Share Email Print

Proceedings Paper

Improved maximum average correlation height filter with adaptive log base selection for object recognition
Author(s): Sara Tehsin; Saad Rehman; Ahmad Bilal Awan; Qaiser Chaudry; Muhammad Abbas; Rupert Young; Afia Asif
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Sensitivity to the variations in the reference image is a major concern when recognizing target objects. A combinational framework of correlation filters and logarithmic transformation has been previously reported to resolve this issue alongside catering for scale and rotation changes of the object in the presence of distortion and noise. In this paper, we have extended the work to include the influence of different logarithmic bases on the resultant correlation plane. The meaningful changes in correlation parameters along with contraction/expansion in the correlation plane peak have been identified under different scenarios. Based on our research, we propose some specific log bases to be used in logarithmically transformed correlation filters for achieving suitable tolerance to different variations. The study is based upon testing a range of logarithmic bases for different situations and finding an optimal logarithmic base for each particular set of distortions. Our results show improved correlation and target detection accuracies.

Paper Details

Date Published: 20 April 2016
PDF: 13 pages
Proc. SPIE 9845, Optical Pattern Recognition XXVII, 984506 (20 April 2016); doi: 10.1117/12.2223621
Show Author Affiliations
Sara Tehsin, National Univ. of Sciences and Technology (Pakistan)
Saad Rehman, National Univ. of Sciences and Technology (Pakistan)
Ahmad Bilal Awan, National Univ. of Sciences and Technology (Pakistan)
Qaiser Chaudry, National Univ. of Sciences and Technology (Pakistan)
Muhammad Abbas, National Univ. of Sciences and Technology (Pakistan)
Rupert Young, Univ. of Sussex (United Kingdom)
Afia Asif, Instanbul Sehir Univ. (Turkey)

Published in SPIE Proceedings Vol. 9845:
Optical Pattern Recognition XXVII
David Casasent; Mohammad S. Alam, Editor(s)

© SPIE. Terms of Use
Back to Top