. In this paper PCA is applied for image compression. Since PCA compression is lossy the compressed image is generally degraded as compared to original image. Also PCA is compared with most commonly used image compression technique which is JPEG.JPEG is also a lossy image compression technique which start by separating the image into 8*8 pixel groups and applying DCT transform individual 8*8 pixel groups .In this paper PCA and JPEG compression are applied to the image and various parameter like PSNR and MSE is calculated for both of the compression technique. The Mean Square Error (MSE) and the Peak Signal to Noise Ratio (PSNR) are the two error parameter used to compare image compression quality

Multiwavelength depth encoding method for 3D range geometry compression.

This paper presents a novel method for representing three-dimensional (3D) range data within regular two-dimensional (2D) images using multiwavelength encoding. These 2D images can then be further compressed using traditional lossless (e.g.,PNG) or lossy (e.g.,JPEG) image compression techniques. Current 3D range data compression methods require significant filtering to reduce lossy compression artifacts. The nature of the proposed encoding, however, offers a significant level of robustness to such artifacts brought about by high levels of JPEG compression. This enables extremely high compression ratios while maintaining a very low reconstruction error percentage with little to no filtering required to remove compression artifacts. For example, when encoding 3D geometry with the proposed method and storing the resulting 2D image with Matlab R2014a JPEG80 image compression, compression ratios of approximately 935:1 versus the OBJ format can be achieved at an error rate of approximately 0.027% without any filtering.