| |
Online ISSN:1349-8606 |
| Progress in Informatics |
|
| No.7 March 2010 |
|
| Page 63-70 |
PDF(1,784KB) | References |
| doi:10.2201/NiiPi.2010.7.8 |
| Associating faces and names in Japanese photo news articles |
| Akio KITAHARA1 and Keiji YANAI2 |
| 1,2The University of Electro-Communications
|
(Received: October 14, 2009)
(Revised: December 14, 2009)
(Accepted: January 4, 2010)
|
Abstract:
We propose a system which extracts faces and person names from news articles with photos on theWeb and associates them automatically. The system detects face images in news photos with a face detector and extracts person names fromnews text with a morphological analyzer. In addition, the bag-of-keypoints representation 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 at most regarding association of faces and names.
|
Keywords:
Web photo news, face detection, face recognition, eigenface, name extraction, associating names and faces
|
|
|
| PDF(1,784KB) | References |
National Institute of Informatics is a member of CrossRef.
|
