Title :
CUDA Implementation of Deformable Pattern Recognition and its Application to MNIST Handwritten Digit Database
Author :
Mizukami, Yoshiki ; Tadamura, Katsumi ; Warrell, Jonathan ; Li, Peng ; Prince, Simon
Author_Institution :
Grad. Sch. of Sci. & Eng., Yamaguchi Univ., Ube, Japan
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.
Keywords :
handwriting recognition; image classification; CUDA; MNIST handwritten digit database; deformable pattern recognition; distance maps; horizontal displacement; k-nearest neighbor classifier; line segment curvature; nearest foreground pixel; prototype-parallel displacement computation; regularization technique; vertical displacement; Character recognition; Databases; Error analysis; Mathematical model; Pixel; Prototypes; compute unified device architecture; displacement computation; graphics processing unit; handwritten character recognition;
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-7542-1
DOI :
10.1109/ICPR.2010.493