Pub Date : 2021-12-17DOI: 10.1109/PIC53636.2021.9687036
Qianhan Wx, Qian Huan, Xing Ll
More and more attention has been focused on the human action recognition domain. The existing methods are mostly based on single-mode data. However, single-mode data lacks adequate information. So, it is necessary to propose methods based on multimode data. In this paper, we extract two kinds of features from depth videos and skeleton sequences, named STDMI-HOG and STjoint feature respectively. STDMI-HOG is extracted from a new depth feature map Spatial-Temporal Depth Motion Image by Histogram of Oriented Gradient. STjoint feature is extracted from skeleton sequences by ST-GCN extractor. Then two kinds of features are connected to make up a one-dimensional vector. Finally, SVM classifies the actions according to the feature vector. To evaluate the performance, several experiments are conducted on two public datasets: the MSR Action3D dataset and the UTD-MHAD dataset. The accuracy of our method on two datasets is compared with the existing methods, and the experiments prove the outperformance of our method.
{"title":"Human Action Recognition Based on STDMI-HOG and STjoint Feature","authors":"Qianhan Wx, Qian Huan, Xing Ll","doi":"10.1109/PIC53636.2021.9687036","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687036","url":null,"abstract":"More and more attention has been focused on the human action recognition domain. The existing methods are mostly based on single-mode data. However, single-mode data lacks adequate information. So, it is necessary to propose methods based on multimode data. In this paper, we extract two kinds of features from depth videos and skeleton sequences, named STDMI-HOG and STjoint feature respectively. STDMI-HOG is extracted from a new depth feature map Spatial-Temporal Depth Motion Image by Histogram of Oriented Gradient. STjoint feature is extracted from skeleton sequences by ST-GCN extractor. Then two kinds of features are connected to make up a one-dimensional vector. Finally, SVM classifies the actions according to the feature vector. To evaluate the performance, several experiments are conducted on two public datasets: the MSR Action3D dataset and the UTD-MHAD dataset. The accuracy of our method on two datasets is compared with the existing methods, and the experiments prove the outperformance of our method.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"65 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132942574","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687050
Rui Zhan, Yi Ma, Shanshan Yang, Yufei Man, Yu Yang
Digital image steganalysis technology based on deep learning has made rapid development. The latest technology, SFNet based on fractal technology, exceeds the cutting-edge technology SRNet in performance. The disadvantage is that SFNet is not suitable for JPEG steganalysis. Due to the interference of compression noise in JPEG images, it is difficult for SFNet to extract weak stego signal by self-similarity extended network. In this paper, a JPEG steganalysis method based on fractal residual network, called FRNet, is proposed. This paper introduces the residual unit with a shortcut connection into the fractal structure, which helps the network effectively suppress the image content and generate the residual image with stego noise. Then, referring to the bottleneck block of ResNet, the deep feature extraction module is constructed to downsample the feature map and superimpose the weak stego signal between different channels of the convolution layer. Finally, the fractal residual module and depth feature extraction module are used to control the width and depth of the network to maximize the detection performance. Two adaptive steganography algorithms of J-UNIWARD and UERD are chosen to evaluate the performance. Experimental results show that the detection error of FRNet is 11.52% lower than J-XuNet, 10.12% lower than WangNet, and 2.54% lower than SRNet.
{"title":"An Advanced JPEG Steganalysis Method with Balanced Depth and Width Based on Fractal Residual Network","authors":"Rui Zhan, Yi Ma, Shanshan Yang, Yufei Man, Yu Yang","doi":"10.1109/PIC53636.2021.9687050","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687050","url":null,"abstract":"Digital image steganalysis technology based on deep learning has made rapid development. The latest technology, SFNet based on fractal technology, exceeds the cutting-edge technology SRNet in performance. The disadvantage is that SFNet is not suitable for JPEG steganalysis. Due to the interference of compression noise in JPEG images, it is difficult for SFNet to extract weak stego signal by self-similarity extended network. In this paper, a JPEG steganalysis method based on fractal residual network, called FRNet, is proposed. This paper introduces the residual unit with a shortcut connection into the fractal structure, which helps the network effectively suppress the image content and generate the residual image with stego noise. Then, referring to the bottleneck block of ResNet, the deep feature extraction module is constructed to downsample the feature map and superimpose the weak stego signal between different channels of the convolution layer. Finally, the fractal residual module and depth feature extraction module are used to control the width and depth of the network to maximize the detection performance. Two adaptive steganography algorithms of J-UNIWARD and UERD are chosen to evaluate the performance. Experimental results show that the detection error of FRNet is 11.52% lower than J-XuNet, 10.12% lower than WangNet, and 2.54% lower than SRNet.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134593582","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687040
Yanping Ji, Wensi Wang, Wang Chen, Liting Zhang, Mengyu Yang, Xiaowen Wang
Large and complex buildings built in China in recent years, such as Olympic venues, airports, and large hospitals, have brought new fire evacuation problems. Many designs are using Internet of Things (IoT) technology to enhance buildings’ perception of flames and smoke. In this paper, in addition to using IoT to improve the fire-awareness of buildings, a set of algorithms based on the Dijkstra’s shortest path method is designed to operate on the local FPGA edge computing terminal to determine the current optimal evacuation path. An IoT system with an evacuation lighting system provides an optimal route indication for people in the building. Compared with the traditional Internet of Things and cloud computing technology, this design uses FPGA near the data terminal to process and analyze the collected data in real time, which effectively improves the speed of data response and Reduced bandwidth congestion caused by massive data. Reduced power consumption of IoT. The system was tested in the office building of Beijing University of Technology, which can effectively indicate the path under different fire conditions. In the event of a fire, the evacuation algorithm can be updated every 10 seconds, and the emergency lights are updated every 5 seconds and indicate an emergency route.
{"title":"Dijkstra Algorithm Based Building Evacuation Edge Computing and IoT System Design and Implementation","authors":"Yanping Ji, Wensi Wang, Wang Chen, Liting Zhang, Mengyu Yang, Xiaowen Wang","doi":"10.1109/PIC53636.2021.9687040","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687040","url":null,"abstract":"Large and complex buildings built in China in recent years, such as Olympic venues, airports, and large hospitals, have brought new fire evacuation problems. Many designs are using Internet of Things (IoT) technology to enhance buildings’ perception of flames and smoke. In this paper, in addition to using IoT to improve the fire-awareness of buildings, a set of algorithms based on the Dijkstra’s shortest path method is designed to operate on the local FPGA edge computing terminal to determine the current optimal evacuation path. An IoT system with an evacuation lighting system provides an optimal route indication for people in the building. Compared with the traditional Internet of Things and cloud computing technology, this design uses FPGA near the data terminal to process and analyze the collected data in real time, which effectively improves the speed of data response and Reduced bandwidth congestion caused by massive data. Reduced power consumption of IoT. The system was tested in the office building of Beijing University of Technology, which can effectively indicate the path under different fire conditions. In the event of a fire, the evacuation algorithm can be updated every 10 seconds, and the emergency lights are updated every 5 seconds and indicate an emergency route.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132079859","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687024
George Manias, Argyro Mavrogiorgou, Athanasios Kiourtis, Dimitris Kakomitas, D. Kyriazis
The tremendous growth, popularity, and usage of social media in modern societies has led to the production of an enormous real-time volume of social texts and posts, including Tweets that are being produced by users. These collections of social data can be potentially useful, but the extent of meaningful data in these collections is still of high research and business interest. One of the main elements in several application domains, such as policy making, addresses the scope of identifying and categorizing these texts into natural groups based on the topics to which they refer to, in order to better understand and correlate them. The latter is recently realized through the utilization of Topic Modeling and Identification tasks, for identifying and extracting subjective information and topics from raw texts with the ultimate objective to enhance the categorization of them. This paper introduces an end-to-end pipeline that primarily focuses on the phases of the collection, text preprocessing, as well as utilization of Natural Language Processing and Topic Modeling models, which are considered to be of major importance for the successful Topic Modeling and Identification of Tweets and the final interpretation of them.
{"title":"Real-Time Kafka-Based Topic Modeling and Identification of Tweets","authors":"George Manias, Argyro Mavrogiorgou, Athanasios Kiourtis, Dimitris Kakomitas, D. Kyriazis","doi":"10.1109/PIC53636.2021.9687024","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687024","url":null,"abstract":"The tremendous growth, popularity, and usage of social media in modern societies has led to the production of an enormous real-time volume of social texts and posts, including Tweets that are being produced by users. These collections of social data can be potentially useful, but the extent of meaningful data in these collections is still of high research and business interest. One of the main elements in several application domains, such as policy making, addresses the scope of identifying and categorizing these texts into natural groups based on the topics to which they refer to, in order to better understand and correlate them. The latter is recently realized through the utilization of Topic Modeling and Identification tasks, for identifying and extracting subjective information and topics from raw texts with the ultimate objective to enhance the categorization of them. This paper introduces an end-to-end pipeline that primarily focuses on the phases of the collection, text preprocessing, as well as utilization of Natural Language Processing and Topic Modeling models, which are considered to be of major importance for the successful Topic Modeling and Identification of Tweets and the final interpretation of them.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132620564","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687077
Mika Iitti, J. Grönman, J. Turunen, T. Lipping
This paper presents a case study - developing a computer-based classification framework to classify masonry bricks into three quality categories - carried out as a part of the Robocoast R&D Center project. The project aims at better collaboration between universities and industry by establishing an innovation platform where companies can bring their challenges to be addressed together with university experts. The project also promotes collaboration between universities being a part of the RoboAI Competence Centre - a joint research and innovation platform of Satakunta University of Applied Sciences (SAMK) and Tampere University, Pori unit. Automatic classification of bricks is important as it is foreseen that a robotic arm, powered by an automatic classifier, could replace the heavy and tedious work currently performed by humans in brick factories. A convolutional neural network-based solution, using a pretrained VGG-16 deep learning architecture, is proposed. Overall accuracy of 88 % was obtained when considering all three quality classes. When only discarding class 3 bricks, i.e., those that are not suitable for any construction work, the accuracy was 93 %.
{"title":"Classification of Masonry Bricks Using Convolutional Neural Networks – a Case Study in a University-Industry Collaboration Project","authors":"Mika Iitti, J. Grönman, J. Turunen, T. Lipping","doi":"10.1109/PIC53636.2021.9687077","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687077","url":null,"abstract":"This paper presents a case study - developing a computer-based classification framework to classify masonry bricks into three quality categories - carried out as a part of the Robocoast R&D Center project. The project aims at better collaboration between universities and industry by establishing an innovation platform where companies can bring their challenges to be addressed together with university experts. The project also promotes collaboration between universities being a part of the RoboAI Competence Centre - a joint research and innovation platform of Satakunta University of Applied Sciences (SAMK) and Tampere University, Pori unit. Automatic classification of bricks is important as it is foreseen that a robotic arm, powered by an automatic classifier, could replace the heavy and tedious work currently performed by humans in brick factories. A convolutional neural network-based solution, using a pretrained VGG-16 deep learning architecture, is proposed. Overall accuracy of 88 % was obtained when considering all three quality classes. When only discarding class 3 bricks, i.e., those that are not suitable for any construction work, the accuracy was 93 %.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"42 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114025558","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687089
Junqing Li, Huimin Wang, Changqing Song, Ruiyi Han, Taiyuan Hu
For the shortcoming of reduced generalization ability of random forests in the big data era, a classification method for hierarchical clustering of undersampled fused random forests is presented in this paper. The proposed method clusters the majority of samples through a hierarchical clustering algorithm, undersampling the samples of each cluster with a minority samples, bringing the data samples to equilibrium, and then building a random forest. This experiment used the CGSS data for 2015, compared with the classification method of random undersampled fused random forests, the prediction accuracy and F value were improved by 16% and 17%, which proved that the generalization ability of random forests was improved in this method. Based on the analysis of the method and experimental data of this paper, it is concluded that three important decision-making factors affecting commercial medical endowment insurance are family income, the using frequency of internet and age, which provide a new idea for studying the influencing factors of commercial insurance demand and predicting the commercial insurance purchase behavior.
{"title":"Research on Hierarchical Clustering Undersampling and Random Forest Fusion Classification Method","authors":"Junqing Li, Huimin Wang, Changqing Song, Ruiyi Han, Taiyuan Hu","doi":"10.1109/PIC53636.2021.9687089","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687089","url":null,"abstract":"For the shortcoming of reduced generalization ability of random forests in the big data era, a classification method for hierarchical clustering of undersampled fused random forests is presented in this paper. The proposed method clusters the majority of samples through a hierarchical clustering algorithm, undersampling the samples of each cluster with a minority samples, bringing the data samples to equilibrium, and then building a random forest. This experiment used the CGSS data for 2015, compared with the classification method of random undersampled fused random forests, the prediction accuracy and F value were improved by 16% and 17%, which proved that the generalization ability of random forests was improved in this method. Based on the analysis of the method and experimental data of this paper, it is concluded that three important decision-making factors affecting commercial medical endowment insurance are family income, the using frequency of internet and age, which provide a new idea for studying the influencing factors of commercial insurance demand and predicting the commercial insurance purchase behavior.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114801266","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687053
Jukka Ruohonen
This short paper examines the similarities and differences of software vulnerabilities reported for interpreted programming languages. Based on a sample of vulnerabilities from four software repositories (Maven, npm, PyPI, and RubyGems), the Common Vulnerability Scoring System (CVSS) and the Common Weakness Enumeration (CWE) are used for comparing the vulnerabilities across the repositories. According to the results, (i) the severity of the vulnerabilities is similar across the repositories; the median CVSS v.3 base scores are around seven. Similarity can be observed also in terms of the weaknesses underneath the vulnerabilities. In particular, (ii) cross-site scripting and input validation have been the most typical weaknesses across all four repositories. The same applies to path-traversal bugs, unauthorized accesses, and resource management bugs. With these observations, the paper contributes to the recent active research on language-specific software repositories.
{"title":"The Similarities of Software Vulnerabilities for Interpreted Programming Languages","authors":"Jukka Ruohonen","doi":"10.1109/PIC53636.2021.9687053","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687053","url":null,"abstract":"This short paper examines the similarities and differences of software vulnerabilities reported for interpreted programming languages. Based on a sample of vulnerabilities from four software repositories (Maven, npm, PyPI, and RubyGems), the Common Vulnerability Scoring System (CVSS) and the Common Weakness Enumeration (CWE) are used for comparing the vulnerabilities across the repositories. According to the results, (i) the severity of the vulnerabilities is similar across the repositories; the median CVSS v.3 base scores are around seven. Similarity can be observed also in terms of the weaknesses underneath the vulnerabilities. In particular, (ii) cross-site scripting and input validation have been the most typical weaknesses across all four repositories. The same applies to path-traversal bugs, unauthorized accesses, and resource management bugs. With these observations, the paper contributes to the recent active research on language-specific software repositories.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132826780","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687032
Xiuxia Zhang, Jian Hao, Shuyi Wei
Wind power output is influenced by many factors, and its changing trend is complex, so it is difficult to use a single forecasting method to effectively forecast wind power. Moreover, an excellent power prediction model will have a significant impact on rational energy dispatching, demand management, energy conservation and emission reduction. In this paper, based on the classic machine learning model, multiple models are fused to predict the power and optimize the performance of energy. A number of algorithm models are used as base learners to fuse the weights of the prediction results to keep the feature relevance. Then, the weight fusion models are also used as base learners for training, and further high-level models are obtained through Stacking model fusion, which is compared with a number of classical algorithm models to synthesize the best performance energy prediction model. By comparison, the power prediction model fused by multiple models has higher running speed and accuracy, and higher performance in energy power prediction. The results show that the multiple model fusion of classical algorithm models can effectively improve the accuracy of power prediction, thus obtaining the best performance power prediction model.
{"title":"Research on Wind Turbine Power Prediction Based on Model Fusion","authors":"Xiuxia Zhang, Jian Hao, Shuyi Wei","doi":"10.1109/PIC53636.2021.9687032","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687032","url":null,"abstract":"Wind power output is influenced by many factors, and its changing trend is complex, so it is difficult to use a single forecasting method to effectively forecast wind power. Moreover, an excellent power prediction model will have a significant impact on rational energy dispatching, demand management, energy conservation and emission reduction. In this paper, based on the classic machine learning model, multiple models are fused to predict the power and optimize the performance of energy. A number of algorithm models are used as base learners to fuse the weights of the prediction results to keep the feature relevance. Then, the weight fusion models are also used as base learners for training, and further high-level models are obtained through Stacking model fusion, which is compared with a number of classical algorithm models to synthesize the best performance energy prediction model. By comparison, the power prediction model fused by multiple models has higher running speed and accuracy, and higher performance in energy power prediction. The results show that the multiple model fusion of classical algorithm models can effectively improve the accuracy of power prediction, thus obtaining the best performance power prediction model.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134294285","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687072
Jialin Lin, Yufei Wang, Ming Han, Yu Yang, Min Lei
Adaptive steganography is the most advanced steganography currently, an important method to detect it is to integrate the embedding probability into feature extraction of adaptive steganalysis. Unfortunately, most of the existing methods directly use the true embedding probability maps, which are generated by prior knowledge: the specific steganographic strategies and embedding payloads. However, these cannot be known in advance for steganalysis tasks in the real world. To overcome this difficulty, we propose an embedding probability estimation algorithm based on the local binary pattern (LBP) for adaptive steganalysis. The algorithm we proposed has the advantage of not relying on prior knowledge. Meanwhile, for the first time, LBP operator is introduced into embedding probability estimation. As a non-machine learning method, it has a lighter-weight architecture because it does not need large-scale data sets for training. Experimental results show that the algorithm can better reduce the impact of embedding payloads mismatch than the existing methods, especially when the embedding payload is small.
{"title":"A Lightweight Embedding Probability Estimation Algorithm Based on LBP for Adaptive Steganalysis","authors":"Jialin Lin, Yufei Wang, Ming Han, Yu Yang, Min Lei","doi":"10.1109/PIC53636.2021.9687072","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687072","url":null,"abstract":"Adaptive steganography is the most advanced steganography currently, an important method to detect it is to integrate the embedding probability into feature extraction of adaptive steganalysis. Unfortunately, most of the existing methods directly use the true embedding probability maps, which are generated by prior knowledge: the specific steganographic strategies and embedding payloads. However, these cannot be known in advance for steganalysis tasks in the real world. To overcome this difficulty, we propose an embedding probability estimation algorithm based on the local binary pattern (LBP) for adaptive steganalysis. The algorithm we proposed has the advantage of not relying on prior knowledge. Meanwhile, for the first time, LBP operator is introduced into embedding probability estimation. As a non-machine learning method, it has a lighter-weight architecture because it does not need large-scale data sets for training. Experimental results show that the algorithm can better reduce the impact of embedding payloads mismatch than the existing methods, especially when the embedding payload is small.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122099605","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687004
Run Chai, Junchao Wan, Huaping Zhu
Dental caries is a common bacterial disease, as well as early detection such as caries activity test (also known as Cariostat test) is essential for caries control. The Cariostat test is used to determine the risk of caries by comparing the indicator color of culture medium in vitro with the standard color card. The purpose of this paper was to design a machine vision aided automatic color recognition system for measuring the Cariostat scores associated etiologically with dental caries. By calculating a widely color characteristics of each class of culture medium images, a standard color card representing each level of diagnosis was established followed by the Cariostat test. The geometric distance between the test picture and the standard color card was calculated, and the caries risk level could be obtained accordingly by the threshold-controlling. Compared with the subjective judgment of the naked eye, the accuracy, effectiveness, and computational efficiency of our system are fully verified.
{"title":"A Medical Reagent Grade Judgment System Based on Color Intelligent Recognition","authors":"Run Chai, Junchao Wan, Huaping Zhu","doi":"10.1109/PIC53636.2021.9687004","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687004","url":null,"abstract":"Dental caries is a common bacterial disease, as well as early detection such as caries activity test (also known as Cariostat test) is essential for caries control. The Cariostat test is used to determine the risk of caries by comparing the indicator color of culture medium in vitro with the standard color card. The purpose of this paper was to design a machine vision aided automatic color recognition system for measuring the Cariostat scores associated etiologically with dental caries. By calculating a widely color characteristics of each class of culture medium images, a standard color card representing each level of diagnosis was established followed by the Cariostat test. The geometric distance between the test picture and the standard color card was calculated, and the caries risk level could be obtained accordingly by the threshold-controlling. Compared with the subjective judgment of the naked eye, the accuracy, effectiveness, and computational efficiency of our system are fully verified.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129580282","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：