Abstract
This paper proposes an efficient scale and rotation invariant 2-D object recognition method using Complex-Log Mapping (CLM) and Translation Invariant Neural Network (TINN). CLM is known as very useful transform 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. Recently, a new method using an augmented second order neural network (SONN) was introduced as a solution. It requires, however, a connection complexity O(n/sup 2/) for input feature extraction which is too high to be implemented. In this paper, we propose a method reducing 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. >
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.