A Novel Illumination Invariant Feature Extraction Method Based on Improved Local-Gravity-Face

Xin Chen, Xiwei Peng, Jin Tang, Bai Luo

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

In recent years, face recognition technology has made great progress and achieved high accuracy. In the case of extreme illumination changes, the accuracy of face recognition drops sharply. Based on Local-Gravity-Face(LG face), an excellent illumination invariant feature extraction method, this paper proposes an improved LG face and a novel distance measurement method. Combined with Gamma Correction and Difference of Gaussian (DOG) filtering, it achieves a high correct recognition rate on Yale B+, and reduces the amount of calculation, thus can achieve real-time detection.

源语言英语
主期刊名Proceedings of the 40th Chinese Control Conference, CCC 2021
编辑Chen Peng, Jian Sun
出版商IEEE Computer Society
7143-7147
页数5
ISBN(电子版)9789881563804
DOI
出版状态已出版 - 26 7月 2021
活动40th Chinese Control Conference, CCC 2021 - Shanghai, 中国
期限: 26 7月 202128 7月 2021

出版系列

姓名Chinese Control Conference, CCC
2021-July
ISSN(印刷版)1934-1768
ISSN(电子版)2161-2927

会议

会议40th Chinese Control Conference, CCC 2021
国家/地区中国
Shanghai
时期26/07/2128/07/21

指纹

探究 'A Novel Illumination Invariant Feature Extraction Method Based on Improved Local-Gravity-Face' 的科研主题。它们共同构成独一无二的指纹。

引用此