![Sample our Engineering & Technology journals, sign in here to start your access, latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5933/TOC-Subject-Sample-2021-Engineering-Tech.jpg"})
Abstract
An algorithm has been presented here for the recognition of mixed font English numerals. In the first stage of the algorithm pre-processing operations like thinning, smoothing, etc. are carried on the input pattern. In the next stage, the size of the numeral is determined, which is followed by extraction of features. In the feature-extraction phase, some special points like true end points, true group points and true cross points are extracted. Finally, a multilevel decision tree has been used for the purpose of classification. The recognition algorithm has been tested using a large number of different fonts of input token patterns with a recognition rate of more than 95%.
Additional information
Notes on contributors
A.K. Ray
Ray, Ajoy Kumar: (b 1954 Feb. 26). Received B.E. from Calcutta University in 1975 and M. Tech. from I.I.T., Kharagpur in 1977. He has worked in a DST sponsored Project on Pattern Recognition and Picture Processing. Presently he is on the faculty of the Department of Electronics & Electrical Communication Engineering, I.I.T., Kharagpur. His research interests are in Pattern Recognition, Image Processing and Control Systems.