High Compression Rate Research Articles

Deep image compression using scene text quality assessment

Image compression is a fundamental technology for Internet communication engineering. However, a high compression rate with general methods may degrade images, resulting in unreadable texts. In this paper, we propose an image compression method for maintaining text quality. We developed a scene text image quality assessment model to assess text quality in compressed images. The assessment model iteratively searches for the best-compressed image holding high-quality text. Objective and subjective results showed that the proposed method was superior to existing methods. Furthermore, the proposed assessment model outperformed other deep-learning regression models.

Privacy-preserving image compressed sensing by embedding a controllable noise-injected transformation for IoT devices

Recently, compressed sensing (CS) based cryptosystem has received extensive attention in information security field. However, this cryptosystem cannot resist known-plaintext attack (KPA) under the secret key multi-time-using (MTU) scenario because of its linear sampling process. To address this concern, a privacy-preserving image CS scheme is proposed, which embeds a controllable noise-injected transformation (CNT) into the linear sampling process of CS to resist KPA. First, a CNT operation is applied to pre-encrypt the image. Second, the pre-encrypted image is re-encrypted and compressed by using CS at the same time. Third, the final CS measurements are quantized into bits. Since the embedding of CNT operation destroys the linearity of CS, the proposed cryptosystem can resist the existing KPA method under the secret key MTU scenario. Lastly, an iterative total variation (TV) algorithm based on ADMM framework, called TV-ADMM, is proposed for image recovery. Simulation results demonstrate that the proposed cryptosystem significantly enhances the security of the CS-based cryptosystem with slightly sacrificing the compression performance in high compression rate cases.

Super-resolution network with dynamic cleanup and temporal–spatial attention for compressed videos

Video super-resolution methods focus on restoring high-resolution video frames from low-resolution videos with pre-defined degradations, and few consider compression. However, the videos on the Internet are compressed to reduce the massive size of video data. Thus, they also contain visual noises and artifacts due to the lossy compression. In this paper, we propose a video super-resolution model specific for compressed videos to suppress artifacts and restore high-resolution contents. We propose a two-stage super-resolution network for compressed videos that contains three new modules: cleanup and local alignment in the first stage, 3D-convolution temporal–spatial attention in the second stage. Specifically, the cleanup module is designed in stage-1 to suppress the artifacts and noises of low-quality inputs. The subsequent local alignment is designed to aggregate adjacent frames to maintain high-frequency details. The 3D-convolution attention is used in stage-2 to refine the weights of the feature maps. In addition, we propose the new CrfVideos dataset to facilitate fair comparisons, containing HEVC/H.265 compressed videos of different compression levels. Extensive experiments substantiate that our method outperforms state-of-the-art methods on the HEVC/H.265 compressed benchmark with medium to high compression rates by 0.3–0.7 dB in terms of PSNR and exceeds state-of-the-art methods on benchmark Vid4 by 0.2–0.8 dB. The code will be released at https://github.com/cvygkhv/decompression.

Discriminative analysis of wavelets for efficient medical image compression

Critical diagnostic information inferred using state of the artradiology techniques helps radiologists in determining the severity of diseases and hence suggest suitable treatment procedures. As a result, dealing with medical image compression necessitates a trade-off between good perceptual quality and high compression rate. The objective of this work is twofold, i) to investigate the effect of increasing the number of encoding loops on medical image compression parameters, and ii) to determine the most suitable wavelet for medical image compression. Haar, Daubechies, Biorthogonal Demeyer, Coifletand Symlet wavelets are used for comparison. Six different sets of medical images are used for testing and from the results obtained it is observed that increasing the number of encoding loops results in better compression parameters but increasing beyond 9 has no significant effect on compression parameters and thus the optimum choice for the number of encoding loops is 9. From the second analysis it is observed that changing the type of wavelets used has no significant effect on the compression parameters.

Effect of microstructure variation on corrosion properties of as-cast 0Cr23Ni13 stainless steel at high strain rate of hot compression

Effect of microstructure variation on corrosion properties of as-cast 0Cr23Ni13 stainless steel at high strain rate of hot compression

Remote sensing image compression with long-range convolution and improved non-local attention model

It is a challenge to achieve high compression rates for remote sensing images because they have rich information and complex backgrounds. Long-range context information can help the model to identify spatial redundant features. Therefore, we propose a long-range convolution compression network (LRCompNet) for remote sensing images. In order to capture long-range context information, we first propose a long-range convolution, and a light-weight compression model is designed. Additionally, an improved non-local attention model is proposed to reduce the computation complexity in order to accommodate remote sensing image compression. We also collect two remote sensing datasets (GoogleMap dataset and GF7 dataset) to test the proposed method and existing codecs, such as JPEG, JPEG2000 and learned compression models. We assess the overall performance of our method in terms of rate-distortion curves and execution time, respectively. Results on both datasets show that the proposed compression network achieves improved rate-distortion performance. Furthermore, the proposed method significantly reduces the time complexity when compared to other methods.

A Novel Implicit Neural Representation for Volume Data

The storage of medical images is one of the challenges in the medical imaging field. There are variable works that use implicit neural representation (INR) to compress volumetric medical images. However, there is room to improve the compression rate for volumetric medical images. Most of the INR techniques need a huge amount of GPU memory and a long training time for high-quality medical volume rendering. In this paper, we present a novel implicit neural representation to compress volume data using our proposed architecture, that is, the Lanczos downsampling scheme, SIREN deep network, and SRDenseNet high-resolution scheme. Our architecture can effectively reduce training time, and gain a high compression rate while retaining the final rendering quality. Moreover, it can save GPU memory in comparison with the existing works. The experiments show that the quality of reconstructed images and training speed using our architecture is higher than current works which use the SIREN only. Besides, the GPU memory cost is evidently decreased.

A Convolutional Self-Attention Network for CSI Reconstruction in MIMO System

A convolutional self-attention network-based channel state information reconstruction method is presented to address the issue of low reconstruction accuracy of channel state information in Multiple-Input Multiple-Output (MIMO) at a high compression rate. First, an encoder-decoder structure-based channel state information reconstruction model is built. The feature is extracted by the encoder’s convolutional network, and the information is compressed by adding an attention block. At the same time, the compressed information is nonuniform quantized to prevent the transmission process from using up too much bandwidth. A dequantization module and an attention block are added to the decoder to reduce the impact of noise on the matrix, converting the continuous value into a discrete value to increase reconstruction accuracy and using the long-time cosine annealing training approach. According to the simulation results, when compared to CsiNet, Lightweight CNN, CRNet, and CLNet, convergence speed is improved by 17.64%, indoor reconstruction precision is improved by an average of 37.4%, and outside reconstruction accuracy is improved by an average of 32.5% under all compressions.

DDQR (dynamic DNA QR coding): An efficient algorithm to represent DNA barcode sequences.

A DNA barcode is a short piece of standard DNA sequence used for species determination and discrimination. Representation of DNA barcodes is essential for DNA barcodes' applications in the transportation and recognition of biological materials. Previously, we have compared different strategies for representing the DNA barcodes. In the present study, we have developed a compression algorithm based on binary coding or Huffman coding scheme, followed by converting the binary digits into Base64 digits. The combination of this compression algorithm and the QR representation leads to the dynamic DNA QR coding algorithm (DDQR). We tested the DDQR algorithm on simulated data and real DNA barcode sequences from the commonly used plant and animal DNA barcode markers: rbcL, matK, trnH-psbA, ITS2, and COI. We compared the compression efficiency of DDQR and another state-of-the-art DNA compression algorithm GeCo3 for sequences with various base compositions and lengths. We found that DDQR had a higher compression rate than GeCo3 for DNA sequences shorter than 800 bp, which is the typical size range for DNA barcodes. We also upgraded a web server (http://www.1kmpg.cn/ddqr) that provides three functions: retrieval of DNA barcode sequences, encoding DNA barcode sequences to DDQR codes, and decoding DDQR codes to DNA barcode sequences. The DDQR algorithm and the webserver will be invaluable to applying DNA barcode technology in the food and traditional medicine industries.

Feature Map Compression for Video Coding for Machines Based on Receptive Block Based Principal Component Analysis

This paper presents a method to effectively compress the intermediate layer feature map of a convolutional neural network for the potential structures of Video Coding for Machines, which is an emerging technology for future machine consumption applications. Notably, most extant studies compress a single feature map and hence cannot entirely consider both global and local information within the feature map. This limits performance maintenance during machine consumption tasks that analyze objects with various sizes in images/videos. To address this problem, a multiscale feature map compression method is proposed that consists of two major processes: receptive block based principal component analysis (RPCA) and uniform integer quantization. The RPCA derives the complete basis kernels of a feature map by selecting a set of major basis kernels that can represent a sufficient percentage of global or local information according to the variable-size receptive blocks of each feature map. After transforming each feature map using the set of major basis kernels, a uniform integer quantizer converts the 32-bit floating-point values of the set of major basis kernels, corresponding RPCA coefficients, and a mean vector to five-bit integer representation values. Experiment results reveal that the proposed method reduces the amount of feature maps by 99.30% with a loss of 8.30% in the average precision ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AP</i> ) on the OpenImageV6 dataset and 0.77% in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AP_M</i> and 0.47% in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AP_L</i> on the MS COCO 2017 validation set while outperforming previous PCA-based feature map compression methods even at higher compression rates.

Some studies on banana and sisal fibers-based hybrid composites

In recent decades, the natural fiber-based composite has fascinated considerable importance as a potential structure material. Natural fibers' attractive features often help to build the modern world’s needs. Composites produced from natural fiber will be a very cost-effective material, especially for the construction industry. The present focus is on developing a polymer matrix composite (polyester resin) using Banana and Sisal fibers at various compositions (40:60, 50:50, 60:40) used as reinforcement. The compression molding machine is used for fabricates fiber-reinforced composite plates. Three types of compositions are taken, the first with both Banana and Sisal fibers in 50 % composition each. The second one with Banana fibers of 60 % and Sisal fiber of 40 % composition, respectively. The third one with Banana fiber of 40 % Sisal fiber of 60 % composition, respectively. The resin is taken in 40 %, and fibers are taken in 60 % for making the composites. The compression, impact, hardness, thermogravimetric analysis, and moisture absorption test were tested for fiber-reinforced composite plates, and the results were compared. From the results, the composite with 40 % Banana fiber and 60 % Sisal fiber showed high compression, impact, hardness, and heat flow rate values. Composite with 60 % Banana and 40 % Sisal fibers had more water absorption properties.

Compressing AIS Trajectory Data Based on the Multi-Objective Peak Douglas–Peucker Algorithm

The automatic identification system (AIS) provides a massive database for ocean science. The original AIS data are redundant. Direct use will cause a waste of data storage space and computation costs; hence, data compression must be performed. The Douglas–Peucker algorithm (DP) is an effective trajectory compression algorithm that can well preserve the spatial characteristics of a trajectory but has the following shortcomings: first, it has poor track recovery when compressing multi-turn routes; second, it does not consider the ship speed and heading; and third, it may have the wrong result of the compressed trajectory crossing the obstacle. To address these situations, this study proposes a multi-objective peak DP algorithm (MPDP) that adopts a peak sampling strategy, considers three optimization objectives (spatial characteristics, heading and speed) of trajectory and adds an obstacle detection mechanism to realize a compression algorithm more suitable for curved trajectories. The classical DP algorithm is compared with the MPDP algorithm by simulating trajectory and real trajectory experiments. The results show that the MPDP algorithm optimizes the length loss rate, simultaneous Euclidean distance, and average deviations of the speed and the heading while maintaining a high compression rate similar to that of the DP algorithm. Moreover, it can also successfully avoid obstacles. The optimization effect is most obvious for the multi-turn or hovering trajectory. The optimization rate of length loss, synchronous Euclidean distance, and average deviation of the heading can reach 40%.

Age-Optimal Hybrid Temporal-Spatial Generalized Deduplication and ARQ for Satellite-Integrated Internet of Things

In a typical Satellite-integrated Internet of Things (SIoT), the limited transmission rate of a sensor causes a stale in data freshness due to unavoidable time waiting for transmission. Moreover, due to the high bit error rate (BER) of the satellite-to-ground link, data freshness will be further exacerbated by frequent retransmissions. Generally, this issue is partially solved using a powerful compression scheme that can reduce the data volume. However, conventional compression schemes will necessitate a significant amount of time to accumulate constant data to a certain quantity, posing a difficult challenge. Therefore, this study proposes an age-optimal hybrid temporal-spatial generalized deduplication and automatic repeat request (HARQ-GD) protocol for the high-sampling data collection in SIoT, considering data compression, and transmission collaboratively. A novel Age of Information (AoI) metric is developed for timeliness evaluation over a two-hop end-to-end link of SIoT, which is optimized to design the proposed HARQ-GD protocol by considering the temporal and spatial correlations of sampled data with specific encoding/decoding algorithms and packet formats. The simulation results indicate that the proposed HARQ-GD protocol performs better performance than typical generalized deduplication (GD) and hybrid automatic repeat request with chase combing (HARQ-CC) schemes in reducing AoI, because of its fewer transmission times and higher compression rate.

Bilateral anisotropic Gabor wavelet transformation based deep stacked auto encoding for lossesless image compression

SummaryA highly challenging aspect of the data compression technique is maintaining the quality of data that reconstructs in high compression rates. To overcome these limitations, a bilateral anisotropic Gabor wavelet transformation with deep stacked auto encoding (BAGWT‐DSAE) technique based lossesless image compression is proposed in this article to save the storage space and processing time during transferring the images. The proposed method contains three main processes namely preprocessing, compression and decompression. Initially input aerial image and digital image are taken and these images are given bilateral filter based preprocessing for eliminates the different types of noises and also multiple artifacts. Then the preprocessed images are given to anisotropic Gabor wavelet transformation based deep stacked auto encoding to compress and decompress the wavelet transform's sensitive sub‐bands effectually. In DSAE, the decoder of the auto encoder achieves a better quality decompressed image. The proposed method is implemented in MATLAB simulations run in PC through Intel Core, 8 GB of RAM, 2.50 GHz CPU and Windows 8. Then, the simulation performance of proposed BAGWT‐DSAE‐LIC method provides 20.23%, 24.85%, and 38.56% low compression ratio and 26.48%, 21.23%, and 12.53% lower computational time, 4.56%, 7.68%, and 8.34% high space saving than the existing methods.

Evaluation of lossy compression algorithms using discrete cosine transform for sounding rocket vibration data

This work evaluates the performance of compression algorithms based on discrete cosine transform (DCT) when used to encode sounding rockets’ vibration signals. Different compression methods that use the three-step strategy (transform, quantization, and entropy encoder) are presented. The performances are evaluated using the relationship between the compression rate and distortion, the latter being measured using the peak signal-to-noise ratio (PSNR) and the difference observed in the power spectral density. The focus of the work is on vibration signals from rocket launches conducted by the Institute of Aeronautics and Space of the Brazilian Air Force. The obtained results present a great variation for the vibration data in the test set. Compressors operating with PSNR close to 50 dB can achieve very high compression rates (over 100) for low power signals. However, if the vibration signal strength increases significantly, the compression rate can be much lower. For the worst case in the test set (signal with the highest power), the work shows that the best proposed method needs a rate of 9.8 to achieve a PSNR of 48.2 dB. When compared to the performance of recently published DCT-based compression algorithms, the proposed technique shows significant improvements. Given a PSNR around 50 dB, for signal with moderate power, improvements above 100% are observed in compression rate.

High-quality restoration image encryption using DCT frequency-domain compression coding and chaos

With the arrival of the age of big data, the amount and types of data in the process of information transmission have increased significantly, and the full-disk encryption mode used by traditional encryption algorithms has certain limitations of the times. In order to further improve the bandwidth efficiency of digital images in the transmission process and the information effectiveness of digital image transmission, this paper proposes an algorithm of high-quality restoration image encryption using DCT frequency-domain compression coding and chaos. Firstly, the image hash value is used for the generation of an encryption key with plaintext correlation, then lightweight chaos is generated based on the key to obtain a pseudo-random sequence. Secondly, the image is partitioned into subblock, and converted from time domain into frequency domain by employing Discrete Cosine Transform (DCT) on each block, then perform quantization operation based on frequency domain information to obtain DCT coefficient matrix. Thirdly, the direct current (DC) coefficients and alternating current (AC) coefficients are extracted in the DCT coefficient matrix and compressed by different encoding methods to obtain two sets of bitstream containing DC coefficient and AC coefficient information. Fourthly, permute the DC coefficient bit stream by the chaotic sequence, and reconstruct it with the AC coefficient bit stream to obtain the frequency domain ciphertext image. Finally, the chaotic sequence is used to diffuse ciphertext, and the processed hash value is hidden in the ciphertext to obtain the final ciphertext. The theoretical and experimental analysis showed that the key length reaches 341 bits, and the PSNR value of the restored image is close to 60, all of which satisfy the theoretical value. Therefore, the algorithm has the characteristics of high compression rate, high-quality image restoration large key space, strong plaintext sensitivity, strong key sensitivity and so on. Our method proposed in this paper is expected to provide a new idea for confidential and secure communication in the age of big data.

Transformer-Based Data-Driven Video Coding Acceleration for Industrial Applications

With the exploding development of edge intelligence and smart industry, deep learning-based intelligent industrial solutions are promptly applied in the manufacturing process. Many intelligent industrial solutions such as automatic manufacturing inspection are computer vision based and require fast and efficient video encoding techniques so that video streams can be processed as quickly as possible either at the edge cluster or over the cloud. As one of the most popular video coding standards, the high efficiency video coding (HEVC) standard has been applied to various industrial scenes. However, HEVC brings not only a higher compression rate but also a significant increase in encoding complexity, which hinders its practical application in industrial scenarios. Fortunately, a large amount of video coding data makes it possible to accelerate the encoding process in the industry. To speed up the video coding process in some industrial scenes, this paper proposes a data-driven fast approach for coding tree unit (CTU) partitioning in HEVC intracoding. First, we propose a method to represent the partition result of a CTU as a column vector of length 21. Then, we employ lots of encoding data produced in normal industry scenes to train transformer models used to predict the partitioning vector of the CTU. Finally, the final partitioning structure of the CTU is generated from the partitioning vector after a postprocessing operation and used by an industrial encoder. Compared with the original HEVC encoder used by some industrial applications, experiment results show that our approach achieves 58.77% encoding time reduction with 3.9% bit rate loss, which indicates that our data-driven approach for video coding has great capacity working in industrial applications.

Individual Online Learning Behavior Analysis Based on Hadoop.

The online individual behavior analysis is an important means for mining user interests. The user retweeting behavior prediction is typical problem for online individual behavior analysis. In order to make online learning behavior prediction method more suitable for the application of large-scale datasets, the improved condensed K nearest neighbor (ICKNN) method is proposed in this paper. Inspired by the idea of compressing samples in the condensed nearest neighbor (CNN) algorithm, this proposed method has adopted the Hadoop platform to parallelize the traditional CNN algorithm. For the traditional CNN method, as the value of K increases, the compression ratio decreases and so as the efficiency. The proposed ICKNN method can parallelize the traditional CNN method under the Hadoop framework to enhance efficiency. The proposed ICKNN method in this paper is validated by actual Twitter retweeting dataset. It can be seen that the proposed method in this paper has a higher compression rate than the traditional CNN algorithm. In terms of accuracy, the classification accuracy of the proposed ICKNN method has decreased compared with the traditional KNN method. However, the time consumed by the ICKNN method has significantly reduced compared with the traditional KNN method and CNN method, which can greatly improve the efficiency.

Near Lossless Compression for 3D Radiological Images Using Optimal Multilinear Singular Value Decomposition (3D-VOI-OMLSVD).

Storage and transmission of high-compression 3D radiological images that create high-quality reconstruction upon decompression are critical necessities for effective and efficient teleradiology. To cater to this need, we propose a near lossless 3D image volume compression method based on optimal multilinear singular value decomposition called “3D-VOI-OMLSVD.” The proposed strategy first eliminates any blank 2D image slices from the 3D image volume and uses the selective bounding volume (SBV) to identify and extract the volume of Interest (VOI). Following this, the VOI is decomposed with an optimal multilinear singular value decomposition (OMLSVD) to obtain the corresponding core tensor, factor matrices, and singular values that are compressed with adaptive binary range coder (ABRC), integrated as an entropy encoder. The compressed file can be transferred or transmitted and then decompressed in order to reconstruct the original image. The resultant decompressed VOI is acquired by reversing the above process and then fusing it with the background, using the bound volume coordinates associated with the compressed 3D image. The proposed method performance was tested on a variety of 3D radiological images with different imaging modalities and dimensions using quantitative evaluation metrics such as the compression rate (CR), bit rate (BR), peak signal to noise ratio (PSNR), and structural similarity index (SSIM). Furthermore, we also investigate the impact of VOI extraction on the model performance, before comparing it with two popular compression methods, namely JPEG and JPEG2000. Our proposed method, 3D-VOI-OMLSVD, displayed a high CR value, with a maximum of 37.31, and a low BR, with the lowest reported to be 0.21. The SSIM score was consistently high, with an average performance of 0.9868, while using < 1 second for decoding the image. We observe that with VOI extraction, the compression rate increases manifold, and bit rate drops significantly, and thus reduces the encoding and decoding time to a great extent. Compared to JPEG and JPEG2000, our method consistently performs better in terms of higher CR and lower BR. The results indicate that the proposed compression methodology performs consistently to create high-quality image compressions, and overall gives a better outcome when compared against two state-of-the-art and widely used methods, JPEG and JPEG2000.

Research on Modeling Method of Massive Launch Vehicle Time Series Data

Massive time series data is produced with the newly proposed long-term test, with high data sampling frequency, usually 40Hz, and the sampling lasts for a long time, often more than one year. Therefore, it brings the storage problem of massive launch vehicle time series data. In view of the shortcomings that the traditional storage method based on files may be difficult to meet the storage requirements of high concurrent writing, high compression rate and high query speed, the data modeling method is studied in this paper. For storage method based on files, relational database storage and time series database, the data model is constructed, and the configuration parameters are optimized, and the optimal storage method is selected by the performance simulation carried out. The simulation results show that under the massive time series data scenario, the storage method based on time series database has twice the writing speed of the others; It has the highest storage compression rate, up to 80%, far exceeding the uncompressed storage method based on files and the relational database storage method with data expansion; It has the fastest time-related query speed, more than 100,000 records/s, 3 times that of relational database and 10 times that of files. Among them, the storage method based on time series database has the best performance, and meets the storage requirements of massive time series data in the future for launch vehicles.