期刊
PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND COMMUNICATION
卷 458, 期 -, 页码 459-466出版社
SPRINGER-VERLAG SINGAPORE PTE LTD
DOI: 10.1007/978-981-10-2035-3_47
关键词
Handwritten digit recognition; Indic scripts; Mojette transform; Principal component analysis; Multiple classifiers
Handwritten Digit Recognition (HDR) has become one of the challenging areas of research in the field of document image processing during the last few decades. It has wide variety of applications including reading the amounts in cheque, mail sorting, reading aid for the blind and so on. In this paper, an attempt is made to recognize handwritten digits written in four different scripts namely, Bangla, Devanagari, Arabic and Telugu using Mojette transform. The Principal Component Analysis (PCA) is then applied for dimensionality reduction of the feature vector and also shortening the training time. Finally, a 48-element feature vector is tested on CMATERdb3 handwritten digit databases using multiple classifiers and an average overall accuracy of 98.17 % is achieved using Multi Layer Perceptron (MLP) classifier.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据