Proteins are critical for lives. They not only build 10%-35% of our body tissues, but also can be used to understand the structures of different viruses, and then help us to explore effective vaccines. Hence, predicting new protein structures is very important for human health. However, the structure of protein is complicated. Exploration using human experiments is cost-consuming. Recently, artificial intelligence (AI) technology, such as imitation learning and reinforcement learning (RL), has been rapidly developed and significantly improved the efficiency in many different domains. In this project, we will try to use RL to solve the protein folding structure prediction problem. First, we adopted the PH structure as a relatively simple representation of the protein structure, where different peptides can be categorized into two types: P(hydrophilic) and H(hydrophobic). The goal of the protein folding is to try to make more H pairs during the folding process. We then formulated the protein folding problem as a reinforcement learning process. If a new H pair is generated during folding, we collect -1 reward. Such RL reward is designed based on the protein dataset (Protein Data Bank). Finally, we implemented three RL algorithms: 1) Q-learning, 2) Deep Q-learning, and 3) Double Deep Q-learning (DDQN). We implemented and compared the three algorithms in terms of their accuracy and efficiency. We found that all three algorithms can accurately predict the structures of simple proteins. As protein structures become more complicated, the DDQN is performing better.
{"title":"Protein Folding Structure Prediction using Reinforcement Learning with Application to Both 2D and 3D Environments","authors":"Jason Lu","doi":"10.1145/3569966.3570102","DOIUrl":"https://doi.org/10.1145/3569966.3570102","url":null,"abstract":"Proteins are critical for lives. They not only build 10%-35% of our body tissues, but also can be used to understand the structures of different viruses, and then help us to explore effective vaccines. Hence, predicting new protein structures is very important for human health. However, the structure of protein is complicated. Exploration using human experiments is cost-consuming. Recently, artificial intelligence (AI) technology, such as imitation learning and reinforcement learning (RL), has been rapidly developed and significantly improved the efficiency in many different domains. In this project, we will try to use RL to solve the protein folding structure prediction problem. First, we adopted the PH structure as a relatively simple representation of the protein structure, where different peptides can be categorized into two types: P(hydrophilic) and H(hydrophobic). The goal of the protein folding is to try to make more H pairs during the folding process. We then formulated the protein folding problem as a reinforcement learning process. If a new H pair is generated during folding, we collect -1 reward. Such RL reward is designed based on the protein dataset (Protein Data Bank). Finally, we implemented three RL algorithms: 1) Q-learning, 2) Deep Q-learning, and 3) Double Deep Q-learning (DDQN). We implemented and compared the three algorithms in terms of their accuracy and efficiency. We found that all three algorithms can accurately predict the structures of simple proteins. As protein structures become more complicated, the DDQN is performing better.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127179506","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}
Zuchuang Zheng, Shanliang Xue, Meijiao Xu, Mao-sheng Li, Ruxue Ma
Software testing is an important means to ensure software quality. The quality and efficiency of software testing can be greatly improved by modeled software testing. Software test maturity model (TMM) is a reference model to guide software organizations to improve test maturity. However, there is a lack of guidance on software testing objectives and process improvement, which leads to poor enforceability and low execution efficiency. To solve the above problems, based on the maturity objectives and content of the five test levels of the TMM model, an improved software testing V model (RAD) is proposed, and a software quality evaluation method is proposed for the improved RAD model.
{"title":"Software quality evaluation based on improved RAD model and AHP","authors":"Zuchuang Zheng, Shanliang Xue, Meijiao Xu, Mao-sheng Li, Ruxue Ma","doi":"10.1145/3569966.3570036","DOIUrl":"https://doi.org/10.1145/3569966.3570036","url":null,"abstract":"Software testing is an important means to ensure software quality. The quality and efficiency of software testing can be greatly improved by modeled software testing. Software test maturity model (TMM) is a reference model to guide software organizations to improve test maturity. However, there is a lack of guidance on software testing objectives and process improvement, which leads to poor enforceability and low execution efficiency. To solve the above problems, based on the maturity objectives and content of the five test levels of the TMM model, an improved software testing V model (RAD) is proposed, and a software quality evaluation method is proposed for the improved RAD model.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126753240","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}
During printing and shooting, the degradation of printing micro dots significantly affects the decoding and reading of hidden anti-counterfeiting information. However, existing image restoration methods cannot effectively restore image information. Moreover, there are relatively few datasets related to halftone dot images, and most datasets differ from the real data. Therefore, we propose an end-to-end restoration model based on the single-image super-resolution information. Specifically, we constructed a PMD dataset for real printing of anti-counterfeiting scenes. Based on this dataset, we used the high-resolution image information as the target. The positional inclination of the degraded images is corrected using the blank and interline characteristics of the printing micro dots images. The restoration is completed with the help of feature extraction and upsample of ESRGAN. In addition, we propose evaluation measures suitable for error detection, correction, and decoding requirements for microscopic image information. The experimental results show that, within the noise tolerance range, the image information restored by our method has a maximum average bit error rate is 0.97% and a Euclidean distance is 0.00804 pixels, whereas traditional filtering measures cannot effectively restore image information. The experimental results verified the effectiveness and robustness of the proposed method.
{"title":"Research on Image Information Restoration Algorithm of Printing Micro Dots Based on GAN","authors":"Bo Yuan, Peng Cao","doi":"10.1145/3569966.3571169","DOIUrl":"https://doi.org/10.1145/3569966.3571169","url":null,"abstract":"During printing and shooting, the degradation of printing micro dots significantly affects the decoding and reading of hidden anti-counterfeiting information. However, existing image restoration methods cannot effectively restore image information. Moreover, there are relatively few datasets related to halftone dot images, and most datasets differ from the real data. Therefore, we propose an end-to-end restoration model based on the single-image super-resolution information. Specifically, we constructed a PMD dataset for real printing of anti-counterfeiting scenes. Based on this dataset, we used the high-resolution image information as the target. The positional inclination of the degraded images is corrected using the blank and interline characteristics of the printing micro dots images. The restoration is completed with the help of feature extraction and upsample of ESRGAN. In addition, we propose evaluation measures suitable for error detection, correction, and decoding requirements for microscopic image information. The experimental results show that, within the noise tolerance range, the image information restored by our method has a maximum average bit error rate is 0.97% and a Euclidean distance is 0.00804 pixels, whereas traditional filtering measures cannot effectively restore image information. The experimental results verified the effectiveness and robustness of the proposed method.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114948762","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}
Software test case selection is committed to select the fewest test cases from test suites to perform a complete test at the least cost. Machine learning and multi-objective optimization techniques have developed rapidly in recent years, and they have been successfully applied to test case selection. In this paper, we present a method called DB-NSGA2, which uses the density clustering algorithm in machine learning combined with the non-dominated ranking algorithm (NSGA2) for test case selection, which can better select the test cases required for testing. In particular, we apply some of the clustering results generated by the clustering algorithm to the crossover and mutation operations of the NSGA2 to improve diversity progeny populations and ensure the transmission of good individuals. Extensive experiments show that the test cases selected by our method can produce a better set of Pareto solutions and can detect more faults at a lower cost than other methods.
{"title":"Multi-objective software test case selection based on density analysis","authors":"Huihui Jia, Cheng Zhang, Sijie Wu","doi":"10.1145/3569966.3570010","DOIUrl":"https://doi.org/10.1145/3569966.3570010","url":null,"abstract":"Software test case selection is committed to select the fewest test cases from test suites to perform a complete test at the least cost. Machine learning and multi-objective optimization techniques have developed rapidly in recent years, and they have been successfully applied to test case selection. In this paper, we present a method called DB-NSGA2, which uses the density clustering algorithm in machine learning combined with the non-dominated ranking algorithm (NSGA2) for test case selection, which can better select the test cases required for testing. In particular, we apply some of the clustering results generated by the clustering algorithm to the crossover and mutation operations of the NSGA2 to improve diversity progeny populations and ensure the transmission of good individuals. Extensive experiments show that the test cases selected by our method can produce a better set of Pareto solutions and can detect more faults at a lower cost than other methods.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128648292","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}
With the development of cloud computing and cloud storage technology, the data scale has grown rapidly. In order to store and process large-scale data, there are thousands of nodes and devices in the cloud storage center, resulting in a surge in the frequency of failures. In various types of failure events, storage device failure is the most important one. However, most cloud storage systems lack disk failure prediction mechanisms and could only replace disks after disk failures. It is particularly important to predict the potential risks in the system operation environment. In this paper, we propose a disk failure prediction approach that supports multi granularity data fusion, which solves problems of unbalanced samples, single data source, cross scenario model migration and insufficient generalization ability of prediction models in disk failure prediction. Through our proposed approach, the cloud storage system could accurately predict disk failures and actively push prediction results to users, so as to improve the pertinence and planning of the operation and maintenance work. The approach presented in this paper has been validated to be valid through a series of qualitative and quantitative experiments.
{"title":"A Failure Prediction Approach Supporting Multi Granularity Data Fusion for Large-scale Cloud Storage Systems","authors":"Yongyang Cheng, T. Zhang, Jing Luo","doi":"10.1145/3569966.3570119","DOIUrl":"https://doi.org/10.1145/3569966.3570119","url":null,"abstract":"With the development of cloud computing and cloud storage technology, the data scale has grown rapidly. In order to store and process large-scale data, there are thousands of nodes and devices in the cloud storage center, resulting in a surge in the frequency of failures. In various types of failure events, storage device failure is the most important one. However, most cloud storage systems lack disk failure prediction mechanisms and could only replace disks after disk failures. It is particularly important to predict the potential risks in the system operation environment. In this paper, we propose a disk failure prediction approach that supports multi granularity data fusion, which solves problems of unbalanced samples, single data source, cross scenario model migration and insufficient generalization ability of prediction models in disk failure prediction. Through our proposed approach, the cloud storage system could accurately predict disk failures and actively push prediction results to users, so as to improve the pertinence and planning of the operation and maintenance work. The approach presented in this paper has been validated to be valid through a series of qualitative and quantitative experiments.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129641877","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}
Reactor primary circuit system is a complex dynamic system, variable parameter coupling, operation safety problems are prominent. In order to reduce the risk, a multi-source information fusion diagnosis system based on signed directed graph (SDG) and particle swarm optimization BP neural network (PSO-BP) is proposed. Utilizing D-S evidence theory for neural network diagnostic information fusion, logic inference combining SDG model, to determine potential failure. Simulation test shows that the intelligent diagnosis model could estimate the faults effectively, and provides the fault alarm transmission path.
{"title":"Research on Fault Diagnosis Method for Reactor Primary Circuit System Based on multi-source information fusion","authors":"Jie Ma, Zhuang Han, Qiao Peng","doi":"10.1145/3569966.3570079","DOIUrl":"https://doi.org/10.1145/3569966.3570079","url":null,"abstract":"Reactor primary circuit system is a complex dynamic system, variable parameter coupling, operation safety problems are prominent. In order to reduce the risk, a multi-source information fusion diagnosis system based on signed directed graph (SDG) and particle swarm optimization BP neural network (PSO-BP) is proposed. Utilizing D-S evidence theory for neural network diagnostic information fusion, logic inference combining SDG model, to determine potential failure. Simulation test shows that the intelligent diagnosis model could estimate the faults effectively, and provides the fault alarm transmission path.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127136964","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}
Abstract—With the development of vehicles and traffic system in the early 21st century, the need for a monitored traffic system and vehicle classification is enlarging. Together with the development of deep learning, computer vision realm has emerged versatile models that is able to fulfill the need of classification. Those popular models include CNN, Vision Trans- former, Metaformer and so on. However, these models handle the problem based on different data processing techniques, they either lacks efficiency or effectiveness. In particular, CNN is shortcoming in global data while ViT is lack of extraction of local information. Therefore, based on this research gap, we proposed a model called MetaCNN, which combines CNN and Poolformer – a specific metaformer structure, which takes the strength of the two models and compensate for both models’ deficiencies. Finally, in order to verify the feasibility of our model, we tested our model on a real-world remote sensing datasets of vehicle images in six different regions with different weather conditions. Our model MetaCNN has demonstrated better recognition performance compared to other baseline models. The results further prove that our model MetaCNN is adept at vehicle classification of remote sensing images though under complex scenarios
{"title":"MetaCNN: A New Hybrid Deep Learning Image-based Approach for Vehicle Classification Using Transformer-like Framework","authors":"Juntian Chen, Ruikang Luo","doi":"10.1145/3569966.3570099","DOIUrl":"https://doi.org/10.1145/3569966.3570099","url":null,"abstract":"Abstract—With the development of vehicles and traffic system in the early 21st century, the need for a monitored traffic system and vehicle classification is enlarging. Together with the development of deep learning, computer vision realm has emerged versatile models that is able to fulfill the need of classification. Those popular models include CNN, Vision Trans- former, Metaformer and so on. However, these models handle the problem based on different data processing techniques, they either lacks efficiency or effectiveness. In particular, CNN is shortcoming in global data while ViT is lack of extraction of local information. Therefore, based on this research gap, we proposed a model called MetaCNN, which combines CNN and Poolformer – a specific metaformer structure, which takes the strength of the two models and compensate for both models’ deficiencies. Finally, in order to verify the feasibility of our model, we tested our model on a real-world remote sensing datasets of vehicle images in six different regions with different weather conditions. Our model MetaCNN has demonstrated better recognition performance compared to other baseline models. The results further prove that our model MetaCNN is adept at vehicle classification of remote sensing images though under complex scenarios","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115931653","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}
Shaopeng Yang, Tiancheng Zhang, Siyuan Mao, Gensitskiy Yu., Yiming Sun
With the deep integration of artificial intelligence technology and education, the traditional educational pattern has changed hugely. And the adaptive learning based on automatically tracing the knowledge status of students at various stages has attracted much attention. As a key technology, knowledge tracing has become an important research. Although deep learning has been used in knowledge tracing and promoted certain performance improvement, it still has drawbacks. First, current researches consider less the explicit representation of meta path between users, exercise items and knowledge points, ignoring some of the higher-order information. Secondly, the effect of higher-order information of knowledge points on prediction is ignored. Therefore, we proposes a meta-path based four-way co-attention mechanism model MAKT to inversely infer the unobservable knowledge cognitive proficiency of learners. Based on meta path, the MAKT model integrates instance information and higher-order information between nodes to effectively enhance the representation of user, exercise item and knowledge points. The effectiveness of the model was demonstrated in tests on a real data set.
{"title":"MAKT: A Knowledge Tracing Model Based on Meta Path and Attention Mechanism","authors":"Shaopeng Yang, Tiancheng Zhang, Siyuan Mao, Gensitskiy Yu., Yiming Sun","doi":"10.1145/3569966.3569987","DOIUrl":"https://doi.org/10.1145/3569966.3569987","url":null,"abstract":"With the deep integration of artificial intelligence technology and education, the traditional educational pattern has changed hugely. And the adaptive learning based on automatically tracing the knowledge status of students at various stages has attracted much attention. As a key technology, knowledge tracing has become an important research. Although deep learning has been used in knowledge tracing and promoted certain performance improvement, it still has drawbacks. First, current researches consider less the explicit representation of meta path between users, exercise items and knowledge points, ignoring some of the higher-order information. Secondly, the effect of higher-order information of knowledge points on prediction is ignored. Therefore, we proposes a meta-path based four-way co-attention mechanism model MAKT to inversely infer the unobservable knowledge cognitive proficiency of learners. Based on meta path, the MAKT model integrates instance information and higher-order information between nodes to effectively enhance the representation of user, exercise item and knowledge points. The effectiveness of the model was demonstrated in tests on a real data set.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124506611","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}
Yaqun Wang, Di Sun, Lei Liu, Luan Ye, Kaidi Fu, Xinyu Jin
Yolo has achieved great success in the field of image segmentation, and has been applied to infrared thermal imaging detection. However, in the feature pyramid for feature fusion, high-level spatial feature information is lost, and both high-level and low-level features have poor semantics. This paper proposes an infrared thermal imaging cervical spine part extraction method based on improved Yolo v3. In order to make up for the channel information lost in feature fusion, this paper convolves the high-level features, and then enhances the residual features to reduce the semantic loss caused by the number of channels by compensating for the spatial context information. To reduce the semantic gap of additive fusion, this paper applies an attention mechanism on low-level features. The improved Yolo v3 algorithm was used to extract the cervical vertebrae in infrared thermal images, and comparative experiments were completed. Experiments on the dataset collected in the cooperative hospital demonstrate that our proposed improved Yolo v3 achieves better performance.
{"title":"Detection of cervical vertebrae from infrared thermal imaging based on improved Yolo v3","authors":"Yaqun Wang, Di Sun, Lei Liu, Luan Ye, Kaidi Fu, Xinyu Jin","doi":"10.1145/3569966.3570059","DOIUrl":"https://doi.org/10.1145/3569966.3570059","url":null,"abstract":"Yolo has achieved great success in the field of image segmentation, and has been applied to infrared thermal imaging detection. However, in the feature pyramid for feature fusion, high-level spatial feature information is lost, and both high-level and low-level features have poor semantics. This paper proposes an infrared thermal imaging cervical spine part extraction method based on improved Yolo v3. In order to make up for the channel information lost in feature fusion, this paper convolves the high-level features, and then enhances the residual features to reduce the semantic loss caused by the number of channels by compensating for the spatial context information. To reduce the semantic gap of additive fusion, this paper applies an attention mechanism on low-level features. The improved Yolo v3 algorithm was used to extract the cervical vertebrae in infrared thermal images, and comparative experiments were completed. Experiments on the dataset collected in the cooperative hospital demonstrate that our proposed improved Yolo v3 achieves better performance.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125960194","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}
Noise reduction is one of the most exciting problems in speckle pattern. We present an Image Enhancement Filtering Algorithm on experimental speckle correlation fringes and speckle image of cone respectively. In the algorithm, adaptively automatic threshold and gradient of the detecting pixel is calculated according to the mean value of the 3 × 3 area pixels around the detecting pixel and the human vision system. The results show that this technique is capable of significantly improving the quality patterns and enhancing the contrast with the edge of the speckle image, as well as preserving more detailed information of the cone.
{"title":"An Image Enhancement Filtering Algorithm for Speckle Patterns","authors":"Boyuan Yao, Ying Wu","doi":"10.1145/3569966.3570043","DOIUrl":"https://doi.org/10.1145/3569966.3570043","url":null,"abstract":"Noise reduction is one of the most exciting problems in speckle pattern. We present an Image Enhancement Filtering Algorithm on experimental speckle correlation fringes and speckle image of cone respectively. In the algorithm, adaptively automatic threshold and gradient of the detecting pixel is calculated according to the mean value of the 3 × 3 area pixels around the detecting pixel and the human vision system. The results show that this technique is capable of significantly improving the quality patterns and enhancing the contrast with the edge of the speckle image, as well as preserving more detailed information of the cone.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129892689","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：