Title :
Associating Faces and Names in Japanese Photo News Articles on the Web
Author :
Kitahara, Akio ; Joutou, Taichi ; Yanai, Keiji
Author_Institution :
Univ. of Electro-Commun., Chofu
Abstract :
We propose a system which extracts faces and person names from news articles with photos on the Web and associates them automatically. The system detects face images in news photos with a face detector and extracts person names from news text with a morphological analyzer. In addition, the bag-of-keypoints technique is applied to the extracted face images for filtering out non-face images. The system uses the eigenface representation as image features of the extracted faces, and associates them with the extracted names by the modified k-means clustering in the eigenface subspace. In the experiment, we obtained the 66% precision rate regarding association of faces and names.
Keywords :
eigenvalues and eigenfunctions; face recognition; feature extraction; filtering theory; pattern clustering; text analysis; Japanese photo news articles; bag-of-keypoints technique; eigenface representation; face detector; face extraction; image filtering; modified k-means clustering; news photos; person names extraction; Application software; Computer science; Data mining; Detectors; Face detection; Face recognition; Image analysis; Image coding; Principal component analysis; TV;
Conference_Titel :
Advanced Information Networking and Applications - Workshops, 2008. AINAW 2008. 22nd International Conference on
Conference_Location :
Okinawa
Print_ISBN :
978-0-7695-3096-3
DOI :
10.1109/WAINA.2008.97
