Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Face Detection Algorithm Based on the Calculation of Vector Correlation

Wang,Shoujue Sun,Hua(Laboratory of Artificial Neural Networks,Institute of Semiconductors,Chinese academy of Sciences,Beijing 100083,China)  
In this paper,a new face detection algorithm is based on high dimensional imaginal geometry and biomimetics informatics(HDIGBI)has been proposed.HDIGBI is a brand new theory developed in recent years.From the viewpoint of vector correlation in high dimensional space,the difference of two images was analyzed It uses vector to present the image information and calculates the angle of two vectors as the metric of correlation of face candidate and mean face template.After the simulation experiment of the in-troduced algorithm and Euclidean Distance,it was theoretically analyzed and discussed that the proposed algorithm has apparently ad-vantage over the Euclidean Distance.Furthermore,in our experiments in color images,the improved new algorithm can get rid of confounding effect of illumination variation.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved