摘要 |
PURPOSE: A method for face description using first and second order eigenfeatures regardless of lighting and view-angle invariant is provided to interpret and recognize the human faces. CONSTITUTION: The 2-order eigenfeatures are used for lighting-invariant face description and both the 1-order and 2-order eigenfeatures are used for view-angle-invariant face description(420). After normalization and quantization, the features describe face effectively and efficiently. To reduce the size of face descriptor, variable length code is used to encode the quantized eigenfeatures(440). The method is used in internet multimedia database retrieval, digital library, video editing, surveillance and tracking, and other applications using face recognition and verification.
|