High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Multi-Language Handwritten Character Recognition using Artificial Neural Networks

Author(s):

Suraj S Kumar , Mount Zion College of Engineering; Hari S, Mount Zion College of Engineering

Keywords:

Handwritten Character Recognition, Artificial Neural Networks

Abstract

Construction of an Optical Character Recognition (OCR) model for handwritten documents poses many challenges, the most prominent of them being dataset collection, character segmentation and classification. In this paper we recognize individual characters from multi language handwritten documents. We take Malayalam and English for recognition. Our approach has five stages, preprocessing, line detection, word detection, character segmentation and classification. First extract individual lines from the document then words from each line, and then characters from each word. Masking is performed to tackle the overlapping of character bounding boxes due to skewed lines and the presence of diacritics. The segmented characters fed to ANN model for recognition.

Other Details

Paper ID: IJSRDV8I40526
Published in: Volume : 8, Issue : 4
Publication Date: 01/07/2020
Page(s): 493-497

Article Preview

Download Article