Invention Grant
US07164781B2 Method and apparatus of recognizing face using 2nd-order independent component analysis (ICA)/principal component analysis (PCA)
有权
使用二阶独立分量分析(ICA)/主成分分析(PCA)识别面部的方法和装置
- Patent Title: Method and apparatus of recognizing face using 2nd-order independent component analysis (ICA)/principal component analysis (PCA)
- Patent Title (中): 使用二阶独立分量分析(ICA)/主成分分析(PCA)识别面部的方法和装置
-
Application No.: US10377752Application Date: 2003-03-04
-
Publication No.: US07164781B2Publication Date: 2007-01-16
- Inventor: Hyun-woo Kim , Tae-kyun Kim , Seok-cheol Kee , Jong-ha Lee , Won-jun Hwang , Chang-kyu Choi
- Applicant: Hyun-woo Kim , Tae-kyun Kim , Seok-cheol Kee , Jong-ha Lee , Won-jun Hwang , Chang-kyu Choi
- Applicant Address: KR Suwon
- Assignee: Samsung Electronics Co., Ltd.
- Current Assignee: Samsung Electronics Co., Ltd.
- Current Assignee Address: KR Suwon
- Agency: Buchanan Ingersoll & Rooney PC
- Priority: KR10-2002-0011428 20020304; KR10-2002-0059141 20020928
- Main IPC: G06K9/00
- IPC: G06K9/00

Abstract:
A method and apparatus for recognizing and searching for a face using 2nd-order independent component analysis (ICA) are provided. The method includes performing PCA on an input original image and generating a low-pass filtered image by removing high-frequency component from the original image, subtracting the low-pass filtered image from the original image and obtaining residual image having only frequency-components, and performing ICA on the residual image and generating feature information corresponding to the original image. While an original ICA subtracts independent components (i.e., independent basis components) from gray scale images, the proposed 2nd-order ICA is robust to illumination variation since it is applied to make the remaining images correspond to high pass frequency components.
Public/Granted literature
Information query