Hierarchical Face Clustering using SIFT Image Features

Author

Antonopoulos, Panagiotis ; Nikolaidis, Nikos ; Pitas, Ioannis

Author_Institution

Dept. of Informatics, Aristotle Univ. of Thessaloniki

fYear

2007

fDate

1-5 April 2007

Firstpage

325

Lastpage

329

Abstract

In this paper an algorithm to cluster face images found in video sequences is proposed. A novel method for creating a dissimilarity matrix using SIFT image features is introduced. This dissimilarity matrix is used as an input in a hierarchical average linkage clustering algorithm, which yields the clustering result. Three well known clustering validity measures are provided to asses the quality of the resulting clustering, namely the F measure, the overall entropy (OE) and the Gamma statistic. The final result is found to be quite robust to significant scale, pose and illumination variations, encountered in facial images

Keywords

entropy; face recognition; feature extraction; image classification; image sequences; matrix algebra; pattern clustering; statistics; Gamma statistic; SIFT image features; dissimilarity matrix; face images; hierarchical average linkage clustering; hierarchical face clustering; overall entropy; video sequences; Clustering algorithms; Clustering methods; Couplings; Face detection; Face recognition; Hidden Markov models; Humans; Signal processing algorithms; Testing; Video sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence in Image and Signal Processing, 2007. CIISP 2007. IEEE Symposium on

Conference_Location

Honolulu, HI

Print_ISBN

1-4244-0707-9

Type

conf

DOI

10.1109/CIISP.2007.369189

Filename

4221439