JPEG Image Compression Research Articles

Robust data hiding method based on frequency coefficient variance in repetitive compression

Sharing accurate and lossless images with higher quality through digital mediums is challenging, particularly, images shared on social media platforms can serve as good carriers for sending hidden data. However, social media platforms apply severe compression when transferring images end-to-end to serve efficient network transporting bandwidth and provide enough storage space to the users. Within the scope of this research, the proposed method introduces a novel approach by combining cryptographic and steganographic techniques, providing a robust solution to protect hidden data even when subjected to repeatedly compression. The method first encrypts the secret data to be hidden using the Advanced Encryption Standard Cipher Block Chaining (AES-CBC) technique. Then, data hiding is performed on the coefficients obtained by applying Discrete Cosine Transform (DCT) to repeatedly compressed JPEG images, coefficients that are minimally affected by compression or remain unaffected are specifically selected for data hiding. Therefore, secret data is extracted with high accuracy. Experimental results show that the proposed method outperforms the state-of-the-art in achieving robust and effective data hiding techniques based on bit error rate.

Metaheuristic-based energy-aware image compression for mobile app development

AbstractThe widely applied JPEG standard has undergone recent efforts using population-based metaheuristic (PBMH) algorithms to optimise quantisation tables (QTs) for specific images. However, user preferences, like an Android developer’s preference for small-size images, are often overlooked, leading to high-quality images with large file sizes. Another limitation is the lack of comprehensive coverage in current QTs, failing to accommodate all possible combinations of file size and quality. Therefore, this paper aims to propose three distinct contributions. First, to include the user’s opinion in the compression process, the file size of the output image can be controlled by a user in advance. To this end, we propose a novel objective function for population-based JPEG image compression. Second, we suggest a novel representation to tackle the lack of comprehensive coverage. Our proposed representation can not only provide more comprehensive coverage but also find the proper value for the quality factor for a specific image without any background knowledge. Both representation and objective function changes are independent of the search strategies and can be used with any population-based metaheuristic (PBMH) algorithm. Therefore, as the third contribution, we also provide a comprehensive benchmark on 22 state-of-the-art and recently-introduced PBMH algorithms on our new formulation of JPEG image compression. Our extensive experiments on different benchmark images and in terms of different criteria show that our novel formulation for JPEG image compression can work effectively.

Efficient image restoration with style-guided context cluster and interaction

Recently, convolutional neural networks (CNNs) and vision transformers (ViTs) have emerged as powerful tools for image restoration (IR). Nonetheless, they encountered some limitations due to their characteristics, such as CNNs sacrificing global reception and ViTs requiring large memory and graphics resources. To address these limitations and explore an alternative approach for improved IR performance, we propose two clustering-based frameworks for general IR tasks, which are style-guided context cluster U-Net (SCoC-UNet) and style-guided clustered point interaction U-Net (SCPI-UNet). The SCoC-UNet adopts a U-shaped architecture, comprising position embedding, Encoder, Decoder, and reconstruction block. Specifically, the input low-quality image is viewed as a set of unorganized points, each of which is first given location information by the continuous relative position embedding method. These points are then fed into a symmetric Encoder and Decoder which utilize style-guided context cluster (SCoC) blocks to extract potential context features and high-frequency information. Although SCoC-UNet has obtained decent performance for image restoration, its SCoC block can only capture connectivity at points within the same cluster, which may ignore long-range dependencies in different clusters. To address this issue, we further propose a SCPI-UNet based on SCoC-UNet, which leverages a style-guided clustered point interaction (SCPI) block in place of the SCoC block. The SCPI block utilizes a cross-attention mechanism to establish the connections of feature points between different clusters. Extensive experimental results demonstrate that the proposed SCoC-UNet and SCPI-UNet can handle several typical IR tasks (i.e., JPEG compression artifact reduction, image denoising, and super-resolution) and achieve superior quantitative and qualitative performance over some state-of-the-art methods.

FBSE-Based JPEG Image Compression

FBSE-Based JPEG Image Compression

CNN based image resizing forensics for double compressed JPEG images

This paper investigates a novel CNN-based architecture for image resizing forensics in the presence of Double-JPEG compression. Two sub-problems are addressed as part of this paper: first, the detection of resizing in DJPEG images, and second, determining the factor used to resize the image before the second JPEG compression. The image resizing technique used in this paper is image scaling. The proposed network is based on utilizing specially chosen high pass filters that constitute the pre-processing layer, followed by four convolutional layers, two fully connected layers, and a final softmax layer. The high-pass filters preserve the resizing clues in the form of residuals applied at the pre-processing layer, followed by utilizing the residuals as inputs to a CNN to detect the presence of resizing and also for estimating the resizing factor. The proposed network is fully end-to-end and does not rely on any hand-crafting. Experimental validation is carried out utilizing images from the RAISE dataset. Comparative analysis with four state-of-the-art methods demonstrates the proposed CNN-based architecture’s superiority for resizing detection and resize factor determination sub-problems.

Kompresija JPEG i BPG bez gubitka vizuelnih informacija na primeru baze KonJND-1k

Introduction/purpose: This paper presents the results of the research on visually lossless image compression which is of particular interest because it achieves a high degree of compression, while the visual quality of the image is not impaired, i.e., end users are very satisfied with the image quality. The analysis was carried out using the publicly available large-scale picture-wise KonJND-1k database which contains the results of subjective tests on JPEG and BPG compressed images. Methods: Thanks to the availability of images from the KonJND-1k database, the dependence of objective assessments of image quality on parameters that control the degree of compression of source signals (quality factor for JPEG and quantization parameter for BPG) is analyzed. The results of the visually lossless subjective tests are used for a deep analysis of the boundary and typical values of the parameters that control these two types of compression, as well as for the analysis of the corresponding values of the objective quality scores. Furthermore, reliable features for predicting the boundary between visually lossless and visually lossy compression have been identified. For that purpose, the degree of agreement between the predictions and the ground truth values of the peak signal-to-noise ratio (PSNR) and image representation in bits per pixel (bpp) is used. The visually lossless compression ratio is used to compare JPEG and BPG techniques. Results: It is shown that the boundary between visually lossless and visually lossy image compression is found in a wide range of PSNR values (about 20 dB for JPEG and 15 dB for BPG). The corresponding JPEG image compression quality factor values at this threshold also range widely from 31 to 79, with concentration between 40 and 45. For the BPG encoder, the values of the quantization parameter are grouped around 30, and the boundary values are 25 and 34. Furthermore, it is shown that this boundary can be reliably determined based on simple features derived from the original uncompressed image. Gradient-based features known as spatial frequency and spatial information proved to be the best predictors. The degree of agreement between the predictions obtained from these features with the ground truth values of PSNR and bpp in both types of compression is greater than 85%. A comparative analysis has showed that, using BPG compression, it is possible, on the average, to achieve a twice larger compression ratio of visually lossless compression than for JPEG (80 versus 40). Conclusion: Although a high degree of agreement is achieved between the predictions and the ground truth values of PSNR and bpp of the boundary between visually lossless and visually lossy compression, there is a need for the development of new prediction approaches, especially with the BPG technique, which through the compression ratio proved to be superior to the JPEG technique. The existing databases used for the analysis of visually lossless compression contain color images from the visible part of the electromagnetic spectrum. Considering the increasing use of images from the infrared part of the spectrum, there is a need to conduct similar tests in this spectral range.

JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer.

JPEG compression adopts the quantization of Discrete Cosine Transform (DCT) coefficients for effective bit-rate reduction, whilst the quantization could lead to a significant loss of important image details. Recovering compressed JPEG images in the frequency domain has recently garnered increasing interest, complementing the multitude of restoration techniques established in the pixel domain. However, existing DCT domain methods typically suffer from limited effectiveness in handling a wide range of compression quality factors or fall short in recovering sparse quantized coefficients and the components across different colorspaces. To address these challenges, we propose a DCT domain spatial-frequential Transformer, namely DCTransformer, for JPEG quantized coefficient recovery. Specifically, a dual-branch architecture is designed to capture both spatial and frequential correlations within the collocated DCT coefficients. Moreover, we incorporate the operation of quantization matrix embedding, which effectively allows our single model to handle a wide range of quality factors, and a luminance-chrominance alignment head that produces a unified feature map to align different-sized luminance and chrominance components. Our proposed DCTransformer outperforms the current state-of-the-art JPEG artifact removal techniques, as demonstrated by our extensive experiments.

Target acquisition performance in the presence of JPEG image compression

This paper presents an investigation on the effect of JPEG compression on the similarity between the target image and the background, where the similarity is further used to determine the degree of clutter in the image. Four new clutter metrics based on image quality assessment are introduced, among which the Haar wavelet-based perceptual similarity index, known as HaarPSI, provides the best target acquisition prediction results. It is shown that the similarity between the target and the background at the boundary between visually lossless and visually lossy compression does not change significantly compared to the case when an uncompressed image is used. In future work, through subjective tests, it is necessary to check whether this presence of compression at the threshold of just noticeable differences will affect the human target acquisition performance. Similarity values are compared with the results of subjective tests of the well-known target Search_2 database, where the degree of agreement between objective and subjective scores, measured through linear correlation, reached a value of 90%.

Exploring Symmetry in Digital Image Forensics Using a Lightweight Deep-Learning Hybrid Model for Multiple Smoothing Operators

Digital images are widely used for informal information sharing, but the rise of fake photos spreading misinformation has raised concerns. To address this challenge, image forensics is employed to verify the authenticity and trustworthiness of these images. In this paper, an efficient scheme for detecting commonly used image smoothing operators is presented while maintaining symmetry. A new lightweight deep-learning network is proposed, which is trained with three different optimizers to avoid downsizing to retain critical information. Features are extracted from the activation function of the global average pooling layer in three trained deep networks. These extracted features are then used to train a classification model with an SVM classifier, resulting in significant performance improvements. The proposed scheme is applied to identify averaging, Gaussian, and median filtering with various kernel sizes in small-size images. Experimental analysis is conducted on both uncompressed and JPEG-compressed images, showing superior performance compared to existing methods. Notably, there are substantial improvements in detection accuracy, particularly by 6.50% and 8.20% for 32 × 32 and 64 × 64 images when subjected to JPEG compression at a quality factor of 70.

A novel method for resampling detection in highly compressed JPEG images through BAR using a deep learning technique

As JPEG has become a prevalent compression standard, identifying manipulations in JPEG images has become increasingly necessary. However, many of the inspected images are highly compressed, making it challenging for forensics tools and methodologies to detect clues of resampling. To overcome this issue, a new method has been proposed that uses a deep convolutional neural network (CNN) to detect image resampling by removing blocking artifacts (BAR) from recompressed images without altering resampling clues. The proposed framework has three stages: noise residual extraction, feature extraction, and classification. Initially, the image content and BAR are suppressed, and noise residuals from recompressed images are extracted using ten convolutional layers without pooling layers. The feature extraction phase then learns resampling features from the noise residuals in an adaptive manner. Deep resampling characteristics are processed through the fully connected layer to identify whether the input image is double compressed and resized (DCR) or double compressed and unresized (DCUR). The proposed deep CNN has been tested on heterogeneous datasets such as RAISE and DRESDEN, identifying resampling with a mean accuracy of 91.85% and 90.21% in cross-dataset settings. In addition, detecting downscaling with more than an accuracy of 87.98% in highly recompressed images indicates that it outperforms state-of-the-art approaches. Furthermore, the proposed method yields notable results in estimating the resampling factor in recompressed images.

Compression and reconstruction of flotation foam images based on generative adversarial networks

The froth flotation is a beneficiation method that utilizes the differences in the physical and chemical properties of the surface of mineral particles to achieve the effective separation of different minerals. Recently, with the development of image processing and computer technology, machine vision has been widely used in mineral froth flotation. However, due to the high pixels of the flotation froth image and the limited storage space of the industrial computer, it is difficult to save a large amount of image data at the industrial site. To this end, a flotation foam image compression and reconstruction method is presented in this work. First, a lossless froth image is collected from the flotation cell in a gold hydrometallurgical plant. Then, the JPEG image compression algorithm compresses the original images to one in dozens. Under this situation, low-quality and small-volume images can be stored in an industrial computer easily. To reconstruct the compressed image, the generative adversarial networks (GAN) is used in this work, and RRDB and VGG19 are employed as the generative and discriminative models of the network, respectively. The loss function of the model is the sum of three losses, which are L1 loss, perceptual loss, and adversarial loss. Three methods for testing the texture features of the froth image are selected to verify the efficiency of the proposed method. The results show that the reconstructed image can effectively restore the details of the bubbles, reflect the image features, and has less noise and high visual similarity with the original image. The reconstructed images generated by low-resolution images with different compression qualities mostly maintain a restoration degree of more than 90% compared with the original images in three texture features.

Deep steerable pyramid wavelet network for unified JPEG compression artifact reduction

Although numerous methods have been proposed to remove blocking artifacts in JPEG-compressed images, one important issue not well addressed so far is the construction of a unified model that requires no prior knowledge of the JPEG encoding parameters to operate effectively on different compression-level images (grayscale/color) while occupying relatively small storage space to save and run. To address this issue, in this paper, we present a unified JPEG compression artifact reduction model called DSPW-Net, which employs (1) the deep steerable pyramid wavelet transform network for Y-channel restoration, and (2) the classic U-Net architecture for CbCr-channel restoration. To enable our model to work effectively on images with a wide range of compression levels, the quality factor (QF) related features extracted by the convolutional layers in the QF-estimation network are incorporated in the two restoration branches. Meanwhile, recursive blocks with shared parameters are utilized to drastically reduce model parameters and shared-source residual learning is employed to avoid the gradient vanishing/explosion problem in training. Extensive quantitative and qualitative results tested on various benchmark datasets demonstrate the effectiveness of our model as compared with other state-of-the-art deblocking methods.

Energy-aware JPEG image compression: A multi-objective approach

Customer satisfaction is crucially affected by energy consumption in mobile devices. One of the most energy-consuming parts of an application is images. This paper, first, investigates that there is a correlation between energy consumption and image quality as well as image file size. Therefore, these two can be considered as a proxy for energy consumption. In the next step, we focused on proposing a multi-objective strategy to enhance image quality and reduce image file size based on the quantisation table (QT) in JPEG image compression. To this end, we have used two general multi-objective approaches: scalarisation and Pareto-based. In this paper, we embed our strategy into five scalarisation algorithms, including energy-aware multi-objective genetic algorithm (EnMOGA), energy-aware multi-objective particle swarm optimisation (EnMOPSO), energy-aware multi-objective differential evolution (EnMODE), energy-aware multi-objective evolutionary strategy (EnMOES), and energy-aware multi-objective pattern search (EnMOPS). Also, two Pareto-based methods, including a non-dominated sorting genetic algorithm (NSGA-II) and a reference-point-based NSGA-II (NSGA-III) are used for the embedding scheme, and two Pareto-based algorithms, EnNSGAII and EnNSGAIII, are presented. With our proposed scalarisation method, user’s preferences can be set before starting the optimisation process and the algorithm generates only one solution based on the preference, while our Pareto-based approaches generate a set of solutions so that a user can select one of the preferred solutions after the optimisation process.Experimental studies show that the performance of the baseline algorithm is improved by embedding the proposed strategy into metaheuristic algorithms. In particular, EnMOGA, EnMOPS, and EnNSGA-II can perform competitively, among others. From the results, the baseline algorithm in all cases and in comparison to all algorithms yields the worst results. Among the scalarisation methods, EnMOGA and EnMOPS can achieve the first rank in 6 and 7 out of 13 cases and the second rank in 7 and 5 cases in terms of objective function. Also, EnMOES achieved the fifth or worst rank among the scalarisation algorithms. Regarding the Pareto-based algorithms, the table shows that EnNSGAII outperforms EnNSGAIII in 10 out of 13 cases in terms of hyper-volume measure, while it fails in 3 cases. Furthermore, we statistically verify the proposed algorithm’s effectiveness based on the Wilcoxon-signed rank test. Finally, a sensitivity analysis of the parameters is provided. The source code for reproducing the results is available in: https://github.com/SeyedJalaleddinMousavirad/MultiobjectiveJPEGImageCompression.

Feature enhancement and supervised contrastive learning for image splicing forgery detection

Image forgery detection remains a challenging task due to the variation in the scale of the tampered areas and the forensic clues that are obscured by various post-processing operations. Most existing deep learning methods rely only on single-scale high-level features and ignore the correlations of the pixels in intra-image and inter-image. Due to this limitation, previous methods are considered unsuitable for multi-scale splicing forgery detection. To fill this gap, we propose a novel model for improving multi-scale splicing forged regions localization by utilizing multi-level multi-scale feature enhancement and pixel-level supervised contrastive learning. First, we introduce a multi-level multi-scale feature enhancement module (MFEM) to integrate the multi-level information and capture the multi-scale global contextual representation by embedding an improved atrous spatial pyramid pooling (ASPP) mechanism into the non-local module. It strengthens the capability of the model to sense multi-scale tampered regions. Second, the pixel-level supervised contrastive learning mechanism is designed to separately cluster the pixel representations of tampered and real regions within and across images. It improves intra-class compactness and inter-class separability of the pixel embedding space significantly and enhances feature expression capabilities. Third, we design a multi-loss progressive learning (MPL) strategy to integrate the complementary advantages of multi-loss functions to optimize the scale and position parameters of the tampered regions during the training process. Extensive experiments have shown that the proposed model outperforms state-of-the-art methods. It can effectively detect and segment multi-scale tampered regions, even for noisy and JPEG-compressed images.

Three States QRLE (Quantized Run Length Encoding) Based JPEG Image Compression Method

Three States QRLE (Quantized Run Length Encoding) Based JPEG Image Compression Method

Super-resolving compressed images via parallel and series integration of artefacts removal and resolution enhancement

In real-world applications, such as sharing photos on social media platforms, images are always not only sub-sampled but also heavily compressed thus often containing various artefacts. Simple methods for enhancing the resolution of such images will exacerbate the artefacts, rendering them visually objectionable. In spite of its high practical values, super-resolving compressed images is not well studied in the literature. In this paper, we propose a novel compressed image super resolution (CISR) framework based on parallel and series integration of artefacts removal and resolution enhancement. Based on a mathematical inference model for estimating a clean low-resolution (LR) image and a clean high-resolution (HR) image from a down-sampled and compressed observation, we have designed a CISR architecture consisting of two deep neural network modules: the artefacts removal module (ARM) and the resolution enhancement module (REM). The ARM and the REM work in parallel with both taking the compressed LR image as their inputs, at the same time they also work in series with the REM taking the output of the ARM as one of its inputs and the ARM taking the output of the REM as its other input. A technique called unfolding is introduced to recursively suppress the compression artefacts and restore the image resolution. A unique feature of our CISR system is that it exploits the parallel and series connections between the ARM and the REM, and recursive optimization to reduce the model’s dependency on specific types of degradation thus making it possible to train a single model to super-resolve images compressed by different methods to different qualities. Experiments are conducted on a mixture of JPEG and WebP compressed images without assuming apriori compression type and compression quality factor. To demonstrate our technique’s real-world application value, we have also applied the trained models directly to restore social media images which have undergone scaling and compression by unknown algorithms. Visual and quantitative comparisons demonstrate the superiority of our method over state-of-the-art super resolution methods, especially for heavily compressed images.

CNN-based first quantization estimation of double compressed JPEG images

Multiple JPEG compressions leave artifacts in digital images: residual traces that could be exploited in forensics investigations to recover information about the device employed for acquisition or image editing software. In this paper, a novel First Quantization Estimation (FQE) algorithm based on convolutional neural networks (CNNs) is proposed. In particular, a solution based on an ensemble of CNNs was developed in conjunction with specific regularization strategies exploiting assumptions about neighboring element values of the quantization matrix to be inferred. Mostly designed to work in the aligned case, the solution was tested in challenging scenarios involving different input patch sizes, quantization matrices (both standard and custom) and datasets (i.e., RAISE and UCID collections). Comparisons with state-of-the-art solutions confirmed the effectiveness of the presented solution demonstrating for the first time to cover the widest combinations of parameters of double JPEG compressions.

Securing LSB embedding against structural steganalysis

This work explores the extent to which LSB embedding can be made secure against structural steganalysis through a modification of cover image statistics prior to message embedding. LSB embedding disturbs the statistics of consecutive k-tuples of pixels, and a kth-order structural attack detects hidden messages with lengths in proportion to the size of the imbalance amongst sets of k-tuples. To protect against kth-order structural attacks, cover modifications involve the redistribution of k-tuples among the different sets so that symmetries of the cover image are broken, then repaired through the act of LSB embedding so that the stego image bears the statistics of the original cover. We find this is only feasible for securing against up to 3rd-order attacks since higher-order protections result in virtually zero embedding capacities. To protect against 3rd-order attacks, we perform a redistribution of triplets that also preserves the statistics of pairs. This is done by embedding into only certain pixels of each sextuplet, constraining the maximum embedding rate to be ⩽ 2 / 3 bits per channel. Testing on a variety of image formats, we report best performance for JPEG-compressed images with a mean maximum embedding rate undetectable by 2nd- and 3rd-order attacks of 0.21 bpc.

Low dynamic range discrete cosine transform (LDR-DCT) for high-performance JPEG image compression

Low dynamic range discrete cosine transform (LDR-DCT) for high-performance JPEG image compression

Paper] Restoration of JPEG Compressed Image with Narrow Quantization Constraint Set without Parameter Optimization

Paper] Restoration of JPEG Compressed Image with Narrow Quantization Constraint Set without Parameter Optimization