Abstract
The automatic recognition of text on scanned images has enabled many applications, which are based on the single character recognition. In this paper, handwritten Nepali character recognition strategy using artificial immune system and wavelet packet transform was proposed and carefully experimented. The preliminary experiment has been done on the consonant character using artificial immune system. With 116 feature coefficients extracted from 32*32 Nepali character image as its feature vector, which 84 were from wavelet packet transform and 32 achieved by horizontal and vertical histogram, consonant antibody libraries for its character categories were trained and built to recognize handwritten Nepali consonant characters with artificial immune algorithm. The contrast experiment was done using three-tiered feed-forward, back-propagation neural network model with 116 feature coefficients as input, 36 hidden nodes and 31 output nodes for consonant category, sigmoid transfer function. The experimental results indicated that the artificial immune system model has more advantages than BP neural network in character recognition.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
