Pub Date : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073416
Hua-Cong Yang, Yi-Chao Li, Zhi-Yu Liu, Jie Qiu
Current smartphones are integrated with rich sensors, which provides a good opportunity for the smartphone sensor data mining. By mining these data, we are able to analyze the user's behaviors. This paper describes HARLib, a human activity recognition library on the Android operating system. We use accelerometer built-in smartphone to recognize the user's activities, including walking, running, sitting, standing, lying down and stairs. It can be easy embedded into Android applications and provide a good performance of human activity recognition function.
{"title":"HARLib: A human activity recognition library on Android","authors":"Hua-Cong Yang, Yi-Chao Li, Zhi-Yu Liu, Jie Qiu","doi":"10.1109/ICCWAMTIP.2014.7073416","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073416","url":null,"abstract":"Current smartphones are integrated with rich sensors, which provides a good opportunity for the smartphone sensor data mining. By mining these data, we are able to analyze the user's behaviors. This paper describes HARLib, a human activity recognition library on the Android operating system. We use accelerometer built-in smartphone to recognize the user's activities, including walking, running, sitting, standing, lying down and stairs. It can be easy embedded into Android applications and provide a good performance of human activity recognition function.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128470904","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073445
Huan Zeng, Yan Ren, Qing-xian Wang, Neng-Qiang He, Xu-Yang Ding
The popularity and widely use of cellphone have greatly stimulated the spread of the apps. Meanwhile, security issues are increasing quickly, particularly for Android based devices. In this paper, through analyzing the android permissions system and android API system, we want to find out the relationship between permissions and APIs. Furthermore, we propose an approach to detect message intercepting malware. The contribution of this paper is threefold: first, we perform static analysis on the app to extract permissions and system APIs. In order to avoid permissions and APIs over declaration, we build java function call graph and find the system APIs been used; secondly, we proposed a light weight method to dynamic find out and update the relationship between permissions and APIs; third, we proposed a dynamic controlled method to detect android malwares. This proposed method is verified by extensive experiments.
{"title":"Detecting malware and evaluating risk of app using Android permission-API system","authors":"Huan Zeng, Yan Ren, Qing-xian Wang, Neng-Qiang He, Xu-Yang Ding","doi":"10.1109/ICCWAMTIP.2014.7073445","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073445","url":null,"abstract":"The popularity and widely use of cellphone have greatly stimulated the spread of the apps. Meanwhile, security issues are increasing quickly, particularly for Android based devices. In this paper, through analyzing the android permissions system and android API system, we want to find out the relationship between permissions and APIs. Furthermore, we propose an approach to detect message intercepting malware. The contribution of this paper is threefold: first, we perform static analysis on the app to extract permissions and system APIs. In order to avoid permissions and APIs over declaration, we build java function call graph and find the system APIs been used; secondly, we proposed a light weight method to dynamic find out and update the relationship between permissions and APIs; third, we proposed a dynamic controlled method to detect android malwares. This proposed method is verified by extensive experiments.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130345423","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073351
Wei-Long Yang, Luo Lei, Jingwei Deng
The Multi-UAV cooperative reconnaissance mission planning is one of the task allocation and resource scheduling problems during the multi-UAV cooperative control. The key to solve this problem is to build a reasonable solving-model and find an effective solving-algorithm. Based on the analysis of characteristics about reconnaissance missions, this paper takes plenty of constraints and performance planning targets in multi-UAV cooperative reconnaissance mission planning problems into full consideration, in particular the number of surveillance for targets, the reconnaissance time, the types of load requirements, and also the performance requirements of UAV, and thus establishes a more practical mathematical model for the multi-base, multi-target, multi-UAV cooperative reconnaissance problem. What is more, for the problems existed when dealing with the model, such as NP-hard and complex constraints, this paper has designed a modified genetic algorithm, based on the classical one, and meanwhile constructed the initial feasible solutions through a heuristic method, which would avoid the over-slow convergence in the process of evolutionary to a large degree.
{"title":"Optimization and improvement for multi-UAV cooperative reconnaissance mission planning problem","authors":"Wei-Long Yang, Luo Lei, Jingwei Deng","doi":"10.1109/ICCWAMTIP.2014.7073351","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073351","url":null,"abstract":"The Multi-UAV cooperative reconnaissance mission planning is one of the task allocation and resource scheduling problems during the multi-UAV cooperative control. The key to solve this problem is to build a reasonable solving-model and find an effective solving-algorithm. Based on the analysis of characteristics about reconnaissance missions, this paper takes plenty of constraints and performance planning targets in multi-UAV cooperative reconnaissance mission planning problems into full consideration, in particular the number of surveillance for targets, the reconnaissance time, the types of load requirements, and also the performance requirements of UAV, and thus establishes a more practical mathematical model for the multi-base, multi-target, multi-UAV cooperative reconnaissance problem. What is more, for the problems existed when dealing with the model, such as NP-hard and complex constraints, this paper has designed a modified genetic algorithm, based on the classical one, and meanwhile constructed the initial feasible solutions through a heuristic method, which would avoid the over-slow convergence in the process of evolutionary to a large degree.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130467164","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073428
D. A. Jamro, Jingsong Hong, M. Bah, F. A. Mangi
A novel triangular patch antenna of decreased RCS is proposed and investigated for ultra-wide band (UWB) applications. The intention of antenna innovation is to realize radar cross section reduction. The patch slotted and miniaturization techniques are used. A radiating patch is innovated to improve RCS while two slots are notched on patch to maintain good radiation performance and enhance impedance matching of designed antenna. The RCS function of novel antenna is analyzed and matched with a referred patch. It is shown from outcomes that the new patch has an improved RCS in almost all the functioning frequency of 2-12GHz and gain has some reasonable incoherence in the wide band frequency. The simulated results demonstrate that the designed antenna offers good prospect for low RCS antenna applications.
{"title":"Novel triangular patch antenna with reduced radar cross section","authors":"D. A. Jamro, Jingsong Hong, M. Bah, F. A. Mangi","doi":"10.1109/ICCWAMTIP.2014.7073428","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073428","url":null,"abstract":"A novel triangular patch antenna of decreased RCS is proposed and investigated for ultra-wide band (UWB) applications. The intention of antenna innovation is to realize radar cross section reduction. The patch slotted and miniaturization techniques are used. A radiating patch is innovated to improve RCS while two slots are notched on patch to maintain good radiation performance and enhance impedance matching of designed antenna. The RCS function of novel antenna is analyzed and matched with a referred patch. It is shown from outcomes that the new patch has an improved RCS in almost all the functioning frequency of 2-12GHz and gain has some reasonable incoherence in the wide band frequency. The simulated results demonstrate that the designed antenna offers good prospect for low RCS antenna applications.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130781393","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073420
Anping Xiong, Chunxiang Xu, Qi-Xian Gan
Attribute Based Encryption (CP-ABE) access control schemes has become a heated topic area in security since it is more suitable for access control mechanism. Due to the problems such that system attribute revocation is not flexible, system overhead is too big and other issues for existing CP-ABE access control schemes under cloud environment, with the limited access condition of `AND' and `OR' in an access tree, based on AB-ACER schemes, we proposed a CP-ABE scheme with system attribute revocation in Cloud storage. This scheme is based on many minimum attribute sets which shared Re-encryption keys, storage service provider re-encrypts ciphertext when a system attribute is revoked. This scheme is not only keeps security and fine-grained access control of original scheme, but also has a good flexibility and efficiency.
基于属性加密(Attribute Based Encryption, CP-ABE)的访问控制方案由于更适合于访问控制机制而成为安全领域的研究热点。针对现有的云环境下CP-ABE访问控制方案存在系统属性撤销不灵活、系统开销过大等问题，在访问树的“与”和“或”访问条件有限的情况下，我们在AB-ACER方案的基础上，提出了云存储中具有系统属性撤销的CP-ABE方案。该方案基于多个共享重加密密钥的最小属性集，存储服务提供者在系统属性被撤销时对密文进行重新加密。该方案既保持了原方案的安全性和细粒度访问控制，又具有良好的灵活性和效率。
{"title":"A CP-ABE scheme with system attributes revocation in cloud storage","authors":"Anping Xiong, Chunxiang Xu, Qi-Xian Gan","doi":"10.1109/ICCWAMTIP.2014.7073420","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073420","url":null,"abstract":"Attribute Based Encryption (CP-ABE) access control schemes has become a heated topic area in security since it is more suitable for access control mechanism. Due to the problems such that system attribute revocation is not flexible, system overhead is too big and other issues for existing CP-ABE access control schemes under cloud environment, with the limited access condition of `AND' and `OR' in an access tree, based on AB-ACER schemes, we proposed a CP-ABE scheme with system attribute revocation in Cloud storage. This scheme is based on many minimum attribute sets which shared Re-encryption keys, storage service provider re-encrypts ciphertext when a system attribute is revoked. This scheme is not only keeps security and fine-grained access control of original scheme, but also has a good flexibility and efficiency.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114124632","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073390
Yujun Yang, Yimei Yang, Jianping Li
This article first briefly introduces the basic principles of the multipath effects and analyzes the causes of the multipath fading, and then gives the standards definition for some related concepts and rigorous mathematical expressions for those. Then, based on a theoretical model, using dynamic system modeling and simulation software package Simulink of the Matlab software, this article gives the corresponding simulation model, vividly recreates the actual process of multipath fading channels. The simulation results prove the feasibility of this algorithm and have good performances and higher applied value.
{"title":"Research on blind equalization method of multipath channels","authors":"Yujun Yang, Yimei Yang, Jianping Li","doi":"10.1109/ICCWAMTIP.2014.7073390","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073390","url":null,"abstract":"This article first briefly introduces the basic principles of the multipath effects and analyzes the causes of the multipath fading, and then gives the standards definition for some related concepts and rigorous mathematical expressions for those. Then, based on a theoretical model, using dynamic system modeling and simulation software package Simulink of the Matlab software, this article gives the corresponding simulation model, vividly recreates the actual process of multipath fading channels. The simulation results prove the feasibility of this algorithm and have good performances and higher applied value.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114473056","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073368
Junjie Wu, Yue Zhang
Electrocardiogram (ECG) can be used in clinical diagnosis for cardiac function. Also, because individuals have different ECG traces, therefore, they can be acquired as promising biometric features for human identification. Data for experiment in this paper were chosen from MIT-BIH Arrhythmia Database. Lead I ECG traces of 33 normal individuals were used. QRS complexes were extracted from filtered ECG data as features for identification. After dimension reduction by principal component analysis, Back Propagation Neural Networks was used as classifier. Finally, identification results were determined by voting mechanism. The results showed that, accuracy of classification can reach up to 99.6% using the method proposed in this paper. Besides, this method surpasses other researches in a comprehensive way by considering aspects such as the number of leads, data set, complexity and accuracy.
{"title":"ECG identification based on neural networks","authors":"Junjie Wu, Yue Zhang","doi":"10.1109/ICCWAMTIP.2014.7073368","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073368","url":null,"abstract":"Electrocardiogram (ECG) can be used in clinical diagnosis for cardiac function. Also, because individuals have different ECG traces, therefore, they can be acquired as promising biometric features for human identification. Data for experiment in this paper were chosen from MIT-BIH Arrhythmia Database. Lead I ECG traces of 33 normal individuals were used. QRS complexes were extracted from filtered ECG data as features for identification. After dimension reduction by principal component analysis, Back Propagation Neural Networks was used as classifier. Finally, identification results were determined by voting mechanism. The results showed that, accuracy of classification can reach up to 99.6% using the method proposed in this paper. Besides, this method surpasses other researches in a comprehensive way by considering aspects such as the number of leads, data set, complexity and accuracy.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115758671","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073374
Shan Xue, Yong Zhang, Jin Cheng, Qinjun Zhao
With the development of science and technology, mobile robots have more and more extensive applications to complete the task in unknown environment. Create the environmental map of the unknown space is a key to control and navigation of mobile robots. We focus on the related problems of topological map building in unknown environment. The main studies undertaken in this paper are listed as follows: firstly, the paper introduces the research background and points out the present problems of map building. Secondly, topological map is built based on thinning algorithm which is commonly used in image processing of recognition. This avoids producing un-necessary nodes and paths. The environment is modeled in grid map, next the thinning algorithm is applied in the map, and then the effective topological information is extracted. Finally, simulation results show that the topological map based on thinning is clear, simple and effective. Moreover this topological map reduces information storage memory. This will improve the ability of autonomous operation, navigation and path planning further.
{"title":"Topological map building for mobile robots based on thining algorithm","authors":"Shan Xue, Yong Zhang, Jin Cheng, Qinjun Zhao","doi":"10.1109/ICCWAMTIP.2014.7073374","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073374","url":null,"abstract":"With the development of science and technology, mobile robots have more and more extensive applications to complete the task in unknown environment. Create the environmental map of the unknown space is a key to control and navigation of mobile robots. We focus on the related problems of topological map building in unknown environment. The main studies undertaken in this paper are listed as follows: firstly, the paper introduces the research background and points out the present problems of map building. Secondly, topological map is built based on thinning algorithm which is commonly used in image processing of recognition. This avoids producing un-necessary nodes and paths. The environment is modeled in grid map, next the thinning algorithm is applied in the map, and then the effective topological information is extracted. Finally, simulation results show that the topological map based on thinning is clear, simple and effective. Moreover this topological map reduces information storage memory. This will improve the ability of autonomous operation, navigation and path planning further.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123227908","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073387
Songbian Zime
Economic performance evaluation and classification is an important and challenging issue and has been gaining attention the last three decades of academic research, monetary institutions groups and business development. The purpose of this paper is to propose a hybrid model which combines support vector machine with isometric feature mapping (ISOMAP), Principal Component Analysis (PCA) and Locally Linear Embedding (LLE) utilized as a preprocessor in order to improve countries economic performance evaluation and classification capability by support vector machine. The results show that our hybrid approach SMV+ISOMAP only not has the best classification rate, but also produces the lowest incidence of Type II errors and have the excellent Receiver Operating Characteristic (ROC) curve. In addition it's capable to provide on time the economic performance classification for better investment and government decisions.
{"title":"Economic performance evaluation and classification using hybrid manifold learning and support vector machine model","authors":"Songbian Zime","doi":"10.1109/ICCWAMTIP.2014.7073387","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073387","url":null,"abstract":"Economic performance evaluation and classification is an important and challenging issue and has been gaining attention the last three decades of academic research, monetary institutions groups and business development. The purpose of this paper is to propose a hybrid model which combines support vector machine with isometric feature mapping (ISOMAP), Principal Component Analysis (PCA) and Locally Linear Embedding (LLE) utilized as a preprocessor in order to improve countries economic performance evaluation and classification capability by support vector machine. The results show that our hybrid approach SMV+ISOMAP only not has the best classification rate, but also produces the lowest incidence of Type II errors and have the excellent Receiver Operating Characteristic (ROC) curve. In addition it's capable to provide on time the economic performance classification for better investment and government decisions.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131540255","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 : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073396
Mushtaq Ali, Le Dong, Yan Liang, Zongyi Xu, Ling He, Ning Feng
Segmentation of multi-panel figure caption into subfigure captions and text labels is a problem that arises in a number of applications particularly in estimating the total number of panels in the multi-panel figure. The results of the existing methods for solving this problem are unsatisfactory and need improvement. Moreover, these methods are computationally expensive. In this paper, we propose a novel algorithm for the segmentation of multi-panel figure caption. This algorithm needs two inputs, i.e., multi-panel figure caption to be segmented and text label type. Upon receiving these two inputs it will extracts text labels and subfigure captions from the given multi-panel figure caption. We implemented the proposed algorithm and evaluated its results on 100 multipanel figure captions collected from 100 research papers. From the results we observed 100% accuracy for the text label types containing two or more than two characters.
{"title":"A novel algorithm for extracting text labels and subfigure captions from multi-panel figure caption","authors":"Mushtaq Ali, Le Dong, Yan Liang, Zongyi Xu, Ling He, Ning Feng","doi":"10.1109/ICCWAMTIP.2014.7073396","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073396","url":null,"abstract":"Segmentation of multi-panel figure caption into subfigure captions and text labels is a problem that arises in a number of applications particularly in estimating the total number of panels in the multi-panel figure. The results of the existing methods for solving this problem are unsatisfactory and need improvement. Moreover, these methods are computationally expensive. In this paper, we propose a novel algorithm for the segmentation of multi-panel figure caption. This algorithm needs two inputs, i.e., multi-panel figure caption to be segmented and text label type. Upon receiving these two inputs it will extracts text labels and subfigure captions from the given multi-panel figure caption. We implemented the proposed algorithm and evaluated its results on 100 multipanel figure captions collected from 100 research papers. From the results we observed 100% accuracy for the text label types containing two or more than two characters.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131161813","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：