Image Compression Research Articles

Using Compressed JPEG and JPEG2000 Medical Images in Deep Learning: A Review

Machine Learning (ML), particularly Deep Learning (DL), has become increasingly integral to medical imaging, significantly enhancing diagnostic processes and treatment planning. By leveraging extensive datasets and advanced algorithms, ML models can analyze medical images with exceptional precision. However, their effectiveness depends on large datasets, which require extended training times for accurate predictions. With the rapid increase in data volume due to advancements in medical imaging technology, managing the data has become increasingly challenging. Consequently, irreversible compression of medical images has become essential for efficiently handling the substantial volume of data. Extensive research has established recommended compression ratios tailored to specific anatomies and imaging modalities, and these guidelines have been widely endorsed by government bodies and professional organizations globally. This work investigates the effects of irreversible compression on DL models by reviewing the relevant literature. It is crucial to understand how DL models respond to image compression degradations, particularly those introduced by JPEG and JPEG2000—both of which are the only permissible irreversible compression techniques in the most commonly used medical image format—the Digital Imaging and Communications in Medicine (DICOM) standard. This study provides insights into how DL models react to such degradations, focusing on the loss of high-frequency content and its implications for diagnostic interpretation. The findings suggest that while existing studies offer valuable insights, future research should systematically explore varying compression levels based on modality and anatomy, and consider developing strategies for integrating compressed images into DL model training for medical image analysis.

Scalable and Resolution Data Analysis of Image and Video Compression using DL-CNNS Neural Network

Scalable and Resolution Data Analysis of Image and Video Compression using DL-CNNS Neural Network

Elliptic Quaternion Matrices: A MATLAB Toolbox and Applications for Image Processing

In this study, we developed a MATLAB 2024a toolbox that performs advanced algebraic calculations in the algebra of elliptic numbers and elliptic quaternions. Additionally, we introduce color image processing methods, such as principal component analysis, image compression, image restoration, and watermarking, based on singular-value decomposition theory for elliptic quaternion matrices; we added these to the newly developed toolbox. The experimental results demonstrate that elliptic quaternionic methods yield better image analysis and processing performance compared to other hypercomplex number-based methods.

Steganographic Metadata Embedding to Trace the Footprint of WhatsApp Images

This research paper proposes a method to trace the footprint of senders while forwading of images on WhatsApp by embedding metadata (such as mobile numbers) using Least Significant Bit (LSB) steganography. The technique ensures that the hidden information is imperceptible to users and remains intact even after WhatsApp’s image compression. The method allows for tracking the digital footprint of images, providing traceability to combat misinformation, piracy, and privacy concerns. The system is robust, enabling metadata recovery after multiple shares, with applications in digital forensics, media integrity, and monitoring the spread of viral content

Selective Medical Image Encryption and Compression Based on DCT, 3D_Att_ResU-Net and 4D Hyperchaotic Map Schemes

Selective Medical Image Encryption and Compression Based on DCT, 3D_Att_ResU-Net and 4D Hyperchaotic Map Schemes

Coefficient-Shuffled Variable Block Compressed Sensing for Medical Image Compression in Telemedicine Systems

Medical professionals primarily utilize medical images to detect anomalies within the interior structures and essential organs concealed by the skeletal and dermal layers. The primary purpose of medical imaging is to extract image features for the diagnosis of medical conditions. The processing of these images is indispensable for evaluating a patient’s health. However, when monitoring patients over extended periods using specific medical imaging technologies, a substantial volume of data accumulates daily. Consequently, there arises a necessity to compress these data in order to remove duplicates and speed up the process of acquiring data, making it appropriate for effective analysis and transmission. Compressed Sensing (CS) has recently gained widespread acceptance for rapidly compressing images with a reduced number of samples. Ensuring high-quality image reconstruction using conventional CS and block-based CS (BCS) poses a significant challenge since they rely on randomly selected samples. This challenge can be surmounted by adopting a variable BCS approach that selectively samples from diverse regions within an image. In this context, this paper introduces a novel CS method that uses an energy matrix, namely coefficient shuffling variable BCS (CSEM-VBCS), tailored for compressing a variety of medical images with balanced sparsity, thereby achieving a substantial compression ratio and good reconstruction quality. The results of experimental evaluations underscore a remarkable enhancement in the performance metrics of the proposed method when compared to contemporary state-of-the-art techniques. Unlike other approaches, CSEM-VBCS uses coefficient shuffling to prioritize regions of interest, allowing for more effective compression without compromising image quality. This strategy is especially useful in telemedicine, where bandwidth constraints often limit the transmission of high-resolution medical images. By ensuring faster data acquisition and reduced redundancy, CSEM-VBCS significantly enhances the efficiency of remote patient monitoring and diagnosis.

Comparison of deep learning-based models for detection of diseased trees using an image compression algorithm

The object of the research is the application of deep learning algorithms using an improved mathematical lossless image compression method for recognizing and identifying dead trees in aerospace images. The main problem that has been solved is the archiving of images due to their large volume on disk and the possibility of their further processing by deep learning methods such as convolutional and capsule neural networks, which have shown high efficiency and accuracy in image recognition and classification tasks using the proposed new image compression method. The article presents a comparative analysis of the performance of three YOLO (You Only Look Once) models with different types of architectures, such as YOLOv5, YOLOv7 and YOLOv8, to assess the effectiveness of their work for the task of recognizing aerospace tree images obtained from satellites, drones, and aircrafts. Comprehensive analysis of YOLO models presents that model YOLO v8 turned out to be most effective with a positive accuracy of 88.2 %, a recall of 77.4 %, and a mAP50 score of 87.2 %. Moreover, the average detection time was only 0.052 seconds for each image, even though the model size remains very small – 21.5 MB. These results suggest a much better usage of time and precise identification of dead trees, and classified targets with high efficiency. From the research, there is significant prospects of global forest management especially on forest reduction and protection of ecosystems through accurate assessment on the health of forestry. The proposed approach is universal and can be used in real life conditions, providing a good compromise of the speed, accuracy and resources required for forest monitoring and management

A Gray Scale Image Compression Using Hierarchical DWT Decomposition and Mixing Quantization Techniques

This paper describes a hybrid grayscale compression system based on the discrete wavelet transform (DWT) and a polynomial coding technique for mixing quantization schemes to increase the compression ratio while maintaining quality. The proposed compression system consists of three main steps: first, decomposing an image using a three-level DWT; second, applying the 2-D linear polynomial coding technique to the approximation sub-band; and third, dividing the detailed sub-bands of each level into the Most Significant Value (MSV) and Least Significant Value (LSV), where the former is compressed using iterative scalar uniform quantization and the latter by soft quantization thresholding. For testing the performance of the suggested compression system, five standard images of size 256×256 pixels were adopted. The suggested technique showed superior performance in terms of reconstructed (decoded) image quality and compression ratio (gain), where the compression ratio is between 21–27 with a PSNR value between 36–38 dB and the compression ratio of JPEG is between 7–20 with a PSNR value between 33–37 dB.

A Knowledge Base Driven Task-Oriented Image Semantic Communication Scheme

With the development of artificial intelligence and computer hardware, semantic communication has been attracting great interest. As an emerging communication paradigm, semantic communication can reduce the requirement for channel bandwidth by extracting semantic information. This is an effective method that can be applied to image acquisition of unmanned aerial vehicles, which can transmit high-data-volume images within the constraints of limited available bandwidth. However, the existing semantic communication schemes fail to adequately incorporate the guidance of task requirements into the semantic communication process and are difficult to adapt to the dynamic changes of tasks. A task-oriented image semantic communication scheme driven by knowledge base is proposed, aiming at achieving high compression ratio and high quality image reconstruction, and effectively solving the bandwidth limitation. This scheme segments the input image into several semantic information unit under the guidance of task requirements by Yolo-World and Segment Anything Model. The assigned bandwidth for each unit is according to the task relevance scores, which enables high-quality transmission of task-related information with lower communication overheads. An improved metric weighted learned perceptual image patch similarity (LPIPS) is proposed to evaluate the transmission accuracy of the novel scheme. Experimental results show that our scheme achieves a notable performance improvement on weighted LPIPS while the same compression ratio compared with traditional image compression schemes. Our scheme has a higher target capture ratio than traditional image compression schemes under the task of target detection.

Security of Magnetic Resonance Medical Images using Region-based Lossless Image Compression in Healthcare Information Systems

Purpose The purpose of region-based medical image compression is to optimize the compression process by focusing on specific regions of interest within medical images. Unlike traditional compression methods that treat the entire image uniformly, region-based compression techniques identify and prioritize certain areas or regions within the image that are deemed more diagnostically significant or relevant. By allocating more resources to compressing these critical regions while reducing compression in less important areas, region-based compression methods aim to achieve higher compression efficiency while preserving diagnostic quality. This approach is particularly valuable in medical imaging, where accurate representation of anatomical structures or pathological findings is paramount for clinical diagnosis and decision-making. Region-based compression can help reduce storage requirements, transmission bandwidth, and processing time without compromising the diagnostic integrity of medical images, thereby facilitating more efficient healthcare delivery and telemedicine applications. Methods In this study, we utilized distortion-limiting compression techniques to optimize the compression process for specific regions within medical images. We employed lossless scalable RBC (Region-Based Compression) using Discrete Wavelet Transform (DWT) for Digital Imaging and Communication in Medicine (DICOM) images. The initial step involved medical image pre-processing, followed by segmentation to separate the image into regions of interest (ROI) and non-ROI. Compression techniques were then applied to reduce network bandwidth and storage requirements. Fractal lossy compression was employed for the non-ROI portion, while context-tree weighting lossless compression was proposed for the ROI portion, effectively compressing the image while rejecting noisy background elements. During decompression, the original medical image can be reconstructed using the reverse process. This approach optimizes storage and transmission efficiency while preserving diagnostic integrity in medical imaging applications. Results The experiment involved testing various medical images, and the proposed method outperformed previous techniques in terms of results. According to the findings, the improvement in Peak Signal-to-Noise Ratio (PSNR) over current techniques reached up to 24.23 dB compared to the Joint Photographic Experts Group (JPEG). Additionally, it achieved up to 12.22 dB improvement compared to other transform approaches. These significant enhancements prompted the development of a web and mobile platform for compressing and sending medical images, particularly microscopic ones, in real time. Conclusion This research focuses on employing wavelet transform techniques to compress the Region of Interest (ROI) within medical images. This ROI-based compression approach is particularly valuable as it retains essential diagnostic information while reducing the overall file size. Such a technique holds significant promise for telemedicine systems, especially in rural regions where network resources may be limited or constrained. By selectively compressing the most diagnostically relevant areas of medical images, this approach ensures that critical information is preserved while optimizing data transmission and storage efficiency. This can ultimately enhance access to medical imaging services and facilitate remote diagnosis and treatment in underserved areas with limited network infrastructure.

Classifying histopathological growth patterns for resected colorectal liver metastasis with a deep learning analysis.

Histopathological growth patterns are one of the strongest prognostic factors in patients with resected colorectal liver metastases. Development of an efficient, objective and ideally automated histopathological growth pattern scoring method can substantially help the implementation of histopathological growth pattern assessment in daily practice and research. This study aimed to develop and validate a deep-learning algorithm, namely neural image compression, to distinguish desmoplastic from non-desmoplastic histopathological growth patterns of colorectal liver metastases based on digital haematoxylin and eosin-stained slides. The algorithm was developed using digitalized whole-slide images obtained in a single-centre (Erasmus MC Cancer Institute, the Netherlands) cohort of patients who underwent first curative intent resection for colorectal liver metastases between January 2000 and February 2019. External validation was performed on whole-slide images of patients resected between October 2004 and December 2017 in another institution (Radboud University Medical Center, the Netherlands). The outcomes of interest were the automated classification of dichotomous hepatic growth patterns, distinguishing between desmoplastic hepatic growth pattern and non-desmoplatic growth pattern by a deep-learning model; secondary outcome was the correlation of these classifications with overall survival in the histopathology manual-assessed histopathological growth pattern and those assessed using neural image compression. Nine hundred and thirty-two patients, corresponding to 3.641 whole-slide images, were reviewed to develop the algorithm and 870 whole-slide images were used for external validation. Median follow-up for the development and the validation cohorts was 43 and 29 months respectively. The neural image compression approach achieved significant discriminatory power to classify 100% desmoplastic histopathological growth pattern with an area under the curve of 0.93 in the development cohort and 0.95 upon external validation. Both the histopathology manual-scored histopathological growth pattern and neural image compression-classified histopathological growth pattern achieved a similar multivariable hazard ratio for desmoplastic versus non-desmoplastic growth pattern in the development cohort (histopathology manual score: 0.63 versus neural image compression: 0.64) and in the validation cohort (histopathology manual score: 0.40 versus neural image compression: 0.48). The neural image compression approach is suitable for pathology-based classification tasks of colorectal liver metastases.

Balancing the encoder and decoder complexity in image compression for classification

This paper presents a study on the computational complexity of coding for machines, with a focus on image coding for classification. We first conduct a comprehensive set of experiments to analyze the size of the encoder (which encodes images to bitstreams), the size of the decoder (which decodes bitstreams and predicts class labels), and their impact on the rate–accuracy trade-off in compression for classification. Through empirical investigation, we demonstrate a complementary relationship between the encoder size and the decoder size, i.e., it is better to employ a large encoder with a small decoder and vice versa. Motivated by this relationship, we introduce a feature compression-based method for efficient image compression for classification. By compressing features at various layers of a neural network-based image classification model, our method achieves adjustable rate, accuracy, and encoder (or decoder) size using a single model. Experimental results on ImageNet classification show that our method achieves competitive results with existing methods while being much more flexible. The code will be made publicly available.

Laser Scan Compression for Rail Inspection

The automation of rail track inspection addresses key issues in railway transportation, notably reducing maintenance costs and improving safety. However, it presents numerous technical challenges, including sensor selection, calibration, data acquisition, defect detection, and storage. This paper introduces a compression method tailored for laser triangulation scanners, which are crucial for scanning the entire rail track, including the rails, rail fasteners, sleepers, and ballast, and capturing rail profiles for geometry measurement. The compression technique capitalizes on the regularity of rail track data and the sensors’ limited measurement range and resolution. By transforming scans, they can be stored using widely available image compression formats, such as PNG. This method achieved a compression ratio of 7.5 for rail scans used in the rail geometry computation and maintained rail gauge reproducibility. For the scans employed in defect detection, a compression ratio of 5.6 was attained without visibly compromising the scan quality. Lossless compression resulted in compression ratios of 5.1 for the rail geometry computation scans and 3.8 for the rail track inspection scans.

Correction to: A remote sensing image encryption and compression scheme using novel hyperchaotic system and plaintext related random S-box

Correction to: A remote sensing image encryption and compression scheme using novel hyperchaotic system and plaintext related random S-box

Stable successive Neural Image Compression via coherent demodulation-based transformation

Neural Image Compression (NIC) has made significant strides in recent years. However, the existing NIC methods demonstrate instability issues during iterative re-compression cycles, which can degrade image quality with each cycle. This paper introduces a novel framework aimed at enhancing the stability of NIC methods. We first conducted a theoretical analysis and identified that the instability in current NIC methods stems from a lack of idempotency in transformations. Drawing from the domain of signal processing, we then examined the principles of idempotency in coherent demodulation techniques. This examination led to the identification of three foundational principles that inform the design of stable transformations: the cosine function, parameter sharing, and low-pass filtering. Leveraging these insights, we propose the innovative Coherent Demodulation-based Transformation (CDT), which is designed to address the stability challenges in NIC by incorporating these principles into its architecture. The experimental results suggest that CDT not only significantly improve the re-compression stability but also preserves the codec’s rate–distortion performance. Furthermore, it can be broadly applied in current NIC structures. The effectiveness of the module endorses the viability of designing transformation networks based on Coherent Demodulation principles, playing a crucial role in enhancing stability of NIC. The code will be available at https://github.com/baoyu2020/Stable_SuccessiveNIC.

Parallel Lossless Compression of Raw Bayer Images on FPGA-Based High-Speed Camera

Digital image compression is applied to reduce camera bandwidth and storage requirements, but real-time lossless compression on a high-speed high-resolution camera is a challenging task. The article presents hardware implementation of a Bayer colour filter array lossless image compression algorithm on an FPGA-based camera. The compression algorithm reduces colour and spatial redundancy and employs Golomb–Rice entropy coding. A rule limiting the maximum code length is introduced for the edge cases. The proposed algorithm is based on integer operators for efficient hardware implementation. The algorithm is first verified as a C++ model and later implemented on AMD-Xilinx Zynq UltraScale+ device using VHDL. An effective tree-like pipeline structure is proposed to concatenate codes of compressed pixel data to generate a bitstream representing data of 16 parallel pixels. The proposed parallel compression achieves up to 56% reduction in image size for high-resolution images. Pipelined implementation without any state machine ensures operating frequencies up to 320 MHz. Parallelised operation on 16 pixels effectively increases data throughput to 40 Gbit/s while keeping the total memory requirements low due to real-time processing.

Recovering MRI magnetic field strength properties using machine learning based on image compression quality scores

AbstractOver the years, significant hardware advancements have led to higher magnetic field MRI (Magnetic Resonance Imaging) acquisitions, providing improved diagnostic image quality at a higher cost. While higher image quality is desired, the investment required for high-field MRI imaging systems remains a significant consideration. Furthermore, historical patient records may still contain low-field magnetic strength MRI data. In this work, we present how image compression quality scores of MRI images could be used to recover their magnetic field strength properties. This work presents an interesting inverse problem scenario where output properties are used to recover an input property of an image. We implemented supervised machine learning models that utilize compressed image quality scores - based on Mean Squared Error (MSE), Structural Similarity Index (SSIM), Visual Information Fidelity (VIF), and Earth Movers Distance (EM) metrics - as inputs. These models classify images into specific classes of magnetic field strength at which they were acquired (Low, Medium, and High) based solely on the quality scores of their compressed copies. The trained machine learning models (Support Vector Machine (SVM), Logistic Regression, K-nearest Neighbours (KNN), Decision Tree and Random Forest) achieved nearly 100% performance efficiency based on accuracy and F-1 score for all considered quality measures. This comprehensive evaluation offers insights into how compression techniques and quality factors impact image fidelity across various MRI magnetic field strengths. The findings of this study may prove valuable in recovering missing meta-tag information in historical image DICOM records and Context-Based Retrieval Systems (CBRS). The approach of using quality scores as features in training machine learning models, as demonstrated in this work, can be extended to other image groups where input parameters create statistically significant distinctions or are challenging to extract from images.

High-Quality Image Compression Algorithm Design Based on Unsupervised Learning.

Increasingly massive image data is restricted by conditions such as information transmission and reconstruction, and it is increasingly difficult to meet the requirements of speed and integrity in the information age. To solve the urgent problems faced by massive image data in information transmission, this paper proposes a high-quality image compression algorithm based on unsupervised learning. Among them, a content-weighted autoencoder network is proposed to achieve image compression coding on the basis of a smaller bit rate to solve the entropy rate optimization problem. Binary quantizers are used for coding quantization, and importance maps are used to achieve better bit allocation. The compression rate is further controlled and optimized. A multi-scale discriminator suitable for the generative adversarial network image compression framework is designed to solve the problem that the generated compressed image is prone to blurring and distortion. Finally, through training with different weights, the distortion of each scale is minimized, so that the image compression can achieve a higher quality compression and reconstruction effect. The experimental results show that the algorithm model can save the details of the image and greatly compress the memory of the image. Its advantage is that it can expand and compress a large number of images quickly and efficiently and realize the efficient processing of image compression.

MRACNN: Multi-Path Residual Asymmetric Convolution and Enhanced Local Attention Mechanism for Industrial Image Compression

MRACNN: Multi-Path Residual Asymmetric Convolution and Enhanced Local Attention Mechanism for Industrial Image Compression

Adjoint method in PDE-based image compression

We consider a shape optimization based method for finding the best interpolation data in the compression of images with noise. The aim is to reconstruct missing regions by means of minimizing a data fitting term in an L p -norm, for 1 ⩽ p < + ∞, between original images and their reconstructed counterparts using linear diffusion PDE-based inpainting. Reformulating the problem as a constrained optimization over sets (shapes), we derive the topological asymptotic expansion of the considered shape functionals with respect to the insertion of small ball (a single pixel) using the adjoint method. Based on the achieved distributed topological shape derivatives, we propose a numerical approach to determine the optimal set and present numerical experiments showing the efficiency of our method. Numerical computations are presented that confirm the usefulness of our theoretical findings for PDE-based image compression.