Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Handwritten character recognition is still a research challenge in OCR discipline, especially for Indian scripts. The recognition of handwriting however, is still considered as an open research problem due to its substantial variation in appearance. The goal of OCR is to classify optical patterns in an image to the corresponding characters. There are different OCR techniques like Online Handwritten Malayalam Character Recognition using LIBSVM in Matlab. Here real time (x,y) coordinates per stroke are acquired and preprocessed. Directional and Curvature features are extracted and trained in LIBSVM, a tool for SVM Classifers. Testing alphabet is given online to the trained SVM network and the recognized label is displayed in Notepad. Another method proposed is a two-stage approach. The first stage is a group classifier, where a group consists of similar characters and those that misclassify among themselves. In the second stage, a character assigned to a group in the first stage is classified to a particular character class. Another method proposed is Off-line Handwritten Character Recognition using Hidden Markov Model. Training and recognition are performed using Hidden Markov Model Toolkit. Recognition process involves several steps including image acquisition, dataset preparation, pre-processing, feature extraction, training and recognition. An average accuracy of about 81.38% has been obtained. Thus the proposed system is done in python using convolutional neural network. It takes less processing time and has an accuracy of 95%.
Keywords:
Optical Character Recognition, Support Vector Machine, Convolutional Neural Network, Machine Learning
Cite Article:
"IDENTIFICATION AND CONVERSION OF HANDWRITTEN MALAYALAM SCRIPTS USING CONVOLUTIONAL NEURAL NETWORKS", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.2, Issue 3, page no.103 - 112, March-2017, Available :http://www.ijrti.org/papers/IJRTI1703022.pdf
Downloads:
000205347
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator