Lingyu Yan, H. Ling, Dengpan Ye, Chunzhi Wang, Z. Ye, Hongwe Chen
{"title":"Feature fusion based hashing for large scale image copy detection","authors":"Lingyu Yan, H. Ling, Dengpan Ye, Chunzhi Wang, Z. Ye, Hongwe Chen","doi":"10.1080/18756891.2015.1046332","DOIUrl":"https://doi.org/10.1080/18756891.2015.1046332","url":null,"abstract":"Most of existing approaches use only a single feature to represent an image for copy detection. However, a single feature is often insufficient to characterize the image content. Besides, with the exponential growth of online images, it's urgent to explore a way of tackling the problem of large scale. In this paper, we propose a feature fusion based hashing method which effectively utilize the correlation between two feature models and efficiently accomplish large scale image copy detection. To accurately map images into the Hamming space, our hashing method not only preserves the local structure of individual feature but also globally consider the local structures for all the features to learn a group of hash functions. The experiment results show that the proposed method outperforms the state-of-the-art techniques in both accuracy and efficiency.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"100 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134420703","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}
{"title":"A novel system identification in networked environment","authors":"Hongwei Wang, Shan Sun","doi":"10.1109/ICICIP.2014.7010276","DOIUrl":"https://doi.org/10.1109/ICICIP.2014.7010276","url":null,"abstract":"This paper is motivated by the practical modeling considerations of linear time-invariant systems working in a networked environment. Specifically, we limit the problem to off-line identification of open-loop stable continuous time systems in network. The identification problem is formulated under the configuration of event-driven actuators subject to random network induced delays and packet dropouts; the associated networked identification is based on the general non-uniformly sampled data. According to deal with colored process noise and unknown initial conditions, we proposed a modified version of the generalized linear least squares algorithm with a filter to estimate the parameters of the system model. A simulation example is presented to demonstrate the performance of the proposed algorithm.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133152830","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}
{"title":"Improved fast marching method applied on purkinje fibers extraction","authors":"Jie Li, Weigang Lu","doi":"10.1109/ICICIP.2014.7010301","DOIUrl":"https://doi.org/10.1109/ICICIP.2014.7010301","url":null,"abstract":"Purkinje system provides a significant insight into understanding the mechanisms of cardiac pathophysiologies. Extraction of anatomical detailed purkinje fiber network, however, is a very challenging task. In this paper, we present an improved fast marching method for extracting the purkinje fibers in the image. The purkinje network is grown by an iterative algorithm that distributes seed points according to an oriented field. Results show that the method solves robustly the problem of the crossing point.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130745532","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}
{"title":"Output feedback sampled-data stabilization of a class of uncertain nonlinear systems","authors":"Zhihui Wang, J. Zhai, S. Fei","doi":"10.1109/ICICIP.2014.7010339","DOIUrl":"https://doi.org/10.1109/ICICIP.2014.7010339","url":null,"abstract":"This paper investigates the problem of using a sampled-data controller to globally stabilize a class of uncertain nonlinear systems whose output functions are not precisely known. To solve the problem, we first construct a new sampled-data observer and then use the output feedback domination approach to design a linear sampled-data controller. An explicit formula for the maximum allowable sampling period is computed to guarantee global stability of the uncertain nonlinear systems under the proposed controller with appropriate gains.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132245698","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}
{"title":"A hybrid edge detection model of extreme learning machine and cellular automata","authors":"Min Han, Xue Yang, Enda Jiang","doi":"10.1109/ICICIP.2014.7010351","DOIUrl":"https://doi.org/10.1109/ICICIP.2014.7010351","url":null,"abstract":"For remote sensing image, whose spectral signatures are intricate, the traditional edge detection methods cannot obtain satisfactory results. This paper takes the space computing capacity of Cellular Automata (CA) and the data pattern search ability of Extreme Learning Machine (ELM) into account and puts forward a new hybrid edge detection model based on Extreme Learning Machine and Cellular Automata (ELM-CA) for remotely sensed imagery. This model can extract evolution rules of cellular automata. On the basis of the rules, false edges are removed and purer edge map is obtained. The result of the simulation experiment shows that the performance of method suggested by this paper is much better compared to other edge detection arithmetic operators. It can prove that ELM-CA is an ideal method of remote sensing image edge detection.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132819976","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}
{"title":"A missing data estimation approach for small size image sequence","authors":"Zhanli Sun, Yuan Fang, L. Shang, Xiantan Zhu","doi":"10.1109/ICICIP.2014.7010304","DOIUrl":"https://doi.org/10.1109/ICICIP.2014.7010304","url":null,"abstract":"Data missing is a frequently encountered problem for structure-from-motion (SFM). In this paper, a sub-sequence based approach is proposed to deal with the missing data estimation problem for small size image sequence. In the proposed method, the sub-sequences are first extracted from the original sequence. Further, multiple weaker estimators are constructed by means of the column space fitting (CSF) algorithm. Finally, the missing entries are estimated by a linear programming based weighted model. Experimental results on several widely used image sequences demonstrate the effectiveness and feasibility of the proposed algorithm.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116639571","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}
{"title":"Adaptive fault estimation for interconnected nonlinear system with triangular forms","authors":"Lei Liu, Zhanshan Wang","doi":"10.1109/ICICIP.2014.7010264","DOIUrl":"https://doi.org/10.1109/ICICIP.2014.7010264","url":null,"abstract":"In this paper, a novel fault detection and estimation methodology is proposed for a class of interconnected nonlinear continues-time systems with triangular forms. In the distributed fault detection and estimation architecture, a local fault detector is utilized to generate a residual between the subsystem and its detector or observer. Moreover, a threshold for distributed fault detection and estimation in each subsystem are designed. Due to the universal approximation capabilities of the radial basis function neural networks, it is used to estimate the unknown fault dynamics. Finally, the proposed methods are verified in the simulation.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127468752","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}
{"title":"Toeplitz-structured measurement matrix construction for chaotic compressive sensing","authors":"Fuhua Fan","doi":"10.1109/ICICIP.2014.7010279","DOIUrl":"https://doi.org/10.1109/ICICIP.2014.7010279","url":null,"abstract":"There could be difficulties in construction of random measurement matrix. A deterministic method is therefore proposed to construct hybrid chaotic map sparse toeplitz-structured (HcmST) matrix for compressive sensing in this paper. It is proved that HcmST matrix, generated based on hybrid chaos map sequence and its uniform sampling with large interval, meets the RIP characteristic with high probability. Simulation experiments show that HcmST matrix is of low accumulative coherence, and hence, support accurate signal reconstruction.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129139860","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}
{"title":"DNA coding and central dogma based image encryption using vigenere cipher and chaos map","authors":"Linlin Zhang, Tiegang Gao, Rui Yang","doi":"10.1109/ICICIP.2014.7010318","DOIUrl":"https://doi.org/10.1109/ICICIP.2014.7010318","url":null,"abstract":"In this paper, a new image encryption algorithm which base on DNA coding and genetic central dogma, combined with 3-dimensional Vigenere cipher and chaos mapping is proposed. In the proposed scheme, every pixel in original image is represented by four nucleotide bases by carrying out DNA coding. An amino acid matrix is obtain by implementing transcript and translation according to central dogma after randomly eliminating a base from each pixel; substitute the amino acid matrix by using 3-dimensional Vigenere cipher and a new codon matrix is gotten; a semi-finished encrypted image appears after decoding the nucleotide base matrix which is composed by the new codon matrix and the eliminated bases mentioned above; finally the encrypted image is obtained by disturbing image pixels with Logistic chaotic sequence. The proposed algorithm has a large secret key space and strong secret key sensitivity, meanwhile it can effectively resist exhaustive attack and statistical attack. The simulation results show the perfect effect compared with some existing algorithms.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130741807","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}
{"title":"The application of heat supply information network platform based on C/S and B/S models","authors":"Wenbiao Wang, Qi Cai, Siyuan Wang, Xudong Wang","doi":"10.1109/ICICIP.2014.7010267","DOIUrl":"https://doi.org/10.1109/ICICIP.2014.7010267","url":null,"abstract":"Aiming at the problems of some heat supply systems for the measuring points are widely distributed and the data transferring protocols are various, so it's difficult to summarize the heat supply information data. Therefore, some unified communication protocols and network interfaces were used to improve the problems of the heat supply systems in this paper. In this paper, C/S and B/S models were used to build the heat supply information network platform, KingView and WinCC configuration software were used to monitor the heat supply data, Modbus and OPC communication protocols were used to achieve the tasks of the heat supply data transferring between the clients and the servers. Finally, the heat supply data were published on the Internet by Web, it's really convenient for the managers to browse the heat supply information and guide the heating supply so as to improve the heat supply quality.","PeriodicalId":408041,"journal":{"name":"Fifth International Conference on Intelligent Control and Information Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130990450","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}