An Algorithm of Feather and Down Target Detection and Tracking Method Based on Sparse Representation

Feather and down products are becoming more and more popular. In recent years, the research team has done the down automatic detection and recognition by computer. In order to raise the recognition rate of feather and down category, in the paper a goal down image detection adaptive sparse representation and tracking method based on image is proposed, and target detection is used to determine the feather and down category. First of all, after the study, proposed improved adaptive sparse expression theory, and related features in the study of down on the image, the adaptive sparse representation theory and the multi-scale geometric analysis theory is applied to image recognition algorithm. The research will build a new adaptive sparse expression theory system, improve the robustness of the feather of image recognition, and will promote the target tracking technology innovation.

[1]  Yanqiu Wang,et al.  A revised feather and down recognition model based on MOAA SVM , 2010, 2010 2nd IEEE International Conference on Information Management and Engineering.

[2]  Hanseok Ko,et al.  Real-time multi-cue mean-shift hand tracking algorithm in cluttered background , 2011, 2011 4th International Congress on Image and Signal Processing.

[3]  Liu Chao,et al.  A software pattern of the Genetic Algorithm , 2009, Wuhan University Journal of Natural Sciences.

[4]  Xiaofei Yan,et al.  A Feather and Down Category Recognition System Based on GA and SVM , 2009, 2009 International Conference on Education Technology and Computer.

[5]  Robert T. Collins,et al.  Mean-shift blob tracking through scale space , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[6]  Tong Xuefeng Application Research of SVM for Small-set Off-line Handwritten Chinese Characters Recognition , 2002 .

[7]  Alper Yilmaz,et al.  Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.