Title :
Biologically inspired template matching using scene context
Author :
Gao, Changxin ; Sang, Nong
Author_Institution :
Inst. for Pattern Recognition & Artificial Intell., Huazhong Univ. of Sci. & Technol., Wuhan, China
Abstract :
Template matching is widely used in pattern recognition and computer vision. However, the performance of traditional template matching approaches is often sensitive to large intraclass variance, occlusion, minor variety of poses, low-resolution conditions, background clutter etc. To resolve the problem, this paper presents a scene context based template matching method, which is inspired from two biological plausible ways, scene-centered viewpoint and change blindness phenomenon. The proposed method is quite different form conventional template matching methods, since this technique measures the similarity of a template and a sub-image by putting both into scene context, in a semantic representation. This work focuses on object detection task using only one object instance without training. Extensive experiments on three datasets and a video clearly show the superior robustness of the proposed method.
Keywords :
image matching; object detection; text analysis; biologically inspired template matching; computer vision; object detection; pattern recognition; scene centered viewpoint; text based template matching method; Blindness; Clutter; Context; Databases; Humans; Layout; Robustness;
Conference_Titel :
Computer Vision and Pattern Recognition Workshops (CVPRW), 2011 IEEE Computer Society Conference on
Conference_Location :
Colorado Springs, CO
Print_ISBN :
978-1-4577-0529-8
DOI :
10.1109/CVPRW.2011.5981776