1. Handwritten digit recognition system using flda and support vector machines
Authors : Ravi Babu Uppu, Dinesh Reddy Kanchala
Pages : 596-608
DOI : http://dx.doi.org/10.21172/1.71.086
Keywords : Handwritten digit recognitionSVMFLDAMNIST DatabaseImage features
Abstract :
Handwritten Character Recognition (HCR) is the task of recognizing the characters which are present in a digital image of handwritten text. The present paper proposes a novel approach for handwritten digit recognition system. The present paper extracts digit image features based on Fisher Linear Discriminant Analysis (FLDA) and derives classify the digit images using Support Vector Machines (SVM). The present paper mainly concentrates on extraction of features from digit image for effective recognition of the numeral. To find the effectiveness of the proposed method it is tested on MNIST database, CENPARMI, CEDAR and newly collected data. The proposed method is implemented on more than one lakh digit images and gets good comparative recognition results. The percentage of the recognition achieved is about 96.97%.
Citing this Journal Article :
Ravi Babu Uppu, Dinesh Reddy Kanchala, "Handwritten digit recognition system using flda and support vector machines", Volume 7 Issue 1 - May 2016, 596-608
Click here to Submit Copyright Takedown Notice for this article.