Compressed Images Research Articles

Image Processing Techniques for COVID-19 Detection in Chest CT

COVID-19 virus is a disease that has spread around the world recently. Early diagnosis of the disease leads us to the opportunity to treat patients faster to reduce its spread in the community. The CT scan image is one of the routines used to diagnose the COVID-19 diseases in an efficient manner and in a faster time. Fractal Dimension which mean (fragmented or irregular) used in wide range of image processing and analysis applications to get the self- similarity of images. To classify textures, combine images, segment and compress images and to generate incredibly complex and good-looking images, the Fractal Dimension method is used. Moreover, Euler method uses features to explain the structural property caused by noise in binary images. It also describes the topological features and analyze the texture of images. In this paper, a method is proposed to obtain the features of CT scan images for COVID-19 by using a hybrid technique called Fractal Dimension Euler (FDE), which merges the two methods of image processing (Fractal Dimension method and Euler Number Method). The two algorithms aim to segment the CT-scan images for the chest to distinguish between the affected and uninfected area of the chest to detect the COVID-19. The results of the proposed approach were very useful in comparison with another approach, the FD method was applied to CT scan images for COVID- 19 using a method called box counting. After that, the Euler method was used to distinguish between foreground and background by using a threshold value. The best threshold value was (255) which achieved the finest result.

Double Color Image Visual Encryption Based on Digital Chaos and Compressed Sensing

Image encryption is an effective way to protect images in secure transmission or storage. In this paper, we propose a novel double color image visual encryption algorithm based on the improved Chebyshev map (ICM) and compressed sensing. Firstly, a new nonlinear term is introduced into the classical one-dimensional Chebyshev map, and then the ICM is used to generate the secret code stream for the encryption algorithm. Next, the key-controlled sensing measurement matrices are constructed through the ICM, and they are used to compress the integer wavelet coefficients of two plain images. Subsequently, the compressed images are dislocated by dislocation matrices and diffused by an ICM-generated diffusion matrix, respectively. Finally, the encrypted images are embedded into the carrier image using the least significant bit embedding algorithm. Experimental results demonstrate that the proposed method has good visual safety, large key space, and high key sensitivity.

A K-SVD Based Compressive Sensing Method for Visual Chaotic Image Encryption

The visually secure image encryption scheme is an effective image encryption method, which embeds an encrypted image into a visual image to realize a secure and secret image transfer. This paper proposes a merging compression and encryption chaos image visual encryption scheme. First, a dictionary matrix D is constructed with the plain image by the K-SVD algorithm, which can encrypt the image while sparsing. Second, an improved Zeraoulia-Sprott chaotic map and logistic map are employed to generate three S-Boxes, which are used to complete scrambling, diffusion, and embedding operations. The secret keys of this scheme contain the initial value of the chaotic system and the dictionary matrix D, which significantly increases the key space, plain image correlation, and system security. Simulation shows the proposed image encryption scheme can resist most attacks and, compared with the existing scheme, the proposed scheme has a larger key space, higher plain image correlation, and better image restoration quality, improving image encryption processing efficiency and security.

Research on Spaceborne Target Detection Based on Yolov5 and Image Compression

Satellite image compression technology plays an important role in the development of space science. As optical sensors on satellites become more sophisticated, high-resolution and high-fidelity satellite images will occupy more storage. This raises the required transmission bandwidth and transmission rate in the satellite–ground data transmission system. In order to reduce the pressure from image transmission on the data transmission system, a spaceborne target detection system based on Yolov5 and a satellite image compression transmission system is proposed in this paper. It can reduce the pressure on the data transmission system by detecting the object of interest and deciding whether to transmit. An improved Yolov5 network is proposed to detect the small target on the high-resolution satellite image. Simulation results show that the improved Yolov5 network proposed in this paper can detect specific targets in real satellite images, including aircraft, ships, etc. At the same time, image compression has little effect on target detection, so detection complexity can be effectively reduced and detection speed can be improved by detecting the compressed images.

Compressed phase coding-based optical image encryption

With the development of artificial intelligence technology, the traditional inflexible optical image encryption system has been difficult to resist security attacks such as chosen-plaintext attack and known-plaintext attack, and its security has been greatly challenged. Therefore, an optical image encryption method based on compressed phase coding is proposed, in which a spatial light modulator (SLM) is used to encode the phase of the optical system randomly, and then combined with the measurement matrix in the single pixel sampling process to build a flexible key system. In the encryption process, a phase-only SLM is firstly implemented to realize phase encoding of the original plaintext image and loading the phase key. Then the modulated reference light is implemented to further hide the complex amplitude distribution of the encrypted image. Finally, the encoded object light and reference light are coherently superimposed in the digital micromirror device (DMD), and the inner product operation is carried out with the measurement matrix to realize further encryption and collected by the single pixel detector. Both simulation and experiment proved that the proposed compressed phase coding-based image encryption system is similar to "one time one pad" cryptographic system, which greatly improves the security of the optical encryption system.

Super-Resolution of Compressed Images Using Residual Information Distillation Network

Super-Resolution (SR) is a fundamental computer vision task, which reconstructs high-resolution images from low-resolution ones. Existing SR methods mainly recover images from clear low-resolution images, leading to unsatisfactory results when processing compressed low-resolution images. In the paper, we propose a two-stage SR method for compressed images, which consists of the Compression Artifact Removal Module (CARM) and Super-Resolution Module (SRM). The compressed low-resolution image is used to reconstruct the clear low-resolution image by CARM, and the high-resolution image is obtained by SRM. In addition, we propose a residual information distillation block to learn the texture details which are lost during the compression process. The proposed method has been validated and compared with the state of the art, and experimental results show that the proposed method outperforms other super-resolution methods in terms of visual effects and objective evaluation metrics.

DFCE: Decoder-Friendly Chrominance Enhancement for HEVC Intra Coding

We propose a decoder-friendly chrominance enhancement method for the compressed images. Our proposed method is developed based on the luminance-guided chrominance enhancement network (LGCEN) and online learning. With LGCEN, the textures of the compressed chrominance components are enhanced by the guidance of luminance component. Moreover, LGCEN is constructed with the recursive design and the light-weight channel attention mechanism to achieve high performance as well as low complexity. It is arranged at both encoder and decoder sides. Given the input image, we train LGCEN at encoder side by using online learning. With online learning, we partially update network parameters and transmit them to decoder to update LGCEN arranged there. The adoption of online learning effectively reduces the workload of decoder and guarantee high robustness. Compared with the state-of-the-art methods, our proposed approach achieves superior performance.

On classifier performance for remote sensing images compressed by different coders

Remote sensing data are widely used in numerous applications. A conventional task solved using remote sensing images is their classification. The classification maps are commonly produced by some pre-trained classifiers applied either to uncompressed or compressed images where lossy compression is often needed and employed in practice due to the necessity to reduce data volume at stages of image transfer and storage. Then, the classification accuracy depends on the characteristics of an image, a classifier, and a coder used. The main subject of this paper is the factors that determine classification accuracy. One of them is compressed image quality. We fix the quality of compressed image quality characterized by the peak signal-to-noise ratio for several coders and rely on the same training approach. Our goal is twofold. First, we would like to consider classification accuracy for two approaches to classifier training: based on undistorted data and images with simulated distortions. Second, our desire is to compare the performance of different techniques of image compression. The task of this paper is to obtain an idea is it worth training the neural network classifier for uncompressed images or images of similar quality to the quality of compressed data to be classified. The coder’s influence on classification results is of special interest as well. The main results are the following. First, the classification accuracy is almost the same for classifiers trained for uncompressed and simulated compressed data for the general distortion model. Second, there is a certain difference in the classification results for different compression techniques studied. Lightly better classification results are observed for data produced by more sophisticated (modern) coders. Experiments have been carried out for two real-life three-channel Sentinel-2 images of Kharkiv and the Kharkiv region having different complexity. Four typical classes have been considered. As a conclusion, it is possible to state that either the general model of distortions must be modified or the classifier training should be performed for data produced by the corresponding compression technique.

High-speed compressive wide-field fluorescence microscopy with an alternant deep denoisers-based image reconstruction algorithm

As an indispensable tool to observe the microcosmic structures and dynamics, wide-field fluorescence microscopy (WFM) has been widely applied in biological and medical areas, but the low imaging speed hinders its applications in high-speed fluorescent dynamics due to the limited frame rate of the camera. Here, we develop a high-speed compressive wide-field fluorescence microscopy (CWFM) to break the imaging speed limitation of conventional WFM. In our CWFM method, a coded aperture temporal compressive imaging technique is introduced into conventional WFM system to accelerate the imaging speed by reconstructing multiple images from every compressed image. An iterative algorithm with alternant deep denoisers of FFDnet and FastDVDnet is designed to reconstruct high-quality sequential images from every compressed image through spatial denoising and temporal constraining. The high-speed imaging ability of CWFM is verified by measuring the movement of fluorescence beads on a slide, and an imaging speed of 2000 Hz is experimentally obtained with an ordinary CMOS camera of 200 Hz, the imaging speed is increased by an order of magnitude. Using our high-speed CWFM system, we successfully observe the hydrodynamics by detecting the flow of fluorescence beads in the water across a corner of microchannel. This technique provides a well-established tool for detecting the high-speed fluid and biological dynamic scene, especially in microflow and cell tracking.

Frequency Domain Filtered Residual Network for Deepfake Detection

As deepfake becomes more sophisticated, the demand for fake facial image detection is increasing. Although great progress has been made in deepfake detection, the performance of most existing deepfake detection methods degrade significantly when these methods are applied to detect low-quality images for the disappearance of key clues during the compression process. In this work, we mine frequency domain and RGB domain information to specifically improve the detection of low-quality compressed deepfake images. Our method consists of two modules: (1) a preprocessing module and (2) a classification module. In the preprocessing module, we utilize the Haar wavelet transform and residual calculation to obtain the mid-high frequency joint information and fuse the frequency map with the RGB input. In the classification module, the image obtained by concatenation is fed to the convolutional neural network for classification. Because of the combination of RGB and frequency domain, the robustness of the model has been greatly improved. Our extensive experimental results demonstrate that our approach can not only achieve excellent performance when detecting low-quality compressed deepfake images, but also maintain great performance with high-quality images.

Robust, practical and comprehensive analysis of soft compression image coding algorithms for big data

With the advancement of intelligent vision algorithms and devices, image reprocessing and secondary propagation are becoming increasingly prevalent. A large number of similar images are being produced rapidly and widely, resulting in the homogeneity and similarity of images. Moreover, it brings new challenges to compression systems, which need to exploit the potential of deep features and side information of images. However, traditional methods are incompetent for this issue. Soft compression is a novel data-driven image coding algorithm with superior performance. Compared with existing paradigms, it has distinctive characteristics: from hard to soft, from pixels to shapes, and from fixed to random. Soft compression may hold promise for human-centric/data-centric intelligent systems, making them efficient and reliable and finding potential in the metaverse and digital twins, etc. In this paper, we present a comprehensive and practical analysis of soft compression, revealing the functional role of each component in the system.

Quantum Approach to Image Data Encoding and Compression

High-resolution images are being generated due to the rapid development of image sensors. Various image processing algorithms require images of reduced sizes, given the computational constraints. Hence, preprocessing the images to reduce their size is crucial for many applications. This letter proposes a novel approach to compress images using quantum computing. A comparative study on different standard data encoding techniques used in quantum computing is undertaken. We propose four quantum compression techniques by extending the unitary operations of amplitude embedding for compressing images. The proposed methods provide exponential scaling as amplitude embedding is used, where <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$2^{n}$</tex-math></inline-formula> classical data values are encoded into <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$n$</tex-math></inline-formula> qubits. Compression performance, visual evaluation, and objective evaluation are carried out to assess the proposed compression techniques. Our experimental results show that the crucial patterns in images are retained in the compressed images even at 75% compression. The compressed images can be used for postprocessing tasks using classical or quantum computing algorithms.

A low-overhead compressed sensing-driven multi-party secret image sharing scheme

A low-overhead compressed sensing-driven multi-party secret image sharing scheme

A Chaotic Compressed Sensing-Based Multigroup Secret Image Sharing Method for IoT With Critical Information Concealment Function

Nowadays, the requirements for image data sharing among participant nodes of the Internet of Things (IoT) are constantly emerging. And thanks to the popularity of digital cameras and the development of digital photography technologies, the processes of data sharing commonly concern substantial amounts of data that may contain critical or private information. So, how to design a secure and efficient secret image sharing (SIS) method suitable for IoT apparatuses is attracting ever-increasing attention. With the aim of simultaneously realizing SIS, image data compression, and critical information or privacy protection, this article proposes a multigroup SIS method based on the model of compressed sensing (CS) and chaos theory. In the proposed method, participants of SIS are classified into two groups with different authorization levels. Solely members of full-authorized groups could reconstruct secret images with visible critical sectors. Members of restricted-authorized groups, however, could merely obtain reconstruction results with critical sectors concealed. The CS model is introduced to the proposed method to accomplish image data compression and applications of the chaos theory contribute to the secure data transmission. Experimental simulations and theoretical analyses are performed to discuss the feasibility, flexibility, and security of the proposed method.

CWC-transformer: a visual transformer approach for compressed whole slide image classification

CWC-transformer: a visual transformer approach for compressed whole slide image classification

Segmentation-Less Extraction of Text and Non-Text Regions From JPEG 2000 Compressed Document Images Through Partial and Intelligent Decompression

JPEG 2000 is a popular image compression technique that uses Discrete Wavelet Transform (DWT) for compression and subsequently provides many rich features for efficient storage and decompression. Though compressed images are preferred for archival and communication purposes, their processing becomes difficult due to the overhead of decompression and re-compression operations which are needed as many times the data needs to operate. Therefore in this research paper, the novel idea of direct operation over the JPEG 2000 compressed documents is proposed for extracting text and non-text regions without using any segmentation algorithm. The technique avoids full decompression of the compressed document in contrast to the conventional methods, where they fully decompress and then process. Moreover, JPEG 2000 features are explored in this research work to partially and intelligently decompress only the selected regions of interest at different resolutions and bitdepths to accomplish segmentation-less extraction of text and non-text regions. Finally Maximally Stable Extremal Regions (MSER) algorithm is used to extract the layout of segmented text and non-text regions for further analysis. Experiments have been carried out on the standard PRImA Layout Analysis Dataset leading to promising results and saving computational resources.

Blind JPEG Compression Artifacts Removal by Integrating Channel Regulation With Exit Strategy

Compression artifacts removal methods based on convolutional neural networks have attracted great attention. However, most existing methods require a specific trained model for a specific compression quality factor (QF), which inevitably leads to resource-consuming. Unfortunately, the QF is unknown in most practical applications, so it is intractable to choose a suitable model. In this work, we experimentally analyze the relationship between compression index estimation and compression artifacts removal. Based on the connection between them, we couple compression index estimation with compression artifacts removal into a unified network. A network named CRESNet is proposed, working for a wide range of QFs by integrating channel regulation with an exit strategy. Specifically, CRESNet adopts a multi-stage progressive structure with an exit strategy embedded to automatically select the optimal exit stage according to the estimated compression index reflecting the difficulty of the input sample. Benefiting from the exit strategy, CRESNet removes artifacts from slightly compressed images through a simple process while doing an elaborate process for severely compressed images. Furthermore, a compression-information-guided channel regulation (CICR) mechanism is developed to adaptively regulate feature maps based on the estimated compression index. CRESNet achieves a more elegant trade-off between artifacts removal and detail preservation in a resource-efficient manner. Experiments demonstrate that CRESNet achieves state-of-the-art performance.

Compression of mri images with brain pathology based on Haaar wavelet

Currently wavelets are widely used in various fields related to the processing and analysis of signals and images. One application is the task of image compression. The advantage of compression using wavelet algorithms is that they work with the entire image and not with its individual blocks. At high compression ratios this avoids a block structure. This paper analyzes the effectiveness of the compression algorithm for medical MRI images with brain pathology which is based on the Haar wavelet transform. Implementation effective compression methods will allow storing a larger number of patient tomograms on a central server without increasing storage volumes. Experiments were performed and the dependences of indicators for assessing the quality of compressed MRI images on the compression ratio were constructed. The algorithm with zeroing wavelet coefficients by a threshold showed a better result compared to zeroing by levels based on assessing the quality of a compressed MRI image using a set of corresponding metrics.

Content-based image retrieval for industrial material images with deep learning and encoded physical properties

Abstract Industrial materials images are an important application domain for content-based image retrieval. Users need to quickly search databases for images that exhibit similar appearance, properties, and/or features to reduce analysis turnaround time and cost. The images in this study are 2D images of millimeter-scale rock samples acquired at micrometer resolution with light microscopy or extracted from 3D micro-CT scans. Labeled rock images are expensive and time-consuming to acquire and thus are typically only available in the tens of thousands. Training a high-capacity deep learning (DL) model from scratch is therefore not practicable due to data paucity. To overcome this “few-shot learning” challenge, we propose leveraging pretrained common DL models in conjunction with transfer learning. The “similarity” of industrial materials images is subjective and assessed by human experts based on both visual appearance and physical qualities. We have emulated this human-driven assessment process via a physics-informed neural network including metadata and physical measurements in the loss function. We present a novel DL architecture that combines Siamese neural networks with a loss function that integrates classification and regression terms. The networks are trained with both image and metadata similarity (classification), and with metadata prediction (regression). For efficient inference, we use a highly compressed image feature representation, computed offline once, to search the database for images similar to a query image. Numerical experiments demonstrate superior retrieval performance of our new architecture compared with other DL and custom-feature-based approaches.

An Algorithm to Reduce Compression Ratio in Multimedia Applications

In recent years, it has been evident that internet is the most effective means of transmitting information in the form of documents, photographs, or videos around the world. The purpose of an image compression method is to encode a picture with fewer bits while retaining the decompressed image’s visual quality. During transmission, this massive data necessitates a lot of channel space. In order to overcome this problem, an effective visual compression approach is required to resize this large amount of data. This work is based on lossy image compression and is offered for static color images. The quantization procedure determines the compressed data quality characteristics. The images are converted from RGB to International Commission on Illumination CIE La*b*; and YCbCr color spaces before being used. In the transform domain, the color planes are encoded using the proposed quantization matrix. To improve the efficiency and quality of the compressed image, the standard quantization matrix is updated with the respective image block. We used seven discrete orthogonal transforms, including five variations of the Complex Hadamard Transform, Discrete Fourier Transform and Discrete Cosine Transform, as well as thresholding, quantization, de-quantization and inverse discrete orthogonal transforms with CIE La*b*; and YCbCr to RGB conversion. Peak to signal noise ratio, signal to noise ratio, picture similarity index and compression ratio are all used to assess the quality of compressed images. With the relevant transforms, the image size and bits per pixel are also explored. Using the (n, n) block of transform, adaptive scanning is used to acquire the best feasible compression ratio. Because of these characteristics, multimedia systems and services have a wide range of possible applications.