Title
CUDA Implementation of Deformable Pattern Recognition and its Application to MNIST Handwritten Digit Database
Abstract
In this study we propose a deformable pattern recognition method with CUDA implementation. In order to achieve the proper correspondence between foreground pixels of input and prototype images, a pair of distance maps are generated from input and prototype images, whose pixel values are given based on the distance to the nearest foreground pixel. Then a regularization technique computes the horizontal and vertical displacements based on these distance maps. The dissimilarity is measured based on the eight-directional derivative of input and prototype images in order to leverage characteristic information on the curvature of line segments that might be lost after the deformation. The prototype-parallel displacement computation on CUDA and the gradual prototype elimination technique are employed for reducing the computational time without sacrificing the accuracy. A simulation shows that the proposed method with the k-nearest neighbor classifier gives the error rate of 0.57% for the MNIST handwritten digit database.
Year
DOI
Venue
2010
10.1109/ICPR.2010.493
ICPR
Keywords
Field
DocType
foreground pixel,deformable pattern recognition method,deformable pattern recognition,regularization technique,gradual prototype elimination technique,mnist handwritten digit database,cuda implementation,prototype image,nearest foreground pixel,distance map,pixel value,computer graphic,mathematical model,image classification,pixel,prototypes,handwriting recognition,pattern recognition,error rate,databases,directional derivative,k nearest neighbor
Line segment,MNIST database,CUDA,Computer science,Handwriting recognition,Artificial intelligence,Contextual image classification,Computer vision,Pattern recognition,Word error rate,Pixel,Graphics processing unit,Database
Conference
Citations 
PageRank 
References 
8
0.61
8
Authors
5
Name
Order
Citations
PageRank
Yoshiki Mizukami1648.94
Katsumi Tadamura215616.44
Jonathan Warrell349418.95
Peng Li480.61
Simon Prince591460.61