International Journal of Image and Graphics最新文献

{"title":"Feature Engineering Versus Deep Learning for Scene Recognition: A Brief Survey","authors":"Seba Susan, Maduri Tuteja","doi":"10.1142/s0219467825500548","DOIUrl":"https://doi.org/10.1142/s0219467825500548","url":null,"abstract":"Scene recognition is an important computer vision task that has evolved from the study of the biological visual system. Its applications range from video surveillance, autopilot systems, to robotics. The early works were based on feature engineering that involved the computation and aggregation of global and local image descriptors. Several popular image features such as SIFT, SURF, HOG, ORB, LBP, KAZE, etc. have been proposed and applied to the task with successful results. Features can be either computed from the entire image on a global scale, or extracted from local sub-regions and aggregated across the image. Suitable classifier models are deployed that learn to classify these features. This review paper analyzes several of these handcrafted features that have been applied to the scene recognition task over the past decades, and tracks the transition from the traditional feature engineering to deep learning which forms the current state of the art in computer vision. Deep learning is now deemed to have overtaken feature engineering in several computer vision applications. Deep convolutional neural networks and vision transformers are the current state of the art for object recognition. However, scenes from urban landscapes are bound to contain similar objects posing a challenge to deep learning solutions for scene recognition. In our study, a critical analysis of feature engineering and deep learning methodologies for scene recognition is provided, and results on benchmark scene datasets are presented, concluding with a discussion on challenges and possible solutions that may facilitate more accurate scene recognition.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140726217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent Differentiation Framework for Lewy Body Dementia and Alzheimer’s disease using Adaptive Multi-Cascaded ResNet–Autoencoder–LSTM Network","authors":"K. Sravani, V. RaviSankar","doi":"10.1142/s0219467825500664","DOIUrl":"https://doi.org/10.1142/s0219467825500664","url":null,"abstract":"In recent years, most of the patients with dementia have acquired healthcare systems within the primary care system and they also have some challenging psychiatric and medical issues. Here, dementia-based symptoms are not identified in the primary care center, because they are affected by various factors like psychological symptoms, clinically relevant behavior, numerous psychotropic medications, and multiple chronic medical conditions. To enhance the healthcare-related applications, the primary healthcare system with additional resources like coordination with interdisciplinary dementia specialists, feasible diagnosis, and screening process need to be improved. Therefore, the differentiation between Alzheimer’s Disease (AD) and Lewy Body Dementia (LBD) has been acquired to provide the best clinical support to the patients. In this research work, the deep structure depending on AD and LBD systems has been implemented with the help of an adaptive algorithm to provide promising outcomes over dementia detection. Initially, the input images are collected from online sources. Thus, the collected images are forwarded to the newly designed Multi-Cascaded Deep Learning (MSDL), where the ResNet, Autoencoder, and weighted Long-Short Term Memory (LSTM) networks are serially cascaded to provide effective classification results. Then, the fully connected layer of ResNet is given to the Autoencoder structure. Here, the output from the encoder phase is optimized by using the Adaptive Water Wave Cuttlefish Optimization (AWWCO), which is derived from the Water Wave Optimization (WWO) and Cuttlefish Algorithm (CA), and the resultant selected output is fed to the weight-optimized LSTM network. Further, the parameters in the MSDL network are optimized by using the same AWWCO algorithm. Finally, the performance comparison over different heuristic algorithms and conventional dementia detection approaches is done for the validation of the overall effectiveness of the suggested model in terms of various estimation measures.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140727280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust Authentication System with Privacy Preservation for Hybrid Deep Learning-Based Person Identification System Using Multi-Modal Palmprint, Ear, and Face Biometric Features","authors":"Sharad B. Jadhav, N. K. Deshmukh, Sahebrao B. Pawar","doi":"10.1142/s0219467825500494","DOIUrl":"https://doi.org/10.1142/s0219467825500494","url":null,"abstract":"Conventional biometric systems are vulnerable to a range of harmful threats and privacy violations, putting the users who have registered with them in grave danger. Therefore, there is a need to develop a Privacy-Preserving and Authenticating Framework for Biometric-based Systems (PPAF-BS) that allows users to access multiple applications while also protecting their privacy. There are various existing works on biometric-based systems, but most of them do not address privacy concerns. Conventional biometric systems require the storage of biometric data, which can be easily accessed by attackers, leading to privacy violations. Some research works have used differential privacy techniques to address this issue, but they have not been widely applied in biometric-based systems. The existing biometric-based systems have a significant privacy concern, and there is a lack of privacy-preserving techniques in such systems. Therefore, there is a need to develop a PPAF-BS that can protect the user’s privacy and maintain the system’s efficiency. The proposed method uses Hybrid Deep Learning (HDL) with palmprint, ear, and face biometric features for person identification. Additionally, Discrete Cosine Transform (DCT) feature transformation and Lagrange’s interpolation-based image transformation are used as part of the authentication scheme. Sensors are used to record three biometric traits: palmprint, ear, and face. The combination of biometric characteristics provides an accuracy of 96.4% for the [Formula: see text] image size. The proposed LI-based image transformation lowers the original [Formula: see text] pixels to an [Formula: see text] hidden pattern. This drastically decreases the database size, thereby reducing storage needs. The proposed method offers a safe authentication system with excellent accuracy, a fixed-size database, and the privacy protection of multi-modal biometric characteristics without sacrificing overall system efficiency. The system achieves an accuracy of 96.4% for the [Formula: see text] image size, and the proposed LI-based picture transformation significantly reduces the database size, which is a significant achievement in terms of storage requirements. Therefore, the proposed method can be considered an effective solution to the privacy and security concerns of biometric-based systems.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140373148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Damage Object Detection of Steel Wire Rope-Core Conveyor Belts Based on the Improved YOLOv5","authors":"Baomin Wang, Hewei Ding, Fei Teng, Zhirong Wang, Hongqin Liu","doi":"10.1142/s0219467825500573","DOIUrl":"https://doi.org/10.1142/s0219467825500573","url":null,"abstract":"In response to the challenges in detecting damage features in X-ray images of steel wire rope-cores in conveyor belts, such as complex damage shapes, small sizes, low detection precision, and poor generalization ability, an improved YOLOv5 algorithm was proposed. The aim of the model is to accurately and efficiently identify and locate damage in the X-ray images of steel wire rope-cores in conveyor belts. First, the Adaptive Histogram Equalization (AHE) method is used to preprocess the images, reducing the interference of harsh mining environments and improving the quality of the dataset. Second, to better retain image details and enhance the detection ability of damage features, transpose convolutional upsampling is adopted, and the C3 module in the backbone network is replaced by C2f to ensure lightweight network models, meanwhile, it obtains richer gradient flow information and optimizing the loss function. Finally, the improved algorithm is compared with four classical detection algorithms using the damage feature dataset of steel wire rope-core conveyor belts. The experimental result shows that the proposed algorithm achieves an average detection precision of 91.8% and a detection speed of 40 frames per second (FPS) for images collected in harsh mining environments. The designed detection model provides a reference for the automatic recognition and detection of damage to steel wire rope-core conveyor belts.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140382150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Residual Network and Wavelet Transform-Based Non-Local Means Filter for Denoising Low-Dose Computed Tomography","authors":"R. Sehgal, V. Kaushik","doi":"10.1142/s021946782550072x","DOIUrl":"https://doi.org/10.1142/s021946782550072x","url":null,"abstract":"Image denoising helps to strengthen the image statistics and the image processing scenario. Because of the inherent physical difficulties of various recording technologies, images are prone to the emergence of some noise during image acquisition. In the existing methods, poor illumination and atmospheric conditions affect the overall performance. To solve these issues, in this paper Political Taylor-Anti Coronavirus Optimization (Political Taylor-ACVO) algorithm is developed by integrating the features of Political Optimizer (PO) with Taylor series and Anti Coronavirus Optimization (ACVO). The input medical image is subjected to noisy pixel identification step, in which the deep residual network (DRN) is used to discover noise values and then pixel restoration process is performed by the created Political Taylor-ACVO algorithm. Thereafter image enhancement mechanism strategy is done using vectorial total variation (VTV) norm. On the other hand, original image is applied to discrete wavelet transform (DWT) such that transformed result is fed to non-local means (NLM) filter. An inverse discrete wavelet transform (IDWT) is utilized to the filtered outcome for generating the denoised image. Finally, image enhancement result is fused with denoised image computed through filtering model to compute fused output image. The proposed model observed the value for Peak signal-to-noise ratio (PSNR) of 29.167 dB, Second Derivative like Measure of Enhancement (SDME) of 41.02 dB, and Structural Similarity Index (SSIM) of 0.880 for Gaussian noise.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140227312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unsupervised Color-Based Nuclei Segmentation in Histopathology Images with Various Color Spaces and K Values Selection","authors":"Qi Zhang, Zuobin Ying, Jian Shen, Seng-Ka Kou, Jingzhang Sun, Bob Zhang","doi":"10.1142/s0219467825500615","DOIUrl":"https://doi.org/10.1142/s0219467825500615","url":null,"abstract":"The development of digital pathology offers a significant opportunity to evaluate and analyze the whole slides of disease tissue effectively. In particular, the segmentation of nuclei from histopathology images plays an important role in quantitatively measuring and evaluating the acquired diseased tissue. There are many automatic methods to segment cell nuclei in histopathology images. One widely used unsupervised segmentation approach is based on standard k-means or fuzzy c-means (FCM) to process the color histopathology images to segment cell nuclei. Compared with the supervised learning method, this approach can obtain segmented nuclei without annotated nuclei labels for training, which saves a lot of labeling and training time. The color space and [Formula: see text] value among this method plays a crucial role in determining the nuclei segmentation performance. However, few works have investigated various color spaces and [Formula: see text] value selection simultaneously in unsupervised color-based nuclei segmentation with [Formula: see text]-means or FCM algorithms. In this study, we will present color-based nuclei segmentation methods with standard [Formula: see text]-means and FCM algorithms for histopathology images. Several color spaces of Haematoxylin and Eosin (H&E) stained histopathology data and various [Formula: see text] values among [Formula: see text]-means and FCM are investigated correspondingly to explore the suitable selection for nuclei segmentation. A comprehensive nuclei dataset with 7 different organs is used to validate our proposed method. Related experimental results indicate that [Formula: see text] and the YCbCr color spaces with a [Formula: see text] of 4 are more reasonable for nuclei segmentation via [Formula: see text]-means, while the [Formula: see text] color space with [Formula: see text] of 4 is useful via FCM.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140235921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pelican Crow Search Optimization Enabled MIRNet-Based Image Enhancement of Histopathological Images of Uterine Tissue","authors":"Veena I. Patil, Shobha R. Patil","doi":"10.1142/s0219467825500585","DOIUrl":"https://doi.org/10.1142/s0219467825500585","url":null,"abstract":"The digitalized image enhancement methods offer multiple options to improve the visual quality of images. The histopathological image assessment is the golden standard to diagnose endometrial cancer, which is also called uterine cancer that seriously affects the reproductive system of females. Owing to the limited capability, complex relationship among histopathological images and its elucidation utilizing existing methods frequently fails to obtain satisfying outcomes. As a result, in this study, the Pelican crow search optimization_multiple identities representation network (PCSO_MIRNet) is presented for improving the quality of histopathology images of uterine tissue. First, the histopathological images are given to pre-processing stage, which is performed by the median filter. The image enhancement is done utilizing MIRNet, which is trained by devised PCSO. The PCSO is developed by incorporating Pelican Optimization Algorithm (POA) and Crow Search Algorithm (CSA). Furthermore, PCSO_MIRNet attained the best outcomes with a maximal peak signal-to-noise ratio (PSNR) of 44.741 dB, minimal mean squared error (MSE) of 0.937, and minimal degree of distortion (DD) value achieved is 0.068 dB.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140247851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Study of Elliptic Curve Cryptography and Its Applications","authors":"U. Vijay Nikhil, Z. Stamenkovic, S. P. Raja","doi":"10.1142/s0219467825500627","DOIUrl":"https://doi.org/10.1142/s0219467825500627","url":null,"abstract":"This paper aims to provide a comprehensive review on Elliptic Curve Cryptography (ECC), a public key cryptographic system and its applications. The paper discusses important mathematical properties and operations of elliptic curves, like point addition and multiplication operations and its implementation in cryptographic methods such as encryption and decryption. This paper provides a detailed workout on important mathematical problems on elliptic curves and ECC which provides insight into working of essential cryptographic techniques in ECC. And the paper also provides a literature review of research works based on ECC in various fields such as Internet of Things (IoT), Cloud computing, Blockchain and Image Security. And the paper further provides insight into the recent applications of ECC in fields like IoT and Blockchain by comprehensively discussing the proposed mechanism for each of the recent applications and also briefly discussing the security of the proposed mechanism.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140250099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization Research of Bird Detection Algorithm Based on YOLO in Deep Learning Environment","authors":"Xi Chen, Zhenyu Zhang","doi":"10.1142/s0219467825500597","DOIUrl":"https://doi.org/10.1142/s0219467825500597","url":null,"abstract":"Recent environmental degradation has led to an unparalleled decline in wild bird habitats, resulting in a worldwide decrease in bird populations. To prevent extinction, it is vital to implement protective measures. One effective solution could be the application of deep learning techniques to identify bird species and habitats, which would prove useful for bird enthusiasts and rescuers. Therefore, a dataset of 20 globally prized bird species has been collated and analyzed. The Bird-YOLO algorithm precisely identifies avian creatures by combining neural architecture search and knowledge distillation. To diminish noise interference, preprocessing of images and dimension clustering of prior boxes are carried out prior to the training. The experiments show that the Bird-YOLO algorithm attains an 88.23% bird recognition rate, with a frames per second (FPS) of 47.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140250906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HLNBO: Hybrid Leader Namib Beetle Optimization Algorithm-Based LeNet for Classification of Parkinson’s Disease","authors":"S. Sharanyaa, M. Sambath","doi":"10.1142/s0219467825500639","DOIUrl":"https://doi.org/10.1142/s0219467825500639","url":null,"abstract":"Parkinson’s disease (PD) occurs while particular cells of the brain are not able to create dopamine that is required for regulating the count of non-motor as well as motor activities of the human body. One of the earlier symptoms of PD is voice disorder and current research shows that approximately about 90% of patients affected by PD suffer from vocal disorders. Hence, it is vital to extract pathology information in voice signals for detecting PD, which motivates to devise the approaches for feature selection and classification of PD. Here, an effectual technique is devised for the classification of PD, which is termed as Hybrid Leader Namib beetle optimization algorithm-based LeNet (HLNBO-based LeNet). The considered input voice signal is subjected to pre-processing of the signal phase. The pre-processing is carried out to remove the noises and calamities using a Gaussian filter whereas in the feature extraction phase, several features are extracted. The extracted features are given to the feature selection stage that is performed employing the Hybrid Leader Squirrel Search Water algorithm (HLSSWA), which is the combination of Hybrid Leader-Based Optimization (HLBO), Squirrel Search Algorithm (SSA), and Water Cycle Algorithm (WCA) by considering the Canberra distance as the fitness function. The PD classification is conducted using LeNet, which is tuned by the designed HLNBO. Additionally, HLNBO is newly presented by merging HLBO and the Namib beetle optimization algorithm (NBO). Thus, the new technique achieved maximal values of accuracy, TPR, and TNR of about 0.949, 0.957, and 0.936, respectively.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140248727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}