Please use this identifier to cite or link to this item: https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/1612
Title: Off-Line Sinhala Handwritten Postal City Name Recognition Using Segmentation Free Algorithms
Authors: Anuradha, A .G.A.V.
Issue Date: 17-Dec-2013
Abstract: Offline handwriting recognition is still an open area in research community. And many researchers pay attention to this area since it is linked with lots of applications. This thesis considers offline Sinhala handwritten postal city name recognition using segmentation free algorithms. Four phases are carried out in this research such as preprocessing, feature detection, recognition and post processing. There are 7 stages in preprocessing phase namely noise removing, thresholding, detection of the rectangular area, skew detection, skew correction, underline removing and thinning. Feature detection techniques used here are horizontal projection profile histogram, vertical projection profile histogram and Gabor filter. 13 features are identified for each image by using those techniques. A feed forward neural network with one hidden layer is used. This is based on the supervised learning algorithm. There are 6 output nodes to classify 50 different postal cities. Data for the training set and testing set is received from the National Science Foundation (NSF) database which consists of Sinhala postal city names written by people for the real purpose as well as from students and some other people. The well trained neural network outputs a binary number which corresponds to the recognized city name. The post processing technique uses a Microsoft Access database which maps the decimal value of the binary number to the city name. It gives the recognized city name in a user readable manner. The accuracy of recognizing city name in this system is about 41%.And the system is implemented using Matlab 7.0.
URI: http://hdl.handle.net/123456789/1612
Appears in Collections:SCS Individual Project - Final Thesis (2008)

Files in This Item:
File Description SizeFormat 
2.pdf
  Restricted Access
1.25 MBAdobe PDFView/Open Request a copy


Items in UCSC Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.