Share Email Print

Optical Engineering

Effective approach for object recognition based on voting
Author(s): Tong-Wei Lu; Nong Sang; Jizhong Liu; Xiaoying Gao
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Object recognition can be formulated as matching image features to model features. When recognition is patch-based, the feature correspondence is one to one. However, due to noise, repetitive structures, and background clutter, features do not match one to one, but one to many. By using the multiscale feature point technique, a new object recognition algorithm is presented to identify the center, scale, and orientation of the objects in the images. This approach recognizes the objects the presence of translation, scale variation, rotation, partial occlusion, and changed viewpoint. It does not require that features match one to one, and maintains the structure information of the object. This is accomplished by voting on the object's center, scale factor, and orientation for each match point. Experimental results demonstrate that the method works well with translation, rotation, scale changes, and partial occlusion, but gives less accurate results when the viewpoint is altered.

Paper Details

Date Published: 1 January 2008
PDF: 5 pages
Opt. Eng. 47(1) 017203 doi: 10.1117/1.2835457
Published in: Optical Engineering Volume 47, Issue 1
Show Author Affiliations
Tong-Wei Lu, Huazhong Univ. of Science and Technology (China)
Nong Sang, Huazhong Univ. of Science and Technology (China)
Jizhong Liu
Xiaoying Gao

© SPIE. Terms of Use
Back to Top