Normalized co-occurrence mutual information for facial pose detection inside videos

Qing, Chunmei and Jiang, Jianmin and Yang, Zhijing (2010) Normalized co-occurrence mutual information for facial pose detection inside videos. IEEE Transactions on Circuits and Systems for Video Technology, 20 (12). 1898 -1902. ISSN 1051-8215

Documents
Normalized_Co-occurrence_Mutual_Information_for_Facial_Pose_Detection_inside_Videos.pdf
[img]
[Download]
Request a copy
[img] PDF
Normalized_Co-occurrence_Mutual_Information_for_Facial_Pose_Detection_inside_Videos.pdf - Whole Document
Restricted to Repository staff only

551kB

Full text URL: http://dx.doi.org/10.1109/TCSVT.2010.2087550

Abstract

Human faces captured inside videos are often presented with variable poses, making it difficult to recognize and thus pose detection becomes crucial for such face recognition under non-controlled environment. While existing mutual information (MI) primarily considers the relationship between corresponding individual pixels, we propose a normalized co-occurrence mutual information in this letter to capture the information embedded not only in corresponding pixel values but also in their geographical locations. In comparison with the existing MIs, the proposed presents an essential advantage that both marginal entropy and joint entropy can be optimally exploited in measuring the similarity between two given images. When developed into a facial pose detection algorithm inside video sequences, we show, through extensive experiments, that such design is capable of achieving the best performances among all the representative existing techniques compared.

Item Type:Article
Additional Information:Human faces captured inside videos are often presented with variable poses, making it difficult to recognize and thus pose detection becomes crucial for such face recognition under non-controlled environment. While existing mutual information (MI) primarily considers the relationship between corresponding individual pixels, we propose a normalized co-occurrence mutual information in this letter to capture the information embedded not only in corresponding pixel values but also in their geographical locations. In comparison with the existing MIs, the proposed presents an essential advantage that both marginal entropy and joint entropy can be optimally exploited in measuring the similarity between two given images. When developed into a facial pose detection algorithm inside video sequences, we show, through extensive experiments, that such design is capable of achieving the best performances among all the representative existing techniques compared.
Keywords:Co-occurrence matrix, facial pose detection, mutual information, normalized co-occurrence mutual information
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
Divisions:College of Science > School of Engineering
ID Code:4017
Deposited By:INVALID USER
Deposited On:13 Feb 2011 19:39
Last Modified:18 Jul 2011 16:38

Repository Staff Only: item control page