Pub Date : 2023-08-17DOI: 10.1142/s0219467825500354
Zhijing Gao, Weilin Qiu, Ren Wenqi, Xiao Yan
{"title":"Research on robust digital watermarking based on reversible information hiding","authors":"Zhijing Gao, Weilin Qiu, Ren Wenqi, Xiao Yan","doi":"10.1142/s0219467825500354","DOIUrl":"https://doi.org/10.1142/s0219467825500354","url":null,"abstract":"","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49136822","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 : 2023-08-04DOI: 10.1142/s0219467825500147
Laxmikant Eshwarappa, G. G. Rajput
Currently, the identification of text from video frames and normal scene images has got amplified awareness amongst analysts owing to its diverse challenges and complexities. Owing to a lower resolution, composite backdrop, blurring effect, color, diverse fonts, alternate textual placement among panels of photos and videos, etc., text identification is becoming complicated. This paper suggests a novel method for identifying texts from video with five stages. Initially, “video-to-frame conversion”, is done during pre-processing. Further, text region verification is performed and keyframes are recognized using CNN. Then, improved candidate text block extraction is carried out using MSER. Subsequently, “DCT features, improved distance map features, and constant gradient-based features” are extracted. These characteristics subsequently provided “Long Short-Term Memory (LSTM)” for detection. Finally, OCR is done to recognize the texts in the image. Particularly, the Self-Improved Bald Eagle Search (SI-BESO) algorithm is used to adjust the LSTM weights. Finally, the superiority of the SI-BESO-based technique over many other techniques is demonstrated.
{"title":"Optimal Classification Model for Text Detection and Recognition in Video Frames","authors":"Laxmikant Eshwarappa, G. G. Rajput","doi":"10.1142/s0219467825500147","DOIUrl":"https://doi.org/10.1142/s0219467825500147","url":null,"abstract":"Currently, the identification of text from video frames and normal scene images has got amplified awareness amongst analysts owing to its diverse challenges and complexities. Owing to a lower resolution, composite backdrop, blurring effect, color, diverse fonts, alternate textual placement among panels of photos and videos, etc., text identification is becoming complicated. This paper suggests a novel method for identifying texts from video with five stages. Initially, “video-to-frame conversion”, is done during pre-processing. Further, text region verification is performed and keyframes are recognized using CNN. Then, improved candidate text block extraction is carried out using MSER. Subsequently, “DCT features, improved distance map features, and constant gradient-based features” are extracted. These characteristics subsequently provided “Long Short-Term Memory (LSTM)” for detection. Finally, OCR is done to recognize the texts in the image. Particularly, the Self-Improved Bald Eagle Search (SI-BESO) algorithm is used to adjust the LSTM weights. Finally, the superiority of the SI-BESO-based technique over many other techniques is demonstrated.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48648435","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}
Human action recognition in videos is an important task in computer vision with applications in fields such as surveillance, human–computer interaction, and sports analysis. However, it is a challenging task due to the complex background changes and redundancy of long-term video information. In this paper, we propose a novel bi-directional long short-term memory method with attention pooling based on joint motion and difference entropy (JEAP-BiLSTM) to address these challenges. To obtain discriminative features, we introduce a joint entropy map that measures both the entropy of motion and the entropy of change. The Bi-LSTM method is then applied to capture visual and temporal associations in both forward and backward directions, enabling efficient capture of long-term temporal correlation. Furthermore, attention pooling is used to highlight the region of interest and to mitigate the effects of background changes in video information. Experiments on the UCF101 and HMDB51 datasets demonstrate that the proposed JEAP-BiLSTM method achieves recognition rates of 96.4% and 75.2%, respectively, outperforming existing methods. Our proposed method makes significant contributions to the field of human action recognition by effectively capturing both spatial and temporal patterns in videos, addressing background changes, and achieving state-of-the-art performance.
{"title":"A Jeap-BiLSTM Neural Network for Action Recognition","authors":"Lunzheng Tan, Yanfei Liu, Li-min Xia, Shangsheng Chen, Zhanben Zhou","doi":"10.1142/s0219467825500184","DOIUrl":"https://doi.org/10.1142/s0219467825500184","url":null,"abstract":"Human action recognition in videos is an important task in computer vision with applications in fields such as surveillance, human–computer interaction, and sports analysis. However, it is a challenging task due to the complex background changes and redundancy of long-term video information. In this paper, we propose a novel bi-directional long short-term memory method with attention pooling based on joint motion and difference entropy (JEAP-BiLSTM) to address these challenges. To obtain discriminative features, we introduce a joint entropy map that measures both the entropy of motion and the entropy of change. The Bi-LSTM method is then applied to capture visual and temporal associations in both forward and backward directions, enabling efficient capture of long-term temporal correlation. Furthermore, attention pooling is used to highlight the region of interest and to mitigate the effects of background changes in video information. Experiments on the UCF101 and HMDB51 datasets demonstrate that the proposed JEAP-BiLSTM method achieves recognition rates of 96.4% and 75.2%, respectively, outperforming existing methods. Our proposed method makes significant contributions to the field of human action recognition by effectively capturing both spatial and temporal patterns in videos, addressing background changes, and achieving state-of-the-art performance.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46374210","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 : 2023-08-03DOI: 10.1142/s0219467825500135
Nusrat Fatma, Pawan Singh, M. K. Siddiqui
Epilepsy is an unavoidable major persistent and critical neurological disorder that influences the human brain. Moreover, this is apparently distinguished via its recurrent malicious seizures. A seizure is a phase of synchronous, abnormal innervations of a neuron’s population which might last from seconds to a few minutes. In addition, epileptic seizures are transient occurrences of complete or partial irregular unintentional body movements that combine with consciousness loss. As epileptic seizures rarely occurred in each patient, their effects based on physical communications, social interactions, and patients’ emotions are considered, and treatment and diagnosis are undergone with crucial implications. Therefore, this survey reviews 65 research papers and states an important analysis on various machine-learning approaches adopted in each paper. The analysis of different features considered in each work is also done. This survey offers a comprehensive study on performance attainment in each contribution. Furthermore, the maximum performance attained by the works and the datasets used in each work is also examined. The analysis on features and the simulation tools used in each contribution is examined. At the end, the survey expanded with different research gaps and their problem which is beneficial to the researchers for promoting advanced future works on epileptic seizure detection.
{"title":"Survey on Epileptic Seizure Detection on Varied Machine Learning Algorithms","authors":"Nusrat Fatma, Pawan Singh, M. K. Siddiqui","doi":"10.1142/s0219467825500135","DOIUrl":"https://doi.org/10.1142/s0219467825500135","url":null,"abstract":"Epilepsy is an unavoidable major persistent and critical neurological disorder that influences the human brain. Moreover, this is apparently distinguished via its recurrent malicious seizures. A seizure is a phase of synchronous, abnormal innervations of a neuron’s population which might last from seconds to a few minutes. In addition, epileptic seizures are transient occurrences of complete or partial irregular unintentional body movements that combine with consciousness loss. As epileptic seizures rarely occurred in each patient, their effects based on physical communications, social interactions, and patients’ emotions are considered, and treatment and diagnosis are undergone with crucial implications. Therefore, this survey reviews 65 research papers and states an important analysis on various machine-learning approaches adopted in each paper. The analysis of different features considered in each work is also done. This survey offers a comprehensive study on performance attainment in each contribution. Furthermore, the maximum performance attained by the works and the datasets used in each work is also examined. The analysis on features and the simulation tools used in each contribution is examined. At the end, the survey expanded with different research gaps and their problem which is beneficial to the researchers for promoting advanced future works on epileptic seizure detection.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44591500","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 : 2023-08-03DOI: 10.1142/s0219467825500196
Kai Pan, Hongyan Chi
As an important form of expression in modern civilization art, printmaking has a rich variety of types and a prominent sense of artistic hierarchy. Therefore, printmaking is highly favored around the world due to its unique artistic characteristics. Classifying print types through image feature elements will improve people’s understanding of print creation. Convolutional neural networks (CNNs) have good application effects in the field of image classification, so CNN is used for printmaking analysis. Considering that the classification effect of the traditional convolutional neural image classification model is easily affected by the activation function, the T-ReLU activation function is introduced. By utilizing adjustable parameters to enhance the soft saturation characteristics of the model and avoid gradient vanishing, a T-ReLU convolutional model is constructed. A better convolutional image classification model is proposed based on the T-ReLU convolutional model, taking into account the issue of subpar multi-level feature fusion in deep convolutional image classification models. Utilize normalization to analyze visual input, an eleven-layer convolutional network with residual units in the convolutional layer, and cascading thinking to fuse convolutional network defects. The performance test results showed that in the data test of different styles of artificial prints, the GT-ReLU model can obtain the best image classification accuracy, and the image classification accuracy rate is 0.978. The GT-ReLU model maintains a classification accuracy above 94.4% in the multi-dataset test classification performance test, which is higher than that of other image classification models. For the use of visual processing technology in the field of classifying prints, the research content provides good reference value.
{"title":"Research on Printmaking Image Classification and Creation Based on Convolutional Neural Network","authors":"Kai Pan, Hongyan Chi","doi":"10.1142/s0219467825500196","DOIUrl":"https://doi.org/10.1142/s0219467825500196","url":null,"abstract":"As an important form of expression in modern civilization art, printmaking has a rich variety of types and a prominent sense of artistic hierarchy. Therefore, printmaking is highly favored around the world due to its unique artistic characteristics. Classifying print types through image feature elements will improve people’s understanding of print creation. Convolutional neural networks (CNNs) have good application effects in the field of image classification, so CNN is used for printmaking analysis. Considering that the classification effect of the traditional convolutional neural image classification model is easily affected by the activation function, the T-ReLU activation function is introduced. By utilizing adjustable parameters to enhance the soft saturation characteristics of the model and avoid gradient vanishing, a T-ReLU convolutional model is constructed. A better convolutional image classification model is proposed based on the T-ReLU convolutional model, taking into account the issue of subpar multi-level feature fusion in deep convolutional image classification models. Utilize normalization to analyze visual input, an eleven-layer convolutional network with residual units in the convolutional layer, and cascading thinking to fuse convolutional network defects. The performance test results showed that in the data test of different styles of artificial prints, the GT-ReLU model can obtain the best image classification accuracy, and the image classification accuracy rate is 0.978. The GT-ReLU model maintains a classification accuracy above 94.4% in the multi-dataset test classification performance test, which is higher than that of other image classification models. For the use of visual processing technology in the field of classifying prints, the research content provides good reference value.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48183056","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 : 2023-08-03DOI: 10.1142/s0219467825500159
K. Sameera, P. Swarnalatha
The development of any country is influenced by the growth in the agriculture sector. The prevalence of pests and diseases in plants affects the productivity of any agricultural product. Early diagnosis of the disease can substantially decrease the effort and the fund required for disease management. The Internet of Things (IoT) provides a framework for offering solutions for automatic farming. This paper devises an automated detection technique for foliar disease classification in apple trees using an IoT network. Here, classification is performed using a hybrid classifier, which utilizes the Deep Residual Network (DRN) and Deep [Formula: see text] Network (DQN). A new Adaptive Tunicate Swarm Sine–Cosine Algorithm (TSSCA) is used for modifying the learning parameters as well as the weights of the proposed hybrid classifier. The TSSCA is developed by adaptively changing the navigation foraging behavior of the tunicates obtained from the Tunicate Swarm Algorithm (TSA) in accordance with the Sine–Cosine Algorithm (SCA). The outputs obtained from the Adaptive TSSCA-based DRN and Adaptive TSSCA-based DQN are merged using cosine similarity measure for detecting the foliar disease. The Plant Pathology 2020 — FGVC7 dataset is utilized for the experimental process to determine accuracy, sensitivity, specificity and energy and we achieved the values of 98.36%, 98.58%, 96.32% and 0.413 J, respectively.
{"title":"Optimization with Deep Learning Classifier-Based Foliar Disease Classification in Apple Trees Using IoT Network","authors":"K. Sameera, P. Swarnalatha","doi":"10.1142/s0219467825500159","DOIUrl":"https://doi.org/10.1142/s0219467825500159","url":null,"abstract":"The development of any country is influenced by the growth in the agriculture sector. The prevalence of pests and diseases in plants affects the productivity of any agricultural product. Early diagnosis of the disease can substantially decrease the effort and the fund required for disease management. The Internet of Things (IoT) provides a framework for offering solutions for automatic farming. This paper devises an automated detection technique for foliar disease classification in apple trees using an IoT network. Here, classification is performed using a hybrid classifier, which utilizes the Deep Residual Network (DRN) and Deep [Formula: see text] Network (DQN). A new Adaptive Tunicate Swarm Sine–Cosine Algorithm (TSSCA) is used for modifying the learning parameters as well as the weights of the proposed hybrid classifier. The TSSCA is developed by adaptively changing the navigation foraging behavior of the tunicates obtained from the Tunicate Swarm Algorithm (TSA) in accordance with the Sine–Cosine Algorithm (SCA). The outputs obtained from the Adaptive TSSCA-based DRN and Adaptive TSSCA-based DQN are merged using cosine similarity measure for detecting the foliar disease. The Plant Pathology 2020 — FGVC7 dataset is utilized for the experimental process to determine accuracy, sensitivity, specificity and energy and we achieved the values of 98.36%, 98.58%, 96.32% and 0.413 J, respectively.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45955735","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 : 2023-08-03DOI: 10.1142/s0219467825500202
Yuan Liu
A product image recommendation algorithm with transformer model using deep reinforcement learning is proposed. First, the product image recommendation architecture is designed to collect users’ historical product image clicking behaviors through the log information layer. The recommendation strategy layer uses collaborative filtering algorithm to calculate users’ long-term shopping interest and gated recurrent unit to calculate users’ short-term shopping interest, and predicts users’ long-term and short-term interest output based on users’ positive and negative feedback sequences. Second, the prediction results are fed into the transformer model for content planning to make the data format more suitable for subsequent content recommendation. Finally, the planning results of the transformer model are input to Deep Q-Leaning Network to obtain product image recommendation sequences under the learning of this network, and the results are transmitted to the data result layer, and finally presented to users through the presentation layer. The results show that the recommendation results of the proposed algorithm are consistent with the user’s browsing records. The average accuracy of product image recommendation is 97.1%, the maximum recommended time is 1.0[Formula: see text]s, the coverage and satisfaction are high, and the practical application effect is good. It can recommend more suitable products for users and promote the further development of e-commerce.
{"title":"Product Image Recommendation with Transformer Model Using Deep Reinforcement Learning","authors":"Yuan Liu","doi":"10.1142/s0219467825500202","DOIUrl":"https://doi.org/10.1142/s0219467825500202","url":null,"abstract":"A product image recommendation algorithm with transformer model using deep reinforcement learning is proposed. First, the product image recommendation architecture is designed to collect users’ historical product image clicking behaviors through the log information layer. The recommendation strategy layer uses collaborative filtering algorithm to calculate users’ long-term shopping interest and gated recurrent unit to calculate users’ short-term shopping interest, and predicts users’ long-term and short-term interest output based on users’ positive and negative feedback sequences. Second, the prediction results are fed into the transformer model for content planning to make the data format more suitable for subsequent content recommendation. Finally, the planning results of the transformer model are input to Deep Q-Leaning Network to obtain product image recommendation sequences under the learning of this network, and the results are transmitted to the data result layer, and finally presented to users through the presentation layer. The results show that the recommendation results of the proposed algorithm are consistent with the user’s browsing records. The average accuracy of product image recommendation is 97.1%, the maximum recommended time is 1.0[Formula: see text]s, the coverage and satisfaction are high, and the practical application effect is good. It can recommend more suitable products for users and promote the further development of e-commerce.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43365571","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 : 2023-08-03DOI: 10.1142/s0219467825500123
Padmanayana Bhat, B. Anoop
The eye-related problem of diabetes is called diabetic retinopathy (DR), which is the main factor contributing to visual loss. This research develops an enhanced deep model for DR classification. Here, deep convolutional neural network (Deep CNN) is trained with the improved invasive weed social ski-driver optimization (IISSDO), which is generated by fusing improved invasive weed optimization (IIWO) and social ski-driver (SSD). The IISSDO-based Deep CNN classifies DR severity into normal, mild, non-proliferative DR (NPDR), moderate NPDR, severe NPDR, and proliferative. Initially, a type 2 fuzzy and cuckoo search (T2FCS) filter performs pre-processing and the quality of the data is improved by data augmentation. The lesion is then divided using DeepJoint segmentation. Then, the Deep CNN determines the DR. The analysis uses the Indian DR image database. The IISSDO-based Deep CNN has the highest accuracy, sensitivity, and specificity of 96.566%, 96.773%, and 96.517%, respectively.
{"title":"Improved Invasive Weed Social Ski-Driver Optimization-Based Deep Convolution Neural Network for Diabetic Retinopathy Classification","authors":"Padmanayana Bhat, B. Anoop","doi":"10.1142/s0219467825500123","DOIUrl":"https://doi.org/10.1142/s0219467825500123","url":null,"abstract":"The eye-related problem of diabetes is called diabetic retinopathy (DR), which is the main factor contributing to visual loss. This research develops an enhanced deep model for DR classification. Here, deep convolutional neural network (Deep CNN) is trained with the improved invasive weed social ski-driver optimization (IISSDO), which is generated by fusing improved invasive weed optimization (IIWO) and social ski-driver (SSD). The IISSDO-based Deep CNN classifies DR severity into normal, mild, non-proliferative DR (NPDR), moderate NPDR, severe NPDR, and proliferative. Initially, a type 2 fuzzy and cuckoo search (T2FCS) filter performs pre-processing and the quality of the data is improved by data augmentation. The lesion is then divided using DeepJoint segmentation. Then, the Deep CNN determines the DR. The analysis uses the Indian DR image database. The IISSDO-based Deep CNN has the highest accuracy, sensitivity, and specificity of 96.566%, 96.773%, and 96.517%, respectively.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41622319","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 : 2023-07-28DOI: 10.1142/s0219467825500172
Pramod M. Bachiphale, N. Zulpe
Problem: Digital devices are becoming increasingly powerful and smart, which is improving quality of life, but presents new challenges to privacy protection. Visual cryptographic schemes provide data sharing privacy, but have drawbacks such as extra storage space, lossy secret images, and the need to store permutation keys. Aim: This paper proposes a light-weight visual sign-cryptography scheme based on optimal key generation to address the disadvantages of existing visual cryptographic schemes and improve the security, sharing quality, and time consumption of multisecret images. Methods: The proposed light-weight visual sign-cryptography (LW-VSC) scheme consists of three processes: band separation, shares generation, and signcryption/un-signcryption. The process of separation and shares generation is done by an existing method. The multiple shares of the secret images are then encrypted/decrypted using light-weight sign-cryptography. The proposed scheme uses a novel harpy eagle search optimization (HESO) algorithm to generate optimal keys for both the encrypt/decrypt processes. Results: Simulation results and comparative analysis showed the proposed scheme is more secure and requires less storage space, with faster encryption/decryption and improved key generation quality. Conclusion: The proposed light-weight visual sign-cryptography scheme based on optimal key generation is a promising approach to enhance security and improve data sharing quality. The HESO algorithm shows promise in improving the quality of key generation, providing better privacy protection in the face of increasingly powerful digital devices.
{"title":"Optimal Multisecret Image Sharing Using Lightweight Visual Sign-Cryptography Scheme With Optimal Key Generation for Gray/Color Images","authors":"Pramod M. Bachiphale, N. Zulpe","doi":"10.1142/s0219467825500172","DOIUrl":"https://doi.org/10.1142/s0219467825500172","url":null,"abstract":"Problem: Digital devices are becoming increasingly powerful and smart, which is improving quality of life, but presents new challenges to privacy protection. Visual cryptographic schemes provide data sharing privacy, but have drawbacks such as extra storage space, lossy secret images, and the need to store permutation keys. Aim: This paper proposes a light-weight visual sign-cryptography scheme based on optimal key generation to address the disadvantages of existing visual cryptographic schemes and improve the security, sharing quality, and time consumption of multisecret images. Methods: The proposed light-weight visual sign-cryptography (LW-VSC) scheme consists of three processes: band separation, shares generation, and signcryption/un-signcryption. The process of separation and shares generation is done by an existing method. The multiple shares of the secret images are then encrypted/decrypted using light-weight sign-cryptography. The proposed scheme uses a novel harpy eagle search optimization (HESO) algorithm to generate optimal keys for both the encrypt/decrypt processes. Results: Simulation results and comparative analysis showed the proposed scheme is more secure and requires less storage space, with faster encryption/decryption and improved key generation quality. Conclusion: The proposed light-weight visual sign-cryptography scheme based on optimal key generation is a promising approach to enhance security and improve data sharing quality. The HESO algorithm shows promise in improving the quality of key generation, providing better privacy protection in the face of increasingly powerful digital devices.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45471841","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 : 2023-07-27DOI: 10.1142/s0219467825500160
Li Fang, Wang Xianghai
In recent years, image denoising methods based on total variational regularization have attracted extensive attention. However, the traditional total variational regularization method is an approximate solution based on convex method, and does not consider the particularity of the region with rich details. In this paper, the adaptive total-variation and nonconvex low-rank model for image denoising is proposed, which is a hybrid regularization model. First, the image is decomposed into sparse terms and low rank terms, and then the total variational regularization is used to denoise. At the same time, an adaptive coefficient based on gradient is constructed to adaptively judge the flat area and detail texture area, slow down the denoising intensity of detail area, and then play the role of preserving detail information. Finally, by constructing a nonconvex function, the optimal solution of the function is obtained by using the alternating minimization method. This method not only effectively removes the image noise, but also retains the detailed information of the image. The experimental results show the effectiveness of the proposed model, and SNR and SSIM of the denoised image are improved.
{"title":"Adaptive Total-Variation and Nonconvex Low-Rank Model for Image Denoising","authors":"Li Fang, Wang Xianghai","doi":"10.1142/s0219467825500160","DOIUrl":"https://doi.org/10.1142/s0219467825500160","url":null,"abstract":"In recent years, image denoising methods based on total variational regularization have attracted extensive attention. However, the traditional total variational regularization method is an approximate solution based on convex method, and does not consider the particularity of the region with rich details. In this paper, the adaptive total-variation and nonconvex low-rank model for image denoising is proposed, which is a hybrid regularization model. First, the image is decomposed into sparse terms and low rank terms, and then the total variational regularization is used to denoise. At the same time, an adaptive coefficient based on gradient is constructed to adaptively judge the flat area and detail texture area, slow down the denoising intensity of detail area, and then play the role of preserving detail information. Finally, by constructing a nonconvex function, the optimal solution of the function is obtained by using the alternating minimization method. This method not only effectively removes the image noise, but also retains the detailed information of the image. The experimental results show the effectiveness of the proposed model, and SNR and SSIM of the denoised image are improved.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44839070","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：