For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Sub-Category Optimization through Cluster Performance Analysis for Multi-View Multi-Pose Object Detection
Dipankar DAS Yoshinori KOBAYASHI Yoshinori KUNO
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2011/07/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
sub-category optimization, cluster performance analysis (CPA), object detection and localization, unsupervised clustering, chi-square merging kernel,
Full Text: PDF>>
The detection of object categories with large variations in appearance is a fundamental problem in computer vision. The appearance of object categories can change due to intra-class variations, background clutter, and changes in viewpoint and illumination. For object categories with large appearance changes, some kind of sub-categorization based approach is necessary. This paper proposes a sub-category optimization approach that automatically divides an object category into an appropriate number of sub-categories based on appearance variations. Instead of using predefined intra-category sub-categorization based on domain knowledge or validation datasets, we divide the sample space by unsupervised clustering using discriminative image features. We then use a cluster performance analysis (CPA) algorithm to verify the performance of the unsupervised approach. The CPA algorithm uses two performance metrics to determine the optimal number of sub-categories per object category. Furthermore, we employ the optimal sub-category representation as the basis and a supervised multi-category detection system with χ2 merging kernel function to efficiently detect and localize object categories within an image. Extensive experimental results are shown using a standard and the authors' own databases. The comparison results reveal that our approach outperforms the state-of-the-art methods.