Image Similarity Matching Retrieval on Synergetic Neural Network
In this paper, an image similarity matching retrieval algorithm based on synergetic neural network (SNN) is proposed. It is a novel method with advantages of no pseudo-state and closer to natural self-organization process in the field of image retrieval. It utilizes feature vector extraction, attention parameter selection, order parameter calculation, pseudo-inverse matrix and its determinant value comparison to achieve better retrieval effect. Due to the structural characteristic of synergetic neural network, it can save time for iteration and improve efficiency and speed. The experimental results show that this algorithm has fast speediness, strong robustness and high accuracy, and provides greater generality and high real-time performance.
Hui Li Xiuli Ma Wanggen Wan Xueli Zhou
School of Communication and Information Engineering,Shanghai University, No.149 Yanchang Road,Shanghai 200072, China
国际会议
上海
英文
1566-1571
2010-10-20（万方平台首次上网日期，不代表论文的发表时间）