A New Algorithm on Mice Action Analysis

作者：Hong Liurong^*

来源：International Conference on Mechatronics and Applied Mechanics (ICMAM 2011), 2011-12-27 to 2011-12-28.

DOI：10.4028/www.scientific.net/AMM.157-158.494

• action analysis
• mice
• similarity
• change information
• K-Means algorithm

Mice action data is important part of the experimental data in neurology, physiological etc. subjects. A algorithm was proposed on action analysis of mice in this paper. Difference of mice in inter-frame was extracted while the position relationship between mice contours and change information was taken into account. Then K-Means clustering algorithm was used to cluster the information while the cluster center was used as the key frame. In the recognition phase, the similarity measure function was defined according to practical significance of the center of K-Means algorithm, the most similar sample class with it was the result. Experimental results showed that the action analysis algorithm is very effective.

• 出版日期2012
• 单位淮北师范大学