Pub Date : 2017-10-01DOI: 10.1109/ICCSNT.2017.8343724
Chunyu Han, Yongzheng Zhang
Domain plays an important role as one of the components on the Internet, so more and more malicious behavior has been conducted by using domains, such as spam, botnet, phishing and the like. DGA (Domain Generation Algorithm), one kind of DNS technology, has been used by domain-flux commonly in botnets. In this paper, we propose a method called CODDULM (C&c domains Of Dga Detection Using Lexical feature and sparse Matrix). Firstly, it finds the NXDomains (Non-existent domains) on the passive DNS traffic to locate the suspicious infected hosts. Secondly, it selects DGA domains by lexical features according to suspicious infected hosts. Lastly, it discovers DGA C&C (Command and Control) domains through SVM (Support Vector Machine algorithm) classifier. At the end of this paper, we conduct the experiment to verify the effect of the method and the high accuracy of it.
{"title":"CODDULM: An approach for detecting C&C domains of DGA on passive DNS traffic","authors":"Chunyu Han, Yongzheng Zhang","doi":"10.1109/ICCSNT.2017.8343724","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343724","url":null,"abstract":"Domain plays an important role as one of the components on the Internet, so more and more malicious behavior has been conducted by using domains, such as spam, botnet, phishing and the like. DGA (Domain Generation Algorithm), one kind of DNS technology, has been used by domain-flux commonly in botnets. In this paper, we propose a method called CODDULM (C&c domains Of Dga Detection Using Lexical feature and sparse Matrix). Firstly, it finds the NXDomains (Non-existent domains) on the passive DNS traffic to locate the suspicious infected hosts. Secondly, it selects DGA domains by lexical features according to suspicious infected hosts. Lastly, it discovers DGA C&C (Command and Control) domains through SVM (Support Vector Machine algorithm) classifier. At the end of this paper, we conduct the experiment to verify the effect of the method and the high accuracy of it.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116753218","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 : 2017-10-01DOI: 10.1109/ICCSNT.2017.8343730
Hongsheng Zhou, Xiaoqiang Song, Li Lin, Li Du
The deployment of PCE (Path Computation Element) architecture in high-speed MPLS/GMPLS networks is widely accepted and facilitates path setup operations for applications with explicitly defined objective functions. In this paper, we propose a new link-abstraction mechanism, which improves the method of establishing domain topology of parent PCE, and further aggregates the abstract topology in the hierarchical PCE method, thus simplifying the topology aggregation of the multi-domain. Meanwhile, considering the constraints of multiple factors which affect cross-domain path calculations, we provide a relatively simple way to select, which solves the key problem of determining the “domain sequence” in the process of cross-domain path calculation. Simulation results show that the proposed method has better performance in terms of blocking probability, end-to-end delay and resource utilization rate.
{"title":"Multi-domain routing technology based on PCE for intelligent optical networks","authors":"Hongsheng Zhou, Xiaoqiang Song, Li Lin, Li Du","doi":"10.1109/ICCSNT.2017.8343730","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343730","url":null,"abstract":"The deployment of PCE (Path Computation Element) architecture in high-speed MPLS/GMPLS networks is widely accepted and facilitates path setup operations for applications with explicitly defined objective functions. In this paper, we propose a new link-abstraction mechanism, which improves the method of establishing domain topology of parent PCE, and further aggregates the abstract topology in the hierarchical PCE method, thus simplifying the topology aggregation of the multi-domain. Meanwhile, considering the constraints of multiple factors which affect cross-domain path calculations, we provide a relatively simple way to select, which solves the key problem of determining the “domain sequence” in the process of cross-domain path calculation. Simulation results show that the proposed method has better performance in terms of blocking probability, end-to-end delay and resource utilization rate.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115499332","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 : 2017-10-01DOI: 10.1109/ICCSNT.2017.8343476
Qing-quan Tan, Qun Liu, Hua-Chun Luo, Bo Liu, Jian Liu
Earthquake often inflicts severe casualties and property losses. Building information data play an important role in earthquake damage evaluation and emergency countermeasures. In this paper, a novel approach for building information collection is proposed and implemented, which is based on GIS technology. The system design is concisely presented, and the research results are introduced. The research results are applied in real earthquake work, and are significant to enhance the earthquake emergency response capability.
{"title":"Design and implementation of building information collection system for earthquake disaster scenario construction based on GIS","authors":"Qing-quan Tan, Qun Liu, Hua-Chun Luo, Bo Liu, Jian Liu","doi":"10.1109/ICCSNT.2017.8343476","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343476","url":null,"abstract":"Earthquake often inflicts severe casualties and property losses. Building information data play an important role in earthquake damage evaluation and emergency countermeasures. In this paper, a novel approach for building information collection is proposed and implemented, which is based on GIS technology. The system design is concisely presented, and the research results are introduced. The research results are applied in real earthquake work, and are significant to enhance the earthquake emergency response capability.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115533116","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 : 2017-10-01DOI: 10.1109/ICCSNT.2017.8343695
Xiaoli Sun, Yusong Tan, Q. Wu, Jing Wang
Continuous subgraph pattern matching is an extension of the traditional subgraph pattern matching and becoming a subject that attracts increasing interest. It requires the near real-time responses and is used in many applications, for example, abnormal monitoring in social networks, cyber attacks monitoring in cyber networks. As the dynamic graph changes with time, the temporal subgraph pattern (i.e., the edges have temporal relation) is considered. In this paper, the Hasse diagram is introduced to represent the temporal relation of the query graph. Then we design the Hasse-cache structure, and propose a continuous temporal subgraph pattern matching algorithm based on the Hasse diagram. The algorithm uses the probability of dynamic graph to reduce the intermediate results, and can implement the matching of topology and the verification of temporal relation simultaneously. Our experiments with real-world datasets show that the proposed algorithm has 10x speedups over the previous approaches.
{"title":"Hasse diagram based algorithm for continuous temporal subgraph query in graph stream","authors":"Xiaoli Sun, Yusong Tan, Q. Wu, Jing Wang","doi":"10.1109/ICCSNT.2017.8343695","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343695","url":null,"abstract":"Continuous subgraph pattern matching is an extension of the traditional subgraph pattern matching and becoming a subject that attracts increasing interest. It requires the near real-time responses and is used in many applications, for example, abnormal monitoring in social networks, cyber attacks monitoring in cyber networks. As the dynamic graph changes with time, the temporal subgraph pattern (i.e., the edges have temporal relation) is considered. In this paper, the Hasse diagram is introduced to represent the temporal relation of the query graph. Then we design the Hasse-cache structure, and propose a continuous temporal subgraph pattern matching algorithm based on the Hasse diagram. The algorithm uses the probability of dynamic graph to reduce the intermediate results, and can implement the matching of topology and the verification of temporal relation simultaneously. Our experiments with real-world datasets show that the proposed algorithm has 10x speedups over the previous approaches.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"384 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114898592","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 : 2017-10-01DOI: 10.1109/ICCSNT.2017.8343679
Song Qiang, Han Xing, Gao Jian
This paper presents the radar task scheduling problem for a prior way which will ignore the issues of the urgency and importance of task time. For this problem, we present a method based on the three characteristic parameters: the task priority, deadline and idle time, composed of an algorithm which accommodates the different load conditions of the radar scheduler by adjusting the parameter weight and composed of a way with time window which makes sure that more high priority tasks can be scheduled in a scheduling interval.
{"title":"A task scheduling simulation for phased array radar with time windows","authors":"Song Qiang, Han Xing, Gao Jian","doi":"10.1109/ICCSNT.2017.8343679","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343679","url":null,"abstract":"This paper presents the radar task scheduling problem for a prior way which will ignore the issues of the urgency and importance of task time. For this problem, we present a method based on the three characteristic parameters: the task priority, deadline and idle time, composed of an algorithm which accommodates the different load conditions of the radar scheduler by adjusting the parameter weight and composed of a way with time window which makes sure that more high priority tasks can be scheduled in a scheduling interval.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129937435","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 : 2017-10-01DOI: 10.1109/ICCSNT.2017.8343479
W. Lijuan, Hou Hong-feng, Xu Changan, Jiang Bo, Ning Tao
In this paper, the problem of traveling disjoint segment sequences in the plane will be studied. The goal is to find the shortest path from the start point, then visiting each segment in the given order, and finally to the target point. By adopting the techniques of division of convex chain, combination optimization and binary search tree, we design a fast algorithm with the O(nlog2n) time complexity to solve it, denoted by BST algorithm, where n is the total number of all segments, and we introduce the main techniques used in this paper in detail. Furthermore, we generate a large amount of test data to test BST algorithm, and compare the efficiency of BST algorithm and Rubber-band algorithm, which is the better solution to this problem. The results show that BST algorithm is superior to Rubber-band algorithm, and it is the optimal algorithm for visiting the disjoint segment sequences so far.
{"title":"A study of algorithms for traveling segment sequences based on convex chain","authors":"W. Lijuan, Hou Hong-feng, Xu Changan, Jiang Bo, Ning Tao","doi":"10.1109/ICCSNT.2017.8343479","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343479","url":null,"abstract":"In this paper, the problem of traveling disjoint segment sequences in the plane will be studied. The goal is to find the shortest path from the start point, then visiting each segment in the given order, and finally to the target point. By adopting the techniques of division of convex chain, combination optimization and binary search tree, we design a fast algorithm with the O(nlog2n) time complexity to solve it, denoted by BST algorithm, where n is the total number of all segments, and we introduce the main techniques used in this paper in detail. Furthermore, we generate a large amount of test data to test BST algorithm, and compare the efficiency of BST algorithm and Rubber-band algorithm, which is the better solution to this problem. The results show that BST algorithm is superior to Rubber-band algorithm, and it is the optimal algorithm for visiting the disjoint segment sequences so far.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128448886","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 : 2017-10-01DOI: 10.1109/ICCSNT.2017.8343693
Wangping Xiong, Jianqiang Du, Bin Nie, Liping Huang, Xian Zhou
Because of the complexities of traditional Chinese medicine's prescriptions, the dose-effect relationship between prescriptions has a significant difference from the common “S” — type curve of the pharmaceutical chemicals, which is nonlinear. Therefore, the study of the dose-effect relationship between prescriptions can not copy the research methods of dose-effect relationship of pharmaceutical chemicals, but need to consider a variety of influencing factors and compatibility of medicines. Based on the collection, collation and analysis of experimental data in a large number of literature of Traditional Chinese Medicine(TCM) prescriptions, this paper first planned to construct algorithm which fused Q-type clustering and R-type clustering to eliminate abnormal data; obtain high-efficiency modeling samples through the correction method of orthogonal signal; build a complete path graph by making the respective variables and dependent variables as nodes and using direct and indirect path coefficient as weights, and analyze the directional and authoritative graph through the complex network model to filter the important variables out; The partial least squares (PLS) nonlinear model towards the dose-effect relationship of TCM was established based on the maximum entropy principle to determine the partial least squares, which has great significance to scientifically illustrate the dose-effect relationship between prescriptions and its effects, systematically study, summarize and draw theories of prescriptions' doses, rationally improve the clinical effects of TCM and guide the choices of clinical doses.
{"title":"Application of modified partial least squares in data analysis of Traditional Chinese Medicine","authors":"Wangping Xiong, Jianqiang Du, Bin Nie, Liping Huang, Xian Zhou","doi":"10.1109/ICCSNT.2017.8343693","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343693","url":null,"abstract":"Because of the complexities of traditional Chinese medicine's prescriptions, the dose-effect relationship between prescriptions has a significant difference from the common “S” — type curve of the pharmaceutical chemicals, which is nonlinear. Therefore, the study of the dose-effect relationship between prescriptions can not copy the research methods of dose-effect relationship of pharmaceutical chemicals, but need to consider a variety of influencing factors and compatibility of medicines. Based on the collection, collation and analysis of experimental data in a large number of literature of Traditional Chinese Medicine(TCM) prescriptions, this paper first planned to construct algorithm which fused Q-type clustering and R-type clustering to eliminate abnormal data; obtain high-efficiency modeling samples through the correction method of orthogonal signal; build a complete path graph by making the respective variables and dependent variables as nodes and using direct and indirect path coefficient as weights, and analyze the directional and authoritative graph through the complex network model to filter the important variables out; The partial least squares (PLS) nonlinear model towards the dose-effect relationship of TCM was established based on the maximum entropy principle to determine the partial least squares, which has great significance to scientifically illustrate the dose-effect relationship between prescriptions and its effects, systematically study, summarize and draw theories of prescriptions' doses, rationally improve the clinical effects of TCM and guide the choices of clinical doses.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128966706","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 : 2017-10-01DOI: 10.1109/ICCSNT.2017.8343481
Changan Xu, Bo Jiang, Lijuan Wang
Given a sequence of ordered convex polygons in which the adjacent polygons may intersect with each other, but the nonadjacent polygons do not intersect, a start point s, and an end point t in the plane, our goal is to obtain a shortest path that starts from s, visits each given polygon in order, and ends at t finally. We converted the touring polygons problem into the problem of computing the shortest path of visiting the disjoint line segments by analyzing the geometrical features of the given convex polygons, and preprocessing the intersection points of the jointed polygons, and using a forward partition process combined with a backward search process for finding the access edge of each convex polygon. Thus, we proposed an 0(max{n, klog⁁2k}) algorithm for solving the original problem, where n is the total number of vertices of the given polygons and k is the total number of polygons.
{"title":"An efficient algorithm for touring a sequence of given convex polygons in the plane","authors":"Changan Xu, Bo Jiang, Lijuan Wang","doi":"10.1109/ICCSNT.2017.8343481","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343481","url":null,"abstract":"Given a sequence of ordered convex polygons in which the adjacent polygons may intersect with each other, but the nonadjacent polygons do not intersect, a start point s, and an end point t in the plane, our goal is to obtain a shortest path that starts from s, visits each given polygon in order, and ends at t finally. We converted the touring polygons problem into the problem of computing the shortest path of visiting the disjoint line segments by analyzing the geometrical features of the given convex polygons, and preprocessing the intersection points of the jointed polygons, and using a forward partition process combined with a backward search process for finding the access edge of each convex polygon. Thus, we proposed an 0(max{n, klog⁁2k}) algorithm for solving the original problem, where n is the total number of vertices of the given polygons and k is the total number of polygons.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125357748","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 : 2017-10-01DOI: 10.1109/ICCSNT.2017.8343705
Junjie Gao, Wei Xiao, Yanan Xie, Feng Gu, Baozhen Yao
The study is dedicated to an intelligent fault diagnosis approach for vehicle maintenance which integrates both the cloud model and case-based reasoning (CBR). The cloud model is used to transform the uncertainty of the subjective quantitative information into qualitative values to calculate the case similarity, which greatly simplifies the input conditions in case retrieval and improves the operability of fault diagnosis. The improved Euclidean distance formula is taken as a measure of the similarity between the fault cases. Compared with the traditional method, it eliminates the similarity deviation and improves the accuracy of case retrieval. The case study of vehicle electrical and electronic equipment is reported, which can prove the approach proposed in this paper is correct and efficient.
{"title":"An intelligent fault diagnosis approach integrating cloud model and CBR","authors":"Junjie Gao, Wei Xiao, Yanan Xie, Feng Gu, Baozhen Yao","doi":"10.1109/ICCSNT.2017.8343705","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343705","url":null,"abstract":"The study is dedicated to an intelligent fault diagnosis approach for vehicle maintenance which integrates both the cloud model and case-based reasoning (CBR). The cloud model is used to transform the uncertainty of the subjective quantitative information into qualitative values to calculate the case similarity, which greatly simplifies the input conditions in case retrieval and improves the operability of fault diagnosis. The improved Euclidean distance formula is taken as a measure of the similarity between the fault cases. Compared with the traditional method, it eliminates the similarity deviation and improves the accuracy of case retrieval. The case study of vehicle electrical and electronic equipment is reported, which can prove the approach proposed in this paper is correct and efficient.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122569587","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 : 2017-10-01DOI: 10.1109/ICCSNT.2017.8343736
Zuchun Ding, Wenying Mo
A novel algorithm to use vehicle sticker (or tag) features and encode the features is proposed. It can make the representation more precise and recognition more accurate. In vehicle recognition or searching, traditional algorithms will be limited because they focus only on the features extracted from colors, logos or sub-types that are not enough to identify a vehicle. Furthermore, the license plate (LP) can be forged easily so the LP is not reliable to identify a specified vehicle. Our algorithm solves this problem by sticker multi-feature encoding. Most vehicles have printed permission labels or certification symbols named vehicle stickers or tags mounted on the frontal glass. These stickers are a kind of special fingerprint features to identify a unique vehicle. Every driver has his own habit to paste different stickers. In this meaning these stickers form specified multi-feature including color, shape, position and amount. Our algorithm encodes the sticker multi-feature to construct structured feature presentation, i.e. the sticker code. In recognition stage, with the matrix distance of the multi-feature encoding, the detailed sticker code can be utilized to distinguish the vehicle types and colors reliably, and can recognize the tiny difference among vehicles with the same colors, logos and even sub-types. Our algorithm decreases the amount of vehicle candidates effectively by accurate feature coding. In our experiments, we coped with 10000 vehicle images taken by public traffic surveillance system to verify the effectiveness of this algorithm in vehicle sticker multi-feature encoding recognition.
{"title":"Vehicle sticker recognition based on multi-feature encoding and feature matrix distance","authors":"Zuchun Ding, Wenying Mo","doi":"10.1109/ICCSNT.2017.8343736","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343736","url":null,"abstract":"A novel algorithm to use vehicle sticker (or tag) features and encode the features is proposed. It can make the representation more precise and recognition more accurate. In vehicle recognition or searching, traditional algorithms will be limited because they focus only on the features extracted from colors, logos or sub-types that are not enough to identify a vehicle. Furthermore, the license plate (LP) can be forged easily so the LP is not reliable to identify a specified vehicle. Our algorithm solves this problem by sticker multi-feature encoding. Most vehicles have printed permission labels or certification symbols named vehicle stickers or tags mounted on the frontal glass. These stickers are a kind of special fingerprint features to identify a unique vehicle. Every driver has his own habit to paste different stickers. In this meaning these stickers form specified multi-feature including color, shape, position and amount. Our algorithm encodes the sticker multi-feature to construct structured feature presentation, i.e. the sticker code. In recognition stage, with the matrix distance of the multi-feature encoding, the detailed sticker code can be utilized to distinguish the vehicle types and colors reliably, and can recognize the tiny difference among vehicles with the same colors, logos and even sub-types. Our algorithm decreases the amount of vehicle candidates effectively by accurate feature coding. In our experiments, we coped with 10000 vehicle images taken by public traffic surveillance system to verify the effectiveness of this algorithm in vehicle sticker multi-feature encoding recognition.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123893766","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：