Please use this identifier to cite or link to this item:
https://elibrary.tucl.edu.np/handle/123456789/7811
Title: | Nepali Character and Word Recognition using Neural Network |
Authors: | Pandey, Ram Chandra |
Keywords: | Neural Network,;Nepali Handwritten Datasets,;Handwriting Recognition. |
Issue Date: | Oct-2016 |
Publisher: | Pulchowk Campus |
Institute Name: | Institute of Engineering |
Level: | Masters |
Citation: | Department of Electronics and Computer Engineering |
Abstract: | The OCR systems developed for the Nepali language carry a very poor recognition rate due to error in character segmentation, ambiguity with similar character, unique character representation style. The purpose of this thesis work is to take image of handwritten or printed Nepali characters and words as input, process the character, train the neural network algorithm, to recognize the pattern and convert to digital form of the input. In this thesis, proposing an OCR for Nepali text in Devanagari script, using multi-layer feed forward back propagation Artificial Neural Network (ANN), which will improve its efficiency and accuracy. Adaptive learning rate with Gradient descent algorithm is proposed in Neural net with two hidden layers used with input and output and MMSE is the performance criteria. Various classifiers for training characters need to be created and stored. |
Description: | The OCR systems developed for the Nepali language carry a very poor recognition rate due to error in character segmentation, ambiguity with similar character, unique character representation style. |
URI: | https://elibrary.tucl.edu.np/handle/123456789/7811 |
Appears in Collections: | Electronics and Computer Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
069MSCS661.pdf | 1.53 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.