A comparative study of fuzzy evolutionary techniques for footprint recognition and performance improvement using wavelet–based fuzzy neural network. (26th August 2013)

• Record Type: Journal Article
• Authors: Kumar, V. Devadoss Ambeth; Ramakrishnan, M.
• Is Part Of: International journal of computer applications technology. Volume 48:Number 2(2013)
• Page Start: 95
• Page End: 105
• Publication Date: 2013-08-26
• Subjects: footprint recognition -- performance improvement -- wavelets -- region of interest -- ROI -- fuzzy neural networks -- FNN -- footprint images -- edge detection -- toe images; Technology -- Data processing -- Periodicals; 620.00285
• Languages: English
• ISSNs: 0952-8091

Abstract

Wavelet and fuzzy neural network is the technique used in the implementation of footprint recognition system. The transformation of the footprint image is done by the wavelet to detect the edge and then according to the statistical distribution disciplinarians of different toe images the membership functions are constructed, keeping the angle and length as parameters. These obtained values are used as single judgement factor. The input to the neural network is given by computing the distance vector between the four model vectors and the comprehensive judgement vector. Template matching is based on the resultant percentage, if it is above 70 then it returns the output as matched else it returns the output as invalid or no match found. Since this wavelet–based method is based on fuzzy neural network, it reflects the different shapes of toe image subjectively and correctively, the test results show noteworthy improvements in recognition rate.