Benchmark Image Research Articles

P‐248: Late‐News Poster: Image Upscaling Techniques for IT Products; Evaluation and Analysis

This paper introduces an upscaler technology which is proven to be effective in improving power reduction for IT products at the system level. Proposed upscaler algorithm utilizes Lanczos and bilinear interpolation both of which are widely used in currently existing upscaler designs on the industry, and carefully analyzes the image distortion caused by 2x scaling of the input image and manipulates the possible artifacts by considering the key performance criteria in the up‐scaling. Our experimental results show that image quality distortion due to the proposed scaling algorithm is significantly improved while the small details in the images are preserved at most thanks to the combination of “blended upscale” and “edge enhancement” sub‐functions in the proposed upscaling design. According to our subjective evaluation, we got the average score of 4.39 over 15 persons with 21 images from well‐known image benchmark suites.

PSDCLS: Parallel simultaneous diffusion–confusion image cryptosystem based on Latin square

Today, due to the unparalleled growth of multimedia data sharing, especially digital images, between users over insecure channels in real-time applications, cryptography algorithms have gained increasing attention for the secure and efficient transmission. In classical chaos-based image cryptosystems, the confusion and diffusion operations are often applied as two separate and independent phases, which threatens the cryptosystem security. To address these problems, in this paper, a fast image cryptosystem based on parallel simultaneous diffusion–confusion strategy has been proposed using Latin squares, called PSDCLS. It consists of three main steps. First, the initial parameters of the Hénon-Sine chaotic map are produced from SHA256 of both the plain image content and the user’s secret key. Second, a chaos-based random Latin square is constructed by employing the chaotic sequence produced through the Hénon-Sine chaotic map. Third, a parallel simultaneous diffusion–confusion scheme is proposed by using Latin square and vectorization technique to overcome the problems of computational complexity and high risk of separable and iterative confusion–diffusion operations in the classical chaos-based image cryptosystems. To analyze and evaluate the security and performance of PSDCLS cryptosystem, we conducted extensive simulations and experiments on various benchmark images. Experimental results and analyses show that PSDCLS achieves excellent scores for information entropy (>7.99), correlation coefficients close to 0, key space (2512), NPCR (>99.60%), UACI (>33.46%). The encryption time for test images of size 512 × 512 and 512×512×3 was around 0.026 and 0.081 s, respectively. Therefore, PSDCLS is highly robust against common cryptographic attacks and serves as a swift cryptosystem for real-time encryption applications. The source code of PSDCLS is accessible at: https://github.com/EbrahimZarei64/PSDCLS.

A Systematic Survey of Deep Learning-Based Single-Image Super-Resolution

Single-image super-resolution (SISR) is an important task in image processing, which aims to enhance the resolution of imaging systems. Recently, SISR has made a huge leap and has achieved promising results with the help of deep learning (DL). In this survey, we give an overview of DL-based SISR methods and group them according to their design targets. Specifically, we first introduce the problem definition, research background, and the significance of SISR. Secondly, we introduce some related works, including benchmark datasets, upsampling methods, optimization objectives, and image quality assessment methods. Thirdly, we provide a detailed investigation of SISR and give some domain-specific applications of it. Fourthly, we present the reconstruction results of some classic SISR methods to intuitively know their performance. Finally, we discuss some issues that still exist in SISR and summarize some new trends and future directions. This is an exhaustive survey of SISR, which can help researchers better understand SISR and inspire more exciting research in this field. An investigation project for SISR is provided at https://github.com/CV-JunchengLi/SISR-Survey.

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.

Scientific mapping and bibliometric analysis of research advancements in underwater image enhancement

Underwater Image Enhancement (UIE) addresses challenges in marine resource exploitation such as absorption, noise, and low contrast. This paper employs bibliometric methods and data from Web of Science to analyze UIE literature. The analysis reveals that research on UIE entered a rapid development stage starting from 2017. Three main areas of technical support for research: underwater image enhancement methods, deep learning-based methods, and underwater image restoration and depth estimation. Hotspots in research include enhancement, deep learning, restoration, feature extraction, and quality assessment. Drawing from the bibliometric analysis, this paper proposes a conceptual framework for UIE research and presents five research suggestions: enhancing method robustness and adaptability, improving real-time performance, integrating software and hardware, establishing underwater image benchmark datasets, and refining quality evaluation systems for underwater images. This study offers valuable references and guidance for the future exploration and development of the UIE field.

CGIHE-VDSR: Color global image histogram equalization with very deep super resolution networks for color image super resolution

Medical and satellite image analysis require incredibly high resolution. Super-resolution combines several low-resolution images of the same scene to generate a high-resolution image. The Super resolution employing deep learning techniques still has an illumination issue. This paper proposes a novel CGIHE-VDSR algorithm that integrates the Very Deep Super Resolution (VDSR) Network with Color Global Image Histogram Equalization (CGIHE) to improve image resolution. In the proposed method, the low-resolution image is first histogram equalized using the CGIHE algorithm. Then, the VDSR network is applied to the histogram equalized image for super-resolution. The comparison of real-time data with the benchmark images is done using the proposed algorithm in the MATLAB platform. The PSNR and SSIM metrics demonstrate that the super resolution image obtained using the proposed method is significantly better than the existing methods.

Chaotic opposition Golden Sinus Algorithm for global optimization problems

Optimization techniques are required to find the best solutions to challenging problems in many engineering disciplines. Metaheuristic algorithms that effectively increase search performance using various evolutionary strategies have become increasingly popular in recent years. The Golden Sinus Algorithm (GoldSa) is a population-based optimization algorithm that uses the sine function and the golden ratio. In this study, a chaotically enhanced opposition-based Golden Sinus Algorithm (Co-GoldSa) has been proposed to improve the efficiency of the exploitation and exploration ability of the GoldSa method. While designing this approach, it is first necessary to analyze the chaotic behavior of the GoldSa parameters. For this purpose, three chaotic GoldSa methods have been developed using eight chaotic maps to determine the effect of the chaotic maps on the parameters with different behaviors. Secondly, the opposition-based learning strategy is adjusted to the cGoldSa to enhance the searching ability. To investigate the proficiency of the proposed Co-GoldSa method, it has been examined with well-known and newly introduced metaheuristic approaches on benchmark functions and classical engineering design problems. Besides, an efficient framework of the multilevel thresholding image segmentation has been presented based on the Co-GoldSa method since the efficient processing of pathological images is quite important in medical diagnostics. The experimental outcomes reveal the superiority of the proposed method in solving global optimization problems, image segmentation, and engineering problems. Thus, the outcomes of the benchmark functions, image segmentation, and classical engineering problems support that the proposed Co-GoldSa approach can be considered a promising method for resolving challenging optimization problems.

An improved deep hashing model for image retrieval with binary code similarities

The exponential growth of data raises an unprecedented challenge in data analysis: how to retrieve interesting information from such large-scale data. Hash learning is a promising solution to address this challenge, because it may bring many potential advantages, such as extremely high efficiency and low storage cost, after projecting high-dimensional data to compact binary codes. However, traditional hash learning algorithms often suffer from the problem of semantic inconsistency, where images with similar semantic features may have different binary codes. In this paper, we propose a novel end-to-end deep hashing method based on the similarities of binary codes, dubbed CSDH (Code Similarity-based Deep Hashing), for image retrieval. Specifically, it extracts deep features from images to capture semantic information using a pre-trained deep convolutional neural network. Additionally, a hidden and fully connected layer is attached at the end of the deep network to derive hash bits by virtue of an activation function. To preserve the semantic consistency of images, a loss function has been introduced. It takes the label similarities, as well as the Hamming embedding distances, into consideration. By doing so, CSDH can learn more compact and powerful hash codes, which not only can preserve semantic similarity but also have small Hamming distances between similar images. To verify the effectiveness of CSDH, we evaluate CSDH on two public benchmark image collections, i.e., CIFAR-10 and NUS-WIDE, with five classic shallow hashing models and six popular deep hashing ones. The experimental results show that CSDH can achieve competitive performance to the popular deep hashing algorithms.

Object-Based Semi-Supervised Spatial Attention Residual UNet for Urban High-Resolution Remote Sensing Image Classification

Accurate urban land cover information is crucial for effective urban planning and management. While convolutional neural networks (CNNs) demonstrate superior feature learning and prediction capabilities using image-level annotations, the inherent mixed-category nature of input image patches leads to classification errors along object boundaries. Fully convolutional neural networks (FCNs) excel at pixel-wise fine segmentation, making them less susceptible to heterogeneous content, but they require fully annotated dense image patches, which may not be readily available in real-world scenarios. This paper proposes an object-based semi-supervised spatial attention residual UNet (OS-ARU) model. First, multiscale segmentation is performed to obtain segments from a remote sensing image, and segments containing sample points are assigned the categories of the corresponding points, which are used to train the model. Then, the trained model predicts class probabilities for all segments. Each unlabeled segment’s probability distribution is compared against those of labeled segments for similarity matching under a threshold constraint. Through label propagation, pseudo-labels are assigned to unlabeled segments exhibiting high similarity to labeled ones. Finally, the model is retrained using the augmented training set incorporating the pseudo-labeled segments. Comprehensive experiments on aerial image benchmarks for Vaihingen and Potsdam demonstrate that the proposed OS-ARU achieves higher classification accuracy than state-of-the-art models, including OCNN, 2OCNN, and standard OS-U, reaching an overall accuracy (OA) of 87.83% and 86.71%, respectively. The performance improvements over the baseline methods are statistically significant according to the Wilcoxon Signed-Rank Test. Despite using significantly fewer sparse annotations, this semi-supervised approach still achieves comparable accuracy to the same model under full supervision. The proposed method thus makes a step forward in substantially alleviating the heavy sampling burden of FCNs (densely sampled deep learning models) to effectively handle the complex issue of land cover information identification and classification.

Mixture correntropy-based robust distance metric learning for classification

Metric learning is a branch of machine learning that aims to learn from the given training data a valid distance metric, with which the similarity between samples can be more effectively evaluated for classification. Metric learning has attracted significant attention, and a large number of models have been proposed in the past few years. However, the traditional methods adopt hinge loss which easily leads to noise sensitivity and instability. In this paper, to improve the robustness performance, we develop a mixture correntropy criterion where two Laplacian kernel functions are combined as the kernel function and induce a more general nonconvex robust loss function by the mixture correntropy. The properties related to the loss function are analysed and presented. The induced loss amalgamates the superiors of the state-of-the-art robust loss functions and is more effective. With this induced loss, we establish a robust metric learning model (called MCML) and design an effective iterative algorithm to optimize the nonconvex challenging problem. The computational complexity and convergence of algorithm are discussed in theory. Furthermore, a boosting version of MCML (BMCML) is derived, where the low-rank basis learning is jointly optimized with the metric to better uncover the data structure. Finally, extensive experiments are conducted on artificial datasets, UCI benchmark datasets and image datasets. The experimental results verify the robustness and effectiveness of the proposed methods.

An efficient approximate multiplier: Design, error analysis and application

Approximate circuits are extensively considered in error-resilient applications to reduce the design complexity. A multiplier is known as a key arithmetic unit of computational block, and thus improving the performance of the multiplier is significantly important to achieve an effective processor. In this paper, we develop two new inaccurate multipliers using approximate 4:2 compressor. Applying error correction block in the structure of these 8-bit multipliers remarkably increases the accuracy of design. The design performance and error metrics of the multipliers are analyzed. Furthermore, as an image processing application, we consider several benchmark images, and compare the quality metrics of image multiplication of our proposed multipliers to those obtained from different under-test multipliers of the previous studies. The design of multipliers is performed using HSPICE with 14 nm FinFET technology. The results demonstrate that the proposed multipliers provide suitable efficiency in the error analysis when compared to the exact multiplier in image processing application.

HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrieval

Existing unsupervised deep product quantization methods primarily aim for the increased similarity between different views of the identical image, whereas the delicate multi-level semantic similarities preserved between images are overlooked. Moreover, these methods predominantly focus on the Euclidean space for computational convenience, compromising their ability to map the multi-level semantic relationships between images effectively. To mitigate these shortcomings, we propose a novel unsupervised product quantization method dubbed Hierarchical Hyperbolic Product Quantization (HiHPQ), which learns quantized representations by incorporating hierarchical semantic similarity within hyperbolic geometry. Specifically, we propose a hyperbolic product quantizer, where the hyperbolic codebook attention mechanism and the quantized contrastive learning on the hyperbolic product manifold are introduced to expedite quantization. Furthermore, we propose a hierarchical semantics learning module, designed to enhance the distinction between similar and non-matching images for a query by utilizing the extracted hierarchical semantics as an additional training supervision. Experiments on benchmark image datasets show that our proposed method outperforms state-of-the-art baselines.

RPSC: Robust Pseudo-Labeling for Semantic Clustering

Clustering methods achieve performance improvement by jointly learning representation and cluster assignment. However, they do not consider the confidence of pseudo-labels which are not optimal as supervised information, resulting into error accumulation. To address this issue, we propose a Robust Pseudo-labeling for Semantic Clustering (RPSC) approach, which includes two stages. In the first stage (RPSC-Self), we design a semantic pseudo-labeling scheme by using the consistency of samples, i.e., samples with same semantics should be close to each other in the embedding space. To exploit robust semantic pseudo-labels for self-supervised learning, we propose a soft contrastive loss (SCL) which encourage the model to believe high-confidence sematic pseudo-labels and be less driven by low-confidence pseudo-labels. In the second stage (RPSC-Semi), we first determine the semantic pseudo-label of a sample based on the distance between itself and cluster centers, followed by screening out reliable semantic pseudo-label by exploiting the consistency. These reliable pseudo-labels are used as supervised information in the pseudo-semi-supervised learning algorithm to further improve the performance. Experimental results show that RPSC outperforms 18 competitive clustering algorithms significantly on six challenging image benchmarks. In particular, RPSC achieves an accuracy of 0.688 on ImageNet-Dogs, which is an up to 24% improvement, compared with the second-best method. Meanwhile, we conduct ablation studies to investigate effects of different augmented strategies on RPSC as well as contributions of terms in SCL to clustering performance. Besides, experimental results indicate that SCL can be easily integrated into existing clustering methods and bring performance improvement.

ROI extraction in corona virus (COVID 19) CT images using intuitionistic fuzzy edge detection

Edge detection is a vital aspect of medical image processing, playing a key role in delineating borders and contours within images. This capability is instrumental for various applications, including segmentation, feature extraction, and diagnostic procedures in the realm of medical imaging. COVID-19 is a deadly disease affecting people in most of countries in the world. COVID-19 is due to the coronavirus which belongs to the family of RNA viruses and causes various symptoms such as pneumonia, fever, breathing difficulty, and lung infection. ROI extraction plays a vital role in disease diagnosis and therapeutic treatment. CT scans can help detect abnormalities in the lungs that are characteristic of COVID-19, such as ground-glass opacities and consolidation. This research work proposes an Intuitionistic fuzzy (IF) edge detector for the segmentation of COVID-19 CT images. Intuitionistic fuzzy sets go beyond conventional fuzzy sets by incorporating an additional parameter, referred to as the hesitation degree or non-membership degree. This extra parameter enhances the ability to represent uncertainty more intricately in expressing the degree to which an element may or may not belong to a set. The IF edge detector generates proficient results, when compared with the traditional edge detection algorithms and is validated in terms of performance metrics for benchmark images. Intuitionistic fuzzy edge detection has been shown to be effective in handling uncertainty and imprecision in edge detection.

Organ-Agnostic Whole Slide Image Analysis using Self-Supervised Transfer Learning

Traditional methods for pathology image analysis are well-known for their time-consuming and labor-intensive nature, often relying on the expertise of pathologists. In recent years, numerous research studies have been proposed to develop automated systems using machine learning approaches to address these challenges. While these systems have demonstrated promising performance, they often exhibit bias towards specific organs, cells, or tasks, limiting their ability to provide generalized solutions for pathology image analysis. To address this issue, I propose an organ-agnostic pathology image analysis system that leverages a self-supervised transfer learning approach. The proposed system comprises two stages: self-supervised representation learning and transfer learning. In the self-supervised representation learning phase, a machine learning model is trained to consistently extract essential features encapsulating the characteristics of diverse pathological images such as visual patterns of tumors. Subsequently, in the transfer learning phase, these well-pretrained models are utilized to train downstream tasks, such as tumor type classification or cancer area segmentation. The proposed approach outperforms all existing state-of-the-art supervised methods in multiple public pathology image benchmarks.

Feature Extraction and Classification of Gray-Scale Images of Brain Tumor using Deep Learning

Deep Learning using CNN plays a paramount role for the classification methods applied on medical image data. With a crucial role in accurate diagnosis, treatment planning and patient management for medical and healthcare systems, CNNs won accolades in the Deep Learning research. As simple the learning model so precise are the results for decision making. The proposed Sequential model of CNN is built with Parametric ReLU with the values aligned to geometric mean, attains a specific goal of tumor classification. The additional support of ground-truth aid in deciding the shape and severity of tumor in the Grayscale MRI of brain tumor. The simple Sequential model, although a minimal version has proved achieved significant classification goals using the GMP-ReLU. Comparative results with variants of ReLU have been charted in this article standing with the proof of consistent classification model with parametric-ReLU. The proposed design is conducted on images from Kaggle and a model is trained (classifier is built), which can be considered as ideal filter for all the benchmark images. The accuracy of proposed design is considerably improved compared to normal ReLU up to 89.214%.

Semi-supervised medical image classification via distance correlation minimization and graph attention regularization

We propose a novel semi-supervised learning method to leverage unlabeled data alongside minimal annotated data and improve medical imaging classification performance in realistic scenarios with limited labeling budgets to afford data annotations. Our method introduces distance correlation to minimize correlations between feature representations from different views of the same image encoded with non-coupled deep neural networks architectures. In addition, it incorporates a data-driven graph-attention based regularization strategy to model affinities among images within the unlabeled data by exploiting their inherent relational information in the feature space. We conduct extensive experiments on four medical imaging benchmark data sets involving X-ray, dermoscopic, magnetic resonance, and computer tomography imaging on single and multi-label medical imaging classification scenarios. Our experiments demonstrate the effectiveness of our method in achieving very competitive performance and outperforming several state-of-the-art semi-supervised learning methods. Furthermore, they confirm the suitability of distance correlation as a versatile dependence measure and the benefits of the proposed graph-attention based regularization for semi-supervised learning in medical imaging analysis.

Data augmentation for deep visual recognition using superpixel based pairwise image fusion

Data augmentation is an important paradigm for boosting the generalization capability of deep learning in image classification tasks. Image augmentation using cut-and-paste strategies has shown very good performance improvement for deep learning. However, these existing methods often overlook the image’s discriminative local context and rely on ad hoc regions consisting of square or rectangular local regions, leading to the loss of complete semantic object parts. In this work, we attempt to overcome these limitations and propose a superpixel-wise local-context-aware efficient image fusion approach for data augmentation. Our approach requires only one forward propagation using a superpixel attention-based label fusion with less computational complexity. The model is trained using a combination of a global classification of the fused (augmented) image loss, a superpixel-wise weighted local classification loss, and a superpixel-based weighted contrastive learning loss. The last two losses are based on the superpixel-aware attentive embeddings. Thus, the resulting deep encoder can learn both local and global features of the images while capturing object-part local context and information. Experiments on diverse benchmark image datasets indicate that the proposed method out-performs many region-based augmentation methods for visual recognition. We have demonstrated its effectiveness not only on CNN models but also on transformer models. The codes are accessible at https://github.com/DanielaPlusPlus/SAFuse.

EAO: Enhanced aquila optimizer for solving optimization problem

The Aquila optimization (AO) algorithm has the drawbacks of local optimization and poor optimization accuracy when confronted with complex optimization problems. To remedy these drawbacks, this paper proposes an Enhanced aquila optimization (EAO) algorithm. To avoid elite individual from entering the local optima, the elite opposition-based learning strategy is added. To enhance the ability of balancing global exploration and local exploitation, a dynamic boundary strategy is introduced. To elevate the algorithm’s convergence rapidity and precision, an elite retention mechanism is introduced. The effectiveness of EAO is evaluated using CEC2005 benchmark functions and four benchmark images. The experimental results confirm EAO’s viability and efficacy. The statistical results of Freidman test and the Wilcoxon rank sum test are confirmed EAO’s robustness. The proposed EAO algorithm outperforms previous algorithms and can useful for threshold optimization and pressure vessel design.

Removing Coding and Inter Pixel Redundancy in Image Compression

The digital image plays an important role in today’s digital world. Storing and transmitting digital images efficiently is a challenging job. There are lots of techniques for reducing the size of digital pictures. This paper adapts the following method. The digital technique is separated into high and low resolutions. The low intensity and high intensity pixels single-handedly is dense and decompressed using three diverse algorithms to hit upon out the occurrence of low down intensity pixels in the picture. Totally six algorithms are experienced by means of benchmark images and the most excellent scheme is selected for concluding compression. A Comparison is made between the results obtained using these techniques and those obtained using JPEG 2000.