By Topic

Scale and rotation invariant pattern recognition using complex-log mapping and translation invariant neural network

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Heung-Ho Lee ; Dept. of Electr. Eng., Chung Nam Nat. Univ., Taejon, South Korea ; Hee-Yong Kwon ; Hee-Yeung Hwang

In this paper, we propose a scale and rotation invariant pattern recognition system using complex-log mapping (CLM) and translation invariant neural network (TINN). CLM is very useful for extracting scale and rotation invariant features. However, the results are given in a wrap-around translated form, which requires subsequent wrap-translation invariant recognition steps. This problem can be solved by using an augmented second order neural network (SONN). It requires, however, a connection complexity O(n2) for input feature extraction which is too high to be implemented. The proposed method reduces the connection complexity to O(n*log(n)) by using TINN. Experimental results show that the recognition performance of the proposed method is almost the same as that of SONN while its network size is significantly reduced

Published in:

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on  (Volume:7 )

Date of Conference:

27 Jun-2 Jul 1994