The video-audio information fusion analysis based on the improved algorithm of MFA-MGR

摘要：

For the Multi-modal nature of the video information, was proposed an fusion analysis algorithm to improve the accuracy and efficiency of video retrieval which used the Multi-modal features of video. The new approach using the variety features are extracted, using the latest MFA dimension reduction algorithm to dimensionality reduction, according to the variety of feature vectors using SVM classification, then using improved MGR algorithm to fusion analysis. The results show that the improved MGR algorithm reducing the actual number of parameters and improved the efficiency of recognition.

关键词： multimedia information retrieval improved MGR algorithm information Fusion dimension reduction

作者: FENG Xiu-fang WANG Jing

作者单位: College of Computer Science and Technology Taiyuan University of technology Taiyuan China

会议类型: 国际会议

会议名称: 2010 4th International Conference on Intelligent Information Techonlogy Application(第四届智能信息技术应用国际学术研讨会 IITA 2010)

会议地点: 秦皇岛

会议语种:英文

页码: 319-322

在线出版日期: 2010-11-05（万方平台首次上网日期，不代表论文的发表时间）