Pub Date : 2023-10-14DOI: 10.1142/s0219467825500305
Manbir Sandhu, Sumit Kushwaha, Tanvi Arora
Computed Tomography (CT) offers great visualization of the intricate internal body structures. To protect a patient from the potential radiation-related health risks, the acquisition of CT images should adhere to the “as low as reasonably allowed” (ALARA) standard. However, the acquired Low-dose CT (LDCT) images are inadvertently corrupted by artifacts and noise during the processes of acquisition, storage, and transmission, degrading the visual quality of the image and also causing the loss of image features and relevant information. Most recently, generative adversarial network (GAN) models based on deep learning (DL) have demonstrated ground-breaking performance to minimize image noise while maintaining high image quality. These models’ ability to adapt to uncertain noise distributions and representation-learning ability makes them highly desirable for the denoising of CT images. The state-of-the-art GANs used for LDCT image denoising have been comprehensively reviewed in this research paper. The aim of this paper is to highlight the potential of DL-based GAN for CT dose optimization and present future scope of research in the domain of LDCT image denoising.
{"title":"A Comprehensive Review of GAN-Based Denoising Models for Low-Dose Computed Tomography Images","authors":"Manbir Sandhu, Sumit Kushwaha, Tanvi Arora","doi":"10.1142/s0219467825500305","DOIUrl":"https://doi.org/10.1142/s0219467825500305","url":null,"abstract":"Computed Tomography (CT) offers great visualization of the intricate internal body structures. To protect a patient from the potential radiation-related health risks, the acquisition of CT images should adhere to the “as low as reasonably allowed” (ALARA) standard. However, the acquired Low-dose CT (LDCT) images are inadvertently corrupted by artifacts and noise during the processes of acquisition, storage, and transmission, degrading the visual quality of the image and also causing the loss of image features and relevant information. Most recently, generative adversarial network (GAN) models based on deep learning (DL) have demonstrated ground-breaking performance to minimize image noise while maintaining high image quality. These models’ ability to adapt to uncertain noise distributions and representation-learning ability makes them highly desirable for the denoising of CT images. The state-of-the-art GANs used for LDCT image denoising have been comprehensively reviewed in this research paper. The aim of this paper is to highlight the potential of DL-based GAN for CT dose optimization and present future scope of research in the domain of LDCT image denoising.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135803438","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}
Pub Date : 2023-09-26DOI: 10.1142/s0219467825500214
P. John Bosco, S. Janakiraman
Content-Based Image Retrieval (CBIR) is a broad research field in the current digital world. This paper focuses on content-based image retrieval based on visual properties, consisting of high-level semantic information. The variation between low-level and high-level features is identified as a semantic gap. The semantic gap is the biggest problem in CBIR. The visual characteristics are extracted from low-level features such as color, texture and shape. The low-level feature increases CBIRs performance level. The paper mainly focuses on an image retrieval system called combined color (TriCLR) (RGB, YCbCr, and [Formula: see text]) with the histogram of texture features in LBP (HistLBP), which, is known as a hybrid of three colors (TriCLR) with Histogram of LBP (TriCLR and HistLBP). The study also discusses the hybrid method in light of low-level features. Finally, the hybrid approach uses the (TriCLR and HistLBP) algorithm, which provides a new solution to the CBIR system that is better than the existing methods.
{"title":"Content-Based Image Retrieval (CBIR): Using Combined Color and Texture Features (TriCLR and HistLBP)","authors":"P. John Bosco, S. Janakiraman","doi":"10.1142/s0219467825500214","DOIUrl":"https://doi.org/10.1142/s0219467825500214","url":null,"abstract":"Content-Based Image Retrieval (CBIR) is a broad research field in the current digital world. This paper focuses on content-based image retrieval based on visual properties, consisting of high-level semantic information. The variation between low-level and high-level features is identified as a semantic gap. The semantic gap is the biggest problem in CBIR. The visual characteristics are extracted from low-level features such as color, texture and shape. The low-level feature increases CBIRs performance level. The paper mainly focuses on an image retrieval system called combined color (TriCLR) (RGB, YCbCr, and [Formula: see text]) with the histogram of texture features in LBP (HistLBP), which, is known as a hybrid of three colors (TriCLR) with Histogram of LBP (TriCLR and HistLBP). The study also discusses the hybrid method in light of low-level features. Finally, the hybrid approach uses the (TriCLR and HistLBP) algorithm, which provides a new solution to the CBIR system that is better than the existing methods.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135718979","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}
Pub Date : 2023-09-25DOI: 10.1142/s0219467825500329
R. S. Rajasree, S. Brintha Rajakumari
Machine learning (ML) and deep learning (DL) techniques can considerably enhance the process of making a precise diagnosis of Alzheimer’s disease (AD). Recently, DL techniques have had considerable success in processing medical data. They still have drawbacks, like large data requirements and a protracted training phase. With this concern, we have developed a novel strategy with the four stages. In the initial stage, the input data is subjected to data imbalance processing, which is crucial for enhancing the accuracy of disease detection. Subsequently, entropy-based, correlation-based, and improved mutual information-based features will be extracted from these pre-processed data. However, the curse of dimensionality will be a serious issue in this work, and hence we have sorted it out via optimization strategy. Particularly, the tunicate updated golden eagle optimization (TUGEO) algorithm is proposed to pick out the optimal features from the extracted features. Finally, the ensemble classifier, which integrates models like CNN, DBN, and improved RNN is modeled to diagnose the diseases by training the selected optimal features from the previous stage. The suggested model achieves the maximum F-measure as 97.67, which is better than the extant methods like [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text], respectively. The suggested TUGEO-based AD detection is then compared to the traditional models like various performance matrices including accuracy, sensitivity, specificity, and precision.
{"title":"Deep Ensemble of Classifiers for Alzheimer’s Disease Detection with Optimal Feature Set","authors":"R. S. Rajasree, S. Brintha Rajakumari","doi":"10.1142/s0219467825500329","DOIUrl":"https://doi.org/10.1142/s0219467825500329","url":null,"abstract":"Machine learning (ML) and deep learning (DL) techniques can considerably enhance the process of making a precise diagnosis of Alzheimer’s disease (AD). Recently, DL techniques have had considerable success in processing medical data. They still have drawbacks, like large data requirements and a protracted training phase. With this concern, we have developed a novel strategy with the four stages. In the initial stage, the input data is subjected to data imbalance processing, which is crucial for enhancing the accuracy of disease detection. Subsequently, entropy-based, correlation-based, and improved mutual information-based features will be extracted from these pre-processed data. However, the curse of dimensionality will be a serious issue in this work, and hence we have sorted it out via optimization strategy. Particularly, the tunicate updated golden eagle optimization (TUGEO) algorithm is proposed to pick out the optimal features from the extracted features. Finally, the ensemble classifier, which integrates models like CNN, DBN, and improved RNN is modeled to diagnose the diseases by training the selected optimal features from the previous stage. The suggested model achieves the maximum F-measure as 97.67, which is better than the extant methods like [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text], respectively. The suggested TUGEO-based AD detection is then compared to the traditional models like various performance matrices including accuracy, sensitivity, specificity, and precision.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135816967","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}
Pub Date : 2023-09-09DOI: 10.1142/s0219467825500275
MD Azam Pasha, M. Narayana
Due to the combination of genetic diseases as well as a variety of biomedical abnormalities, the fatal disease named cancer is caused. Colon and lung cancer are regarded as the two leading diseases for disability and death. The most significant component for demonstrating the best course of action is the histopathological identification of such malignancies. So, in order to minimize the mortality rate caused by cancer, there is a need for early detection of the aliment on both fronts accordingly. In this case, both the deep and machine learning techniques have been utilized to speed up the detection process of cancer which may also help the researchers to study a huge amount of patients over a short period and less loss. Hence, it is highly essential to design a new lung and colon detection model based on deep learning approaches. Initially, a different set of histopathological images is collected from benchmark resources to perform effective analysis. Then, to attain the first set of features, the collected image is offered to the dilated net for attaining deep image features with the help of the Visual Geometry Group (VGG16) and Residual Neural Network (ResNet). Further, the second set of features is attained by the below process. Here, the collected image is given to pre-processing phase and the image is pre–pre-processed with the help of Contrast-limited Adaptive Histogram Equalization (CLAHE) and filter technique. Then, the pre-processed image is offered to the segmentation phase with the help of adaptive binary thresholding and offered to a dilated network that holds VGG16 and ResNet and attained the second set of features. The parameters of adaptive binary thresholding are tuned with the help of a developed hybrid approach called Sand Cat swarm JAya Optimization (SC-JAO) via Sand Cat swarm Optimization (SCO) and JAYA (SC-JAO). Finally, the third set of features is attained by offering the image to pre-processing phase. Then, the pre-processed image is offered to the segmentation phase and the image is a segmented phase and features are tuned by developed SC-JAO. Further, the segmented features are offered to attain the textural features like Gray-Level Co-Occurrence Matrix (GLCM) and Local Weber Pattern (LWP) and attained the third set of features. Then, the attained three different sets of features are given to the optimal weighted feature phase, where the parameters are optimized by the SC-JAO algorithm and then given to the disease prediction phase. Here, disease prediction is made with the help of Attention-based Adaptive Weighted Recurrent Neural Networks (AAW-RNN), and their parameters are tuned by developed SC-JAO. Thus, the developed model achieved an effective lung and colon detection rate over conventional approaches over multiple experimental analyses.
{"title":"Development of Trio Optimal Feature Extraction Model for Attention-Based Adaptive Weighted RNN-Based Lung and Colon Cancer Detection Framework Using Histopathological Images","authors":"MD Azam Pasha, M. Narayana","doi":"10.1142/s0219467825500275","DOIUrl":"https://doi.org/10.1142/s0219467825500275","url":null,"abstract":"Due to the combination of genetic diseases as well as a variety of biomedical abnormalities, the fatal disease named cancer is caused. Colon and lung cancer are regarded as the two leading diseases for disability and death. The most significant component for demonstrating the best course of action is the histopathological identification of such malignancies. So, in order to minimize the mortality rate caused by cancer, there is a need for early detection of the aliment on both fronts accordingly. In this case, both the deep and machine learning techniques have been utilized to speed up the detection process of cancer which may also help the researchers to study a huge amount of patients over a short period and less loss. Hence, it is highly essential to design a new lung and colon detection model based on deep learning approaches. Initially, a different set of histopathological images is collected from benchmark resources to perform effective analysis. Then, to attain the first set of features, the collected image is offered to the dilated net for attaining deep image features with the help of the Visual Geometry Group (VGG16) and Residual Neural Network (ResNet). Further, the second set of features is attained by the below process. Here, the collected image is given to pre-processing phase and the image is pre–pre-processed with the help of Contrast-limited Adaptive Histogram Equalization (CLAHE) and filter technique. Then, the pre-processed image is offered to the segmentation phase with the help of adaptive binary thresholding and offered to a dilated network that holds VGG16 and ResNet and attained the second set of features. The parameters of adaptive binary thresholding are tuned with the help of a developed hybrid approach called Sand Cat swarm JAya Optimization (SC-JAO) via Sand Cat swarm Optimization (SCO) and JAYA (SC-JAO). Finally, the third set of features is attained by offering the image to pre-processing phase. Then, the pre-processed image is offered to the segmentation phase and the image is a segmented phase and features are tuned by developed SC-JAO. Further, the segmented features are offered to attain the textural features like Gray-Level Co-Occurrence Matrix (GLCM) and Local Weber Pattern (LWP) and attained the third set of features. Then, the attained three different sets of features are given to the optimal weighted feature phase, where the parameters are optimized by the SC-JAO algorithm and then given to the disease prediction phase. Here, disease prediction is made with the help of Attention-based Adaptive Weighted Recurrent Neural Networks (AAW-RNN), and their parameters are tuned by developed SC-JAO. Thus, the developed model achieved an effective lung and colon detection rate over conventional approaches over multiple experimental analyses.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136193149","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}
Pub Date : 2023-09-07DOI: 10.1142/s0219467825500342
Madhavarapu Chandan, S. G. Santhi, T. Srinivasa Rao
Due to the major operating restrictions, ensuring security is the fundamental problem of Wireless Sensor Networks (WSNs). Because of their inadequate security mechanisms, WSNs are indeed a simple point for malware (worms, viruses, malicious code, etc.). According to the epidemic nature of worm propagation, it is critical to develop a worm defense mechanism in the network. This concept aims to establish novel malware detection in WSN that consists of several phases: “(i) Preprocessing, (ii) feature extraction, as well as (iii) detection”. At first, the input data is subjected for preprocessing phase. Then, the feature extraction takes place, in which principal component analysis (PCA), improved linear discriminant analysis (LDA), and autoencoder-based characteristics are retrieved. Moreover, the retrieved characteristics are subjected to the detection phase. The detection is performed employing combined shallow learning and DL. Further, the shallow learning includes decision tree (DT), logistic regression (LR), and Naive Bayes (NB); the deep learning (DL) includes deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN). Here, the DT output is given to the DNN, LR output is subjected to CNN, and the NB output is given to the RNN, respectively. Eventually, the DNN, CNN, and RNN outputs are averaged to generate a successful outcome. The combination can be thought of as an Ensemble classifier. The weight of the RNN is optimally tuned through the Self Improved Shark Smell Optimization with Opposition Learning (SISSOOL) model to improve detection precision and accuracy. Lastly, the outcomes of the suggested approach are computed in terms of different measures.
{"title":"Combined Shallow and Deep Learning Models for Malware Detection in Wsn","authors":"Madhavarapu Chandan, S. G. Santhi, T. Srinivasa Rao","doi":"10.1142/s0219467825500342","DOIUrl":"https://doi.org/10.1142/s0219467825500342","url":null,"abstract":"Due to the major operating restrictions, ensuring security is the fundamental problem of Wireless Sensor Networks (WSNs). Because of their inadequate security mechanisms, WSNs are indeed a simple point for malware (worms, viruses, malicious code, etc.). According to the epidemic nature of worm propagation, it is critical to develop a worm defense mechanism in the network. This concept aims to establish novel malware detection in WSN that consists of several phases: “(i) Preprocessing, (ii) feature extraction, as well as (iii) detection”. At first, the input data is subjected for preprocessing phase. Then, the feature extraction takes place, in which principal component analysis (PCA), improved linear discriminant analysis (LDA), and autoencoder-based characteristics are retrieved. Moreover, the retrieved characteristics are subjected to the detection phase. The detection is performed employing combined shallow learning and DL. Further, the shallow learning includes decision tree (DT), logistic regression (LR), and Naive Bayes (NB); the deep learning (DL) includes deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN). Here, the DT output is given to the DNN, LR output is subjected to CNN, and the NB output is given to the RNN, respectively. Eventually, the DNN, CNN, and RNN outputs are averaged to generate a successful outcome. The combination can be thought of as an Ensemble classifier. The weight of the RNN is optimally tuned through the Self Improved Shark Smell Optimization with Opposition Learning (SISSOOL) model to improve detection precision and accuracy. Lastly, the outcomes of the suggested approach are computed in terms of different measures.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43201003","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}
Pub Date : 2023-09-05DOI: 10.1142/s021946782550024x
Sivaramakrishna Yechuri, Sunny Dayal Vanabathina
Speech enhancement methods differ depending on the degree of degradation and noise in the speech signal, so research in the field is still difficult, especially when dealing with residual and background noise, which is highly transient. Numerous deep learning networks have been developed that provide promising results for improving the perceptual quality and intelligibility of noisy speech. Innovation and research in speech enhancement have been opened up by the power of deep learning techniques with implications across a wide range of real time applications. By reviewing the important datasets, feature extraction methods, deep learning models, training algorithms and evaluation metrics for speech enhancement, this paper provides a comprehensive overview. We begin by tracing the evolution of speech enhancement research, from early approaches to recent advances in deep learning architectures. By analyzing and comparing the approaches to solving speech enhancement challenges, we categorize them according to their strengths and weaknesses. Moreover, we discuss the challenges and future directions of deep learning in speech enhancement, including the demand for parameter-efficient models for speech enhancement. The purpose of this paper is to examine the development of the field, compare and contrast different approaches, and highlight future directions as well as challenges for further research.
{"title":"Speech Enhancement: A Review of Different Deep Learning Methods","authors":"Sivaramakrishna Yechuri, Sunny Dayal Vanabathina","doi":"10.1142/s021946782550024x","DOIUrl":"https://doi.org/10.1142/s021946782550024x","url":null,"abstract":"Speech enhancement methods differ depending on the degree of degradation and noise in the speech signal, so research in the field is still difficult, especially when dealing with residual and background noise, which is highly transient. Numerous deep learning networks have been developed that provide promising results for improving the perceptual quality and intelligibility of noisy speech. Innovation and research in speech enhancement have been opened up by the power of deep learning techniques with implications across a wide range of real time applications. By reviewing the important datasets, feature extraction methods, deep learning models, training algorithms and evaluation metrics for speech enhancement, this paper provides a comprehensive overview. We begin by tracing the evolution of speech enhancement research, from early approaches to recent advances in deep learning architectures. By analyzing and comparing the approaches to solving speech enhancement challenges, we categorize them according to their strengths and weaknesses. Moreover, we discuss the challenges and future directions of deep learning in speech enhancement, including the demand for parameter-efficient models for speech enhancement. The purpose of this paper is to examine the development of the field, compare and contrast different approaches, and highlight future directions as well as challenges for further research.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2023-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45839286","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}
Pub Date : 2023-09-01DOI: 10.1142/s0219467825500093
Xin Wang, Xiaogang Dong
The blurring of texture edges often occurs during image data transmission and acquisition. To ensure the detailed clarity of the drag-time images, we propose a time image de-noising method based on sparse regularization. First, the image pixel sparsity index is set, and then an image de-noising model is established based on sparse regularization processing to obtain the neighborhood weights of similar image blocks. Second, a time image de-noising algorithm is designed to determine whether the coding coefficient reaches the standard value, and a new image de-noising method is obtained. Finally, the images of electronic clocks and mechanical clocks are used as two kinds of time images to compare different image de-noising methods, respectively. The results show that the sparsity regularization method has the highest peak signal-to-noise ratio among the six compared methods for different noise standard deviations and two time images. The image structure similarity is always above which shows that the proposed method is better than the other five image de-noising methods.
{"title":"Time Image De-Noising Method Based on Sparse Regularization","authors":"Xin Wang, Xiaogang Dong","doi":"10.1142/s0219467825500093","DOIUrl":"https://doi.org/10.1142/s0219467825500093","url":null,"abstract":"The blurring of texture edges often occurs during image data transmission and acquisition. To ensure the detailed clarity of the drag-time images, we propose a time image de-noising method based on sparse regularization. First, the image pixel sparsity index is set, and then an image de-noising model is established based on sparse regularization processing to obtain the neighborhood weights of similar image blocks. Second, a time image de-noising algorithm is designed to determine whether the coding coefficient reaches the standard value, and a new image de-noising method is obtained. Finally, the images of electronic clocks and mechanical clocks are used as two kinds of time images to compare different image de-noising methods, respectively. The results show that the sparsity regularization method has the highest peak signal-to-noise ratio among the six compared methods for different noise standard deviations and two time images. The image structure similarity is always above which shows that the proposed method is better than the other five image de-noising methods.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135688305","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}
Pub Date : 2023-08-31DOI: 10.1142/s0219467825500226
Rasmiranjan Mohakud, Rajashree Dash
For dermatoscopic skin lesion images, deep learning-based algorithms, particularly convolutional neural networks (CNN), have demonstrated good classification and segmentation capabilities. The impact of utilizing lesion segmentation data on classification performance, however, is still up for being subject to discussion. Being driven in this direction, in this work we propose a hybrid deep learning-based model to classify the skin cancer using segmented images. In the first stage, a fully convolutional encoder–decoder network (FCEDN) is employed to segment the skin cancer image and then in the second phase, a CNN is applied on the segmented images for classification. As the model’s success depends on the hyper-parameters it uses and fine-tuning these hyper-parameters by hand is time-consuming, so in this study the hyper-parameters of the hybrid model are optimized by utilizing an exponential neighborhood gray wolf optimization (ENGWO) technique. Extensive experiments are carried out using the International Skin Imaging Collaboration (ISIC) 2016 and ISIC 2017 datasets to show the efficacy of the model. The suggested model has been evaluated on both balanced and unbalanced datasets. With the balanced dataset, the proposed hybrid model achieves training accuracy up to 99.98%, validation accuracy up to 92.13% and testing accuracy up to 89.75%. It is evident from the findings that the proposed hybrid model outperforms previous known models in a competitive manner over balanced data.
{"title":"A Hybrid Model for Classification of Skin Cancer Images After Segmentation","authors":"Rasmiranjan Mohakud, Rajashree Dash","doi":"10.1142/s0219467825500226","DOIUrl":"https://doi.org/10.1142/s0219467825500226","url":null,"abstract":"For dermatoscopic skin lesion images, deep learning-based algorithms, particularly convolutional neural networks (CNN), have demonstrated good classification and segmentation capabilities. The impact of utilizing lesion segmentation data on classification performance, however, is still up for being subject to discussion. Being driven in this direction, in this work we propose a hybrid deep learning-based model to classify the skin cancer using segmented images. In the first stage, a fully convolutional encoder–decoder network (FCEDN) is employed to segment the skin cancer image and then in the second phase, a CNN is applied on the segmented images for classification. As the model’s success depends on the hyper-parameters it uses and fine-tuning these hyper-parameters by hand is time-consuming, so in this study the hyper-parameters of the hybrid model are optimized by utilizing an exponential neighborhood gray wolf optimization (ENGWO) technique. Extensive experiments are carried out using the International Skin Imaging Collaboration (ISIC) 2016 and ISIC 2017 datasets to show the efficacy of the model. The suggested model has been evaluated on both balanced and unbalanced datasets. With the balanced dataset, the proposed hybrid model achieves training accuracy up to 99.98%, validation accuracy up to 92.13% and testing accuracy up to 89.75%. It is evident from the findings that the proposed hybrid model outperforms previous known models in a competitive manner over balanced data.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44995806","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}
Pub Date : 2023-08-31DOI: 10.1142/s0219467825500238
Sumit Chhabra, Khushboo Bansal
Human brain tumors are now the most serious and horrible diseases for people, causing certain deaths. The patient’s life also becomes more complicated over time as a result of the brain tumor. Thus, it is essential to find tumors early to safeguard and extend the patient’s life. Hence, new improvements are highly essential in the techniques of brain tumor detection in medical areas. To address this, research has introduced automatic brain tumor prediction using Pteropus unicinctus optimization on deep neural networks (PUO-deep NNs). Initially, the data are gathered from the BraTS MICCAI brain tumor dataset and preprocessing and ROI extraction are performed to remove the noise from the data. Then the extracted RoI is forwarded to the fuzzy c-means (FCM) clustering to segment the brain image. The parameters of the FCM tune the PUO algorithm so the image is segmented into the tumor region and the non-tumor region. Then the feature extraction takes place on ResNet. Finally, the deep NN classifier successfully predicted the brain tumor by utilizing the PUO method, which improved the classifier performance and produced extremely accurate results. For dataset 1, the PUO-deep NN achieved values of 87.69% accuracy, 93.81% sensitivity, and 99.01% specificity. The suggested PUO-deep NN also attained the values for dataset 2 of 98.49%, 98.55%, and 95.60%, which is significantly more effective than the current approaches.
{"title":"An Efficient Brain Tumor Prediction Using Pteropus Unicinctus Optimization on Deep Neural Network","authors":"Sumit Chhabra, Khushboo Bansal","doi":"10.1142/s0219467825500238","DOIUrl":"https://doi.org/10.1142/s0219467825500238","url":null,"abstract":"Human brain tumors are now the most serious and horrible diseases for people, causing certain deaths. The patient’s life also becomes more complicated over time as a result of the brain tumor. Thus, it is essential to find tumors early to safeguard and extend the patient’s life. Hence, new improvements are highly essential in the techniques of brain tumor detection in medical areas. To address this, research has introduced automatic brain tumor prediction using Pteropus unicinctus optimization on deep neural networks (PUO-deep NNs). Initially, the data are gathered from the BraTS MICCAI brain tumor dataset and preprocessing and ROI extraction are performed to remove the noise from the data. Then the extracted RoI is forwarded to the fuzzy c-means (FCM) clustering to segment the brain image. The parameters of the FCM tune the PUO algorithm so the image is segmented into the tumor region and the non-tumor region. Then the feature extraction takes place on ResNet. Finally, the deep NN classifier successfully predicted the brain tumor by utilizing the PUO method, which improved the classifier performance and produced extremely accurate results. For dataset 1, the PUO-deep NN achieved values of 87.69% accuracy, 93.81% sensitivity, and 99.01% specificity. The suggested PUO-deep NN also attained the values for dataset 2 of 98.49%, 98.55%, and 95.60%, which is significantly more effective than the current approaches.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48086675","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}
Pub Date : 2023-08-30DOI: 10.1142/s0219467825500299
Xueying Duan
Recognizing abnormal behavior recognition (ABR) is an important part of social security work. To ensure social harmony and stability, it is of great significance to study the identification methods of abnormal human motion behavior. Aiming at the low accuracy of human motion ABR method, ABR method for human motion based on improved deep reinforcement learning (DRL) is proposed. First, the background image is processed in combination with the Gaussian model; second, the background features and human motion trajectory features are extracted, respectively; finally, the improved DRL model is constructed, and the feature information is input into the improvement model to further extract the abnormal behavior features, and the ABR of human motion is realized through the interaction between the agent and the environment. The different methods were examined based on UCF101 data set and HiEve data set. The results show that the accuracy of human motion key point acquisition and posture estimation accuracy is high, the proposed method sensitivity is good, and the recognition accuracy of human motion abnormal behavior is as high as 95.5%. It can realize the ABR for human motion and lay a foundation for the further development of follow-up social security management.
{"title":"Abnormal Behavior Recognition for Human Motion Based on Improved Deep Reinforcement Learning","authors":"Xueying Duan","doi":"10.1142/s0219467825500299","DOIUrl":"https://doi.org/10.1142/s0219467825500299","url":null,"abstract":"Recognizing abnormal behavior recognition (ABR) is an important part of social security work. To ensure social harmony and stability, it is of great significance to study the identification methods of abnormal human motion behavior. Aiming at the low accuracy of human motion ABR method, ABR method for human motion based on improved deep reinforcement learning (DRL) is proposed. First, the background image is processed in combination with the Gaussian model; second, the background features and human motion trajectory features are extracted, respectively; finally, the improved DRL model is constructed, and the feature information is input into the improvement model to further extract the abnormal behavior features, and the ABR of human motion is realized through the interaction between the agent and the environment. The different methods were examined based on UCF101 data set and HiEve data set. The results show that the accuracy of human motion key point acquisition and posture estimation accuracy is high, the proposed method sensitivity is good, and the recognition accuracy of human motion abnormal behavior is as high as 95.5%. It can realize the ABR for human motion and lay a foundation for the further development of follow-up social security management.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":1.6,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41533888","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：