Area Of Image Processing Research Articles

Editorial for Vol.32, No.2

The June 2024 (Vol. 32, No. 2) issue of CIT. Journal of Computing and Information Technology brings four papers from the areas of natural language processing, image processing, network security, and biomedical image classification.

RAN: Infrared and Visible Image Fusion Network Based on Residual Attention Decomposition

Infrared image and visible image fusion (IVIF) is a research direction that is currently attracting much attention in the field of image processing. The main goal is to obtain a fused image by reasonably fusing infrared images and visible images, while retaining the advantageous features of each source image. The research in this field aims to improve image quality, enhance target recognition ability, and broaden the application areas of image processing. To advance research in this area, we propose a breakthrough image fusion method based on the Residual Attention Network (RAN). By applying this innovative network to the task of image fusion, the mechanism of the residual attention network can better capture critical background and detail information in the images, significantly improving the quality and effectiveness of image fusion. Experimental results on public domain datasets show that our method performs excellently on multiple key metrics. For example, compared to existing methods, our method improves the standard deviation (SD) by 35.26%, spatial frequency (SF) by 109.85%, average gradient (AG) by 96.93%, and structural similarity (SSIM) by 23.47%. These significant improvements validate the superiority of our proposed residual attention network in the task of image fusion and open up new possibilities for enhancing the performance and adaptability of fusion networks.

Review on graph theory-based image segmentation with its methods

In areas of digital image processing and computer vision, image segmentation is defined as a crucial process that divides an image into many segments for more straightforward and accurate object analysis. Making use of graph-based techniques as an effective tool for segmenting images has drawn more consideration recently. Since graph-based techniques are attractive and increasingly prevalent and can designate image properties, in this article, some of the primary graph-based techniques have been presented. This scheme utilizes graph theory to create a graph depiction of an image in which each pixel is represented as a node and the edges show the degree of similarity between two pixels. When items are represented by vertices and an edge connects them, a graph may be used to depict the relationship between them. To divide a graph into sub-graphs that reflect significant items of interest, this study explores some graph theoretical approaches for image segmentation, including minimum spanning tree, pyramid-based, graph cut-based, and interactive image segmentation and their employing in significant image processing fields such as medical image analysis for infection diagnosis, and remote sensing.

ConvNextUNet: A small-region attentioned model for cardiac MRI segmentation

Cardiac MRI segmentation is a significant research area in medical image processing, holding immense clinical and scientific importance in assisting the diagnosis and treatment of heart diseases. Currently, existing cardiac MRI segmentation algorithms are often constrained by specific datasets and conditions, leading to a notable decrease in segmentation performance when applied to diverse datasets. These limitations affect the algorithm’s overall performance and generalization capabilities. Inspired by ConvNext, we introduce a two-dimensional cardiac MRI segmentation U-shaped network called ConvNextUNet. It is the first application of a combination of ConvNext and the U-shaped architecture in the field of cardiac MRI segmentation. Firstly, we incorporate up-sampling modules into the original ConvNext architecture and combine it with the U-shaped framework to achieve accurate reconstruction. Secondly, we integrate Input Stem into ConvNext, and introduce attention mechanisms along the bridging path. By merging features extracted from both the encoder and decoder, a probability distribution is obtained through linear and nonlinear transformations, serving as attention weights, thereby enhancing the signal of the same region of interest. The resulting attention weights are applied to the decoder features, highlighting the region of interest. This allows the model to simultaneously consider local context and global details during the learning phase, fully leveraging the advantages of both global and local perception for a more comprehensive understanding of cardiac anatomical structures. Consequently, the model demonstrates a clear advantage and robust generalization capability, especially in small-region segmentation. Experimental results on the ACDC, LVQuan19, and RVSC datasets confirm that the ConvNextUNet model outperforms the current state-of-the-art models, particularly in small-region segmentation tasks. Furthermore, we conducted cross-dataset training and testing experiments, which revealed that the pre-trained model can accurately segment diverse cardiac datasets, showcasing its powerful generalization capabilities. The source code of this project is available at https://github.com/Zemin-Cai/ConvNextUNet.

Research on the rapid 3D measurement of satellite antenna reflectors using stereo tracking technique

Measurement and analysis of surface accuracy are crucial steps in the manufacturing process of satellite antenna reflectors. The conventional close-range photogrammetry requires attaching target points on the surface, which is time-consuming and may damage the surface quality. To overcome these drawbacks, a rapid measurement technique of non-contact three-dimensional (3D) shapes is proposed, which is based on the integration of a stereo tracking method and a structured light measurement method. This paper focuses on addressing the issue of obtaining pose transformation matrices for measurement devices in motion within this method. Initially, a plane tracking scheme and tracking plate pattern is designed. Furthermore, the feature points of the tracking plate are extracted from the target area of image processing. Moreover, the pose transformation matrix of the tracking plate relative to the fixed world coordinate system at different positions is obtained using the triangulation method. Finally, a measurement experiment is conducted, resulting in a stereo tracking scheme error within 0.5%.

Self-supervised pre-training for joint optic disc and cup segmentation via attention-aware network

Image segmentation is a fundamental task in deep learning, which is able to analyse the essence of the images for further development. However, for the supervised learning segmentation method, collecting pixel-level labels is very time-consuming and labour-intensive. In the medical image processing area for optic disc and cup segmentation, we consider there are two challenging problems that remain unsolved. One is how to design an efficient network to capture the global field of the medical image and execute fast in real applications. The other is how to train the deep segmentation network using a few training data due to some medical privacy issues. In this paper, to conquer such issues, we first design a novel attention-aware segmentation model equipped with the multi-scale attention module in the pyramid structure-like encoder-decoder network, which can efficiently learn the global semantics and the long-range dependencies of the input images. Furthermore, we also inject the prior knowledge that the optic cup lies inside the optic disc by a novel loss function. Then, we propose a self-supervised contrastive learning method for optic disc and cup segmentation. The unsupervised feature representation is learned by matching an encoded query to a dictionary of encoded keys using a contrastive technique. Finetuning the pre-trained model using the proposed loss function can help achieve good performance for the task. To validate the effectiveness of the proposed method, extensive systemic evaluations on different public challenging optic disc and cup benchmarks, including DRISHTI-GS and REFUGE datasets demonstrate the superiority of the proposed method, which can achieve new state-of-the-art performance approaching 0.9801 and 0.9087 F1 score respectively while gaining 0.9657 DCdisc\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$DC_{disc}$$\\end{document} and 0.8976 DCcup\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$DC_{cup}$$\\end{document}. The code will be made publicly available.

Design and Analysis of a New Fault-Tolerant QCA-based Nano-Scale Circuit for Morphological Operations in Image Processing

Quantum-dot cellular automata (QCA) is based on traditional cellular automata models in which each cell has one of the finite distinct states at any given time. Cellular automata refer to the use of Coulombic contact rather than wires to connect cells. The discrete character of cellular automata and quantum mechanics have been exploited to develop nano-scale devices that can conduct computations with high switching frequency and low power dissipation. QCA has been utilized in many categories for fault-tolerant and reversible logic computing. On the other hand, the morphology algorithm is an area of image processing that provides a unified methodology and strong tools for image/video processing applications. This work proposes a unique fault-tolerant approach based on QCA to execute the morphological operations in image processing. Two fault-tolerant 5-input majority gates are employed in the implemented QCA architecture, and a control line is used to accomplish dilation and erosion. To assess the capabilities of the proposed fault-tolerant circuit for morphological procedures, its performance is analyzed and confirmed. The proposed design is compared to earlier results, which significantly improve fault-tolerant ability.

Tchebichef Transform Domain-Based Deep Learning Architecture for Image Super-Resolution.

Recent advances in the area of artificial intelligence and deep learning have motivated researchers to apply this knowledge to solve multipurpose applications in the area of computer vision and image processing. Super-resolution (SR), in the past few years, has produced remarkable results using deep learning methods. The ability of deep learning methods to learn the nonlinear mapping from low-resolution (LR) images to their corresponding high-resolution (HR) images leads to compelling results for SR in diverse areas of research. In this article, we propose a deep learning-based image SR architecture in the Tchebichef transform domain. This is achieved by integrating a transform layer into the proposed architecture through a customized Tchebichef convolutional layer (TCL). The role of TCL is to convert the LR image from the spatial domain to the orthogonal transform domain using Tchebichef basis functions. The inversion of the transform mentioned earlier is achieved using another layer known as the inverse TCL (ITCL), which converts back the LR images from the transform domain to the spatial domain. It has been observed that using the Tchebichef transform domain for the task of SR takes the advantage of high and low- frequency representation of images that makes the task of SR simplified. Furthermore, a transfer learning-based approach is adopted to enhance the quality of images by considering Covid19 medical images as an additional experiment. It is shown that our architecture enhances the quality of X-ray and CT images of COVID-19, providing a better image quality that may help in clinical diagnosis. Experimental results obtained using the proposed Tchebichef transform domain SR (TTDSR) architecture provides competitive results when compared with most of the deep learning methods employed using a fewer number of trainable parameters.

Improving the reliability of digital cameras identification by optimizing the noise portraits comparing

The issues of optimization of existing methods for digital camera sensor identification are considered. Ways of improvement of reliability of digital cameras identification is discussed. Homogeneous images were optically recorded to form a noise portrait and test sets of amateur images for 3 cameras of various types. An optimal digital filter was selected to evaluate smoothed images for obtaining noise portraits of identified cameras. Camera identification algorithm was optimized basing on a comparison of light spatial noise portraits. Application of the optimal filter and identity criterion provides an average increase of identification reliability of more than 60 times. The results can be useful in the areas of image registration and processing, security, forensics, big data analysis, etc.

A fast matrix completion method based on truncated$ {\mathit{L}}_{2, 1} $ norm minimization

<abstract> <p>In recent years, a truncated nuclear norm regularization (TNNR) method has obtained much attention from researchers in machine learning and image processing areas, because it is much more accurate on matrices with missing data than other traditional methods based on nuclear norm. However, the TNNR method is reported to be very slow, due to its large number of singular value decomposition (SVD) iterations. In this paper, a truncated $ {\boldsymbol{L}}_\bf{2, 1} $ norm minimization method was presented for fast and accurate matrix completion, which is abbreviated as TLNM. In the proposed TLNM method, the truncated nuclear norm minimization model of TNNR was improved to a truncated $ {\boldsymbol{L}}_\bf{2, 1} $ norm minimization model that aimed to optimize the truncated $ {\boldsymbol{L}}_\bf{2, 1} $ Norm and a weighted noisy matrix simultaneously for improving the accuracy of TLNM. Using Qatar Riyal (QR) decomposition to calculate the orthogonal bases for reconstructing recovery results, the proposed TLNM method is much faster than the TNNR method. Adequate results for color images validate the effectiveness and efficiency of TLNM comparing with TNNR and other competing methods.</p> </abstract>

An Architecture-Oriented Analysis of Stacked Denoising Autoencoders

One of the major threats in computer vison and image processing areas is image tarnishing due to noisy pixels. Image tarnishing occurs when clean images are subjected to multiple feature changes, length transmission, or due to improper image capturing. The growth of Autoencoders in Artificial Neural Networks has paved way to efficient noise removal. In this work, an architecture oriented analysis of stacked denoising autoencoders is implemented by considering two perspectives of noise, namely noise as an inverse problem and noise as a residual problem. Autoencoders have been modelled by considering the approaches: Shallow Model, Deep-Series and Parallel Series models. Autoencoders with Skip Connections and Denoising CNNs have also been implemented and analyzed in order to propose an efficient, optimized and best working model for denoising. The dataset used is Common Object in Context (COCO) and the performance of the model is evaluated based on Structural Similarity Index (SSIM) and Peak Signal to Noise Ratio (PSNR). The analysis has presented the impact of the model structures of the autoencoders, which implicitly tend to treat noise as an inverse problem.

Tensor Methods in Biomedical Image Analysis.

In the past decade, tensors have become increasingly attractive in different aspects of signal and image processing areas. The main reason is the inefficiency of matrices in representing and analyzing multimodal and multidimensional datasets. Matrices cannot preserve the multidimensional correlation of elements in higher-order datasets and this highly reduces the effectiveness of matrix-based approaches in analyzing multidimensional datasets. Besides this, tensor-based approaches have demonstrated promising performances. These together, encouraged researchers to move from matrices to tensors. Among different signal and image processing applications, analyzing biomedical signals and images is of particular importance. This is due to the need for extracting accurate information from biomedical datasets which directly affects patient's health. In addition, in many cases, several datasets have been recorded simultaneously from a patient. A common example is recording electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) of a patient with schizophrenia. In such a situation, tensors seem to be among the most effective methods for the simultaneous exploitation of two (or more) datasets. Therefore, several tensor-based methods have been developed for analyzing biomedical datasets. Considering this reality, in this paper, we aim to have a comprehensive review on tensor-based methods in biomedical image analysis. The presented study and classification between different methods and applications can show the importance of tensors in biomedical image enhancement and open new ways for future studies.

TIFd-FR: Trends, Issues and Future directions of feature extraction in Face Recognition

Today, face recognition is the most prevalent and effective mechanism among various biometric technologies as it is non-invasive method. It helps in identifying or verifying the identity of a person by utilizing its face. But face recognition (FR) can be prone to high error rate. Therefore, efficient feature extraction methods are required for extracting robust facial features to develop efficient FR system. A FR system comprises of mainly three phases, that is, face detection and orientation, extracting facial features and classification of features. The most vital part of an efficient recognition system is extraction of robust features. Hence, extracting facial features is active research area of image processing. Although algorithms have been developed for extracting features, efficient and robust feature extraction still offers great challenge to researchers. Hence, a thorough analysis of feature extraction techniques presented in this work will enable the researchers to select the best suited technique for developing efficient system for recognition of face images. The performance of different feature extraction methods varies under variations in illumination, occlusion and pose etc. It is observed that deep-learning based feature extraction methods outperform wavelet-based methods. After rigorous analysis of various state-of-art techniques it is found that highest accuracy rate of 99.5% is achieved on AR database using wavelet based feature extraction whereas 99.78% is attained using convolutional neural network accuracy and various results achieved till now are stated.

A Comprehensive Review of Single Image Defogging Techniques used for Sea Fog Images

Image Defogging is a well-addressed and challenging problem in the area of image processing. The foggy weather conditions in the atmosphere cause adverse effects on the images captured by the camera which in turn make it difficult to identify and detect the objects. Image defogging has many applications in the real world including traffic safety, remote sensing, agricultural monitoring, maritime surveillance, underwater imaging, etc. Based on these applications many defogging algorithms have been proposed in the past decades. Almost all defogging algorithms concentrate more on land images rather than ocean images. Fog removal from ocean images is more challenging than of removing fog from land images due to the atmospheric properties of fog in the sea. This paper mainly focuses on the study and review of various defogging approaches used for the removal of fog in ocean images. This work discusses some image-defogging techniques applied to ocean images, to get a clear vision of the images for various applications.

A Robust Machine Learning Model for Diabetic Retinopathy Classification.

Ensemble learning is a process that belongs to the artificial intelligence (AI) field. It helps to choose a robust machine learning (ML) model, usually used for data classification. AI has a large connection with image processing and feature classification, and it can also be successfully applied to analyzing fundus eye images. Diabetic retinopathy (DR) is a disease that can cause vision loss and blindness, which, from an imaging point of view, can be shown when screening the eyes. Image processing tools can analyze and extract the features from fundus eye images, and these corroborate with ML classifiers that can perform their classification among different disease classes. The outcomes integrated into automated diagnostic systems can be a real success for physicians and patients. In this study, in the form image processing area, the manipulation of the contrast with the gamma correction parameter was applied because DR affects the blood vessels, and the structure of the eyes becomes disorderly. Therefore, the analysis of the texture with two types of entropies was necessary. Shannon and fuzzy entropies and contrast manipulation led to ten original features used in the classification process. The machine learning library PyCaret performs complex tasks, and the empirical process shows that of the fifteen classifiers, the gradient boosting classifier (GBC) provides the best results. Indeed, the proposed model can classify the DR degrees as normal or severe, achieving an accuracy of 0.929, an F1 score of 0.902, and an area under the curve (AUC) of 0.941. The validation of the selected model with a bootstrap statistical technique was performed. The novelty of the study consists of the extraction of features from preprocessed fundus eye images, their classification, and the manipulation of the contrast in a controlled way.

ChromEDA: Chromosome classification by ensemble framework based domain adaptation.

The precise identification of chromosomal abnormalities based on microscopy images in clinics heavily relies on manual analysis by karyotype experts, which is expensive and labor-intensive. Therefore, there is an urgent need for automatic classification technologies. However, current deep learning-based methods require a large amount of annotated data to achieve satisfactory performance. Additionally, there are domain shifts between datasets obtained from different instruments and clinical agencies, which hinders the utilization of existing public data resources. To overcome these challenges, we propose a novel ensemble learning framework called ChromEDA. This method incorporates soft pseudo-label learning, adversarial learning, and angle classification learning strategies to mitigate the domain shift. To evaluate its performance, we conducted cross-domain classification experiments using both public and private datasets. The results demonstrate that ChromEDA effectively addresses the domain shift issue and outperforms existing methods in cross-domain chromosome classification tasks. RESEARCH HIGHLIGHTS: The research transferred an unsupervised cross-domain algorithm into the chromosome microscopic image processing area, which can support fast and efficient deployment in equipment such as microscopies. To our knowledge, it is the first domain adaption application in chromosome image analysis. The research designed an ensemble learning framework-based chromosome classification model to alleviate the domain shift between different domains. It is a combination of soft pseudo-label learning, adversarial learning, and self-supervised angle recognition, which can significantly reduce the annotation requirements for chromosomal image processing. The results find that for chromosomes sharing the same centromere position category, banding information may contribute more to within-group classification. Thus, banding pattern information is encouraged to be considered for more precise classification of chromosomes.

Image denoising based on a variable spatially exponent PDE

Image denoising is always considered an important area of image processing. In this work, we address a new PDE-based model for image denoising that have been contaminated by multiplicative noise, specially the Speckle one. We propose a new class of PDEs whose nonlinear structure depends on a spatially tensor depending quantity attached to the desired solution, which takes into account the gray level information by introducing a gray level indicator function in the diffusion coefficient. We give some theoretical results, discretization and also stability condition for the suggested model. Finally, we carry out some numerical results to approve the effectiveness of our model by comparing the results obtained with some competitive models.

Brain Tumor Classification, Segmentation, and Detection using Deep Learning - A Review

V.Vapnik in 1965 proposed Vector methods. Kimeldorf presented a technique for creating kernel space based on support vectors in 1971. Support Vector Machine (SVM) techniques were initially presented in the 1990s by V. Vapnik in the field of statistical learning. Since then, pattern recognition, natural language processing, image processing and other areas have seen extensive use of SVM. By converting non-linear sample space into linear space via a kernel approach, the algorithm's complexity is reduced. Image classification is a well-known issue in image processing. Predicting the input image categories using the features is the main objective of image classification. There are several different classifiers, including Artificial Neural Networks, Support Vector Machines, and Random Forests, Decision Forests, k-NNs (k Nearest Neighbors), and Adaptive Boost. SVM is one of the best techniques for categorizing any image or pattern. A common non-invasive technique used in the medical sector for the analysis, diagnosis, treatment of brain tissues is magnetic resonance imaging. When a brain tumor is discovered early, the patient's life can be saved by receiving the appropriate care. It becomes difficult to accurately identify tumors in the MRI slices, which requires fussy work..

Research of different feature detection and matching algorithms on panoramic image

Image stitching is the process of combining numerous photos to make a panorama. The technique of image stitching has rapidly advanced and grown to be a significant area of digital image processing. Many image stitching methods have been proposed and studied in prior study. In this paper, the image stitching process is implemented using different algorithms. For keypoints detection, the algorithms of Harris corner detection, SIFT(Scale-Invariant Feature Transform), SURF(Speeded Up Robust Feature) and ORB(Oriented FAST and Rotated BRIEF) algorithms are applied, then use different methods (i.e., Brute Force, etc.) for feature matching. The RANSAC(Random Sample Consensus) method is used to calculate a homography matrix from matched feature vectors and use it to warp the images. Image blending and cropping methods are proposed to enhance the image quality. Given groups of the self-captured images, experiments have been down to shown the performance of different techniques.

Yoga Pose Estimation Using YOLO Model

Yoga, an historic exercise for every person and intellectual nicely-being, has gained large recognition in todays world . Monitoring yoga postures is essential for ensuring proper form, but yoga without an yoga professional is not good for person. In this research, we go deeply into the area of video processing ,image processing and deep learning, providing a new approach to yoga pose estimation. Leveraging the modern day YOLO (You Only Look Once) pose version, we suggest an revolutionary answer for real-time yoga pose detection in both images and video. The YOLO structure is customized and adaptative to recognizing and detecting yoga postures, maximizing accuracy and performance. YOLO is a popular deep learning algorithm used for object detection and classification in images and videos. It's known for its speed and efficiency. We inspect the result with in the parameter and also use customize data. We specially design this model for yoga Beginner and Intermediate those who cannot afford personal trainer or not able to mange time. Additionally, we renowned the limitations encountered in the course of our studies, also covering the way for future investigations. Keywords: Pose Estimation,YOLO,KeyPoints Detection,Virtual yoga ,ML models