Handwritten Devanagari Character Recognition using Neural Network
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2014, Vol 16, Issue 2
Abstract
Abstract: In this digital era, most important thing is to deal with digital documents, organizations using handwritten documents for storing their information can use handwritten character recognition to convert this information into digital. Handwritten Devanagari characters are more difficult for recognition due to presence of header line, conjunct characters and similarity in shapes of multiple characters. This paper deals with development of grid based method which is combination of image centroid zone and zone centroid zone of individual character or numerical image. In feature extraction using grid or zone based approach individual character or numerical image is divided into n equal sized grids or zones then average distance of all pixels with respect to image centroid or grid centroid is computed. In combination of image centroid and zone centroid approach it computes average distance of all pixels present in each grid with respect to image centroid as well as zone centroid which gives feature vector of size 2xn features. This feature vector is presented to feed forward neural network for recognition. Complete process of Devanagari character recognition works in stages as document preprocessing, segmentation, feature extraction using grid based approach followed by recognition using feed forward neural network.
Authors and Affiliations
Ms. Seema A. Dongare , Prof. Dhananjay B. Kshirsagar , Ms. Snehal V. Waghchaure
Keywords
Related Articles
- EP ID EP99722
- DOI 10.9790/0661-162107479
- Views 91
- Downloads 0
An Overview of Spectrum Sensing and its Techniques
Abstract: Cognitive radio networks provide high bandwidth to mobile users via heterogeneous wireless architectures and dynamic spectrum access techniques. It basically avoids congestion in wireless communicatio...
HiRLoc: High-resolution Robust Localization for Wireless Sensor Networks
In this paper the tiny nodes are deployed in target areas according to the deployment nature of target but nodes are easily targeted by attacker with physical attack of node capture. So, secure,communications in som...
ncremental Mining of Sequential Patterns Using Weights
Real life sequential databases are usually not static. They tend to grow incrementally. So after every update a frequent pattern may no longer remains frequent while some infrequent patterns may appear as frequen...
MSESEP- Mobile Sink Based ESEP using Reliable Cluster Head and Sorting Technique
Abstract: The Wireless Sensor Network (WSN) is composed of sensors. These sensor nodes sense the physical parameters like temperature, pressure, humidity etc. In real time environment these sensors have different energie...
WMNs: The Design and Analysis of Fair Scheduling
Abstract: In this paper an attempt has been made to address the matter of scheduling in wireless mesh networks. First, we offer a comparison of existing scheduling algorithms and then classify them based on the schedulin...