Part Recognition Based on Maximum Mutual Information

Abstract:

Article Preview

A new approach to the problem of part recognition is proposed by using maximum mutual information. The method applies entropy to measure image feature, combined with color information and local shape information, and uses mutual information as a new matching criterion between the images for image recognition. This method solves the problem that histogram algorithm can not represent the spatial information. This method not only has the feature of translation invariant, but also avoids image segmentation which may lead to a complex calculation, so it can be realized easily. The result shows that proposed approach is accuracy, stability, and reliability in the processing of machine part image recognition.

Info:

Periodical:

Key Engineering Materials (Volumes 407-408)

Edited by:

Fan Rui, Qiao Lihong, Chen Huawei, Ochi Akio, Usuki Hiroshi and Sekiya Katsuhiko

Pages:

234-238

DOI:

10.4028/www.scientific.net/KEM.407-408.234

Citation:

S. Ge and D. G. Huang, "Part Recognition Based on Maximum Mutual Information", Key Engineering Materials, Vols. 407-408, pp. 234-238, 2009

Online since:

February 2009

Authors:

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.