发明名称 |
Face recognition method and device |
摘要 |
The present invention provides a face recognition method and device. The method includes: performing down-sampling of different sizes on an original face image; performing block partition processing on a down-sampled image and the original face image; extracting feature of each image block; performing similarity matching between the extracted feature of each image block and features of image blocks corresponding to a pre-registered face image to obtain a similarity of each image block; and obtaining a face image recognition result according to an obtained similarity between all the image blocks. According to the face recognition method and device, down-sampling of different sizes is performed on an original face image, which increases a capability of face image features to describe the face image; a face image recognition result is obtained according to a similarity between all the obtained image blocks, which increases an accuracy of face image recognition. |
申请公布号 |
US9405969(B2) |
申请公布日期 |
2016.08.02 |
申请号 |
US201414444611 |
申请日期 |
2014.07.28 |
申请人 |
Huawei Technologies Co., Ltd. |
发明人 |
Niu Shengshi;Shan Shiguang;Li Yan |
分类号 |
G06K9/00;G06K9/62;G06K9/68;G06K9/46 |
主分类号 |
G06K9/00 |
代理机构 |
|
代理人 |
|
主权项 |
1. A face recognition method, comprising:
obtaining an original face image to be recognized; performing down-sampling on the original face image to obtain at least one down-sampled image whose size is different from a size of the original face image; performing block partition processing on each down-sampled image and the original face image to obtain at least two image blocks on which block partition processing is performed; extracting features of the image blocks on which block partition processing is performed to obtain features of the image blocks; wherein extracting features of the image blocks on which block partition processing is performed to obtain features of the image blocks comprises:
performing local binary pattern (LBP) descriptor extraction on each image block on which block partition processing is performed to obtain an LBP histogram of each image block; andextracting, according to the LBP histogram of each image block, a feature vector of each image block on which block partition processing is performed; performing similarity matching between the feature of each image block and features of image blocks corresponding to a pre-registered face image to obtain a similarity of each image block; and obtaining a face image recognition result according to an obtained similarity between all the image blocks. |
地址 |
Shenzhen CN |