Visual Recognition Based on Randomized Visual Dictionaries

摘要：

　　In visual recognition,Bag-of-Visual-Word(BoVW) method has been widely used due to its excellent categorization performance.However,the conventional BoVW method has problems of visual word synonymy and ambiguity,meanwhile its time efficiency decreases along with visual data scaling up.Thus,this paper proposes a visual recognition method based on randomized visual dictionaries.Firstly,we introduce E2LSH(Exact Euclidean Locality Sensitive Hashing) to cluster local feature points of training video key frames and construct a group of scalable randomized visual dictionaries.Secondly,based upon these randomized visual dictionaries,we train a group of SVM classifiers for each visual concept.Finally,a voting strategy is utilized to integrate opinions of SVM classifiers,thus accomplishing visual recognition.Experimental results show that compared to traditional BoVW method,our method achieves higher visual recognition accuracy,meanwhile guaranteeing acceptable time efficiency.

关键词： visual recognition E2LSH randomized visual vocabulary voting strategy

作者: Ruijie Zhang Bicheng Li Haolin Gao

作者单位: Department of Signal Analysis and Processing Zhengzhou Information Science and Technology Institute,Zhengzhou 450002, China

会议类型: 国际会议

会议名称: 2012 IEEE 14th International Conference on Communication Technology(2012年第十四届通信技术国际会议(ICCT 2012))

会议地点: 成都

会议语种:英文

页码: 1610-1614

在线出版日期: 2012-11-09（万方平台首次上网日期，不代表论文的发表时间）