Offline Handwritten Character Identification technique
Journal: IPASJ International Journal of Electronics & Communication (IIJEC) (Vol.3, No. 8)Publication Date: 2015-09-01
Abstract
ABSTRACT During this paper, associate economical Offline Hand Written Character Recognition algorithmic program is projected supported Associative Memory internet (AMN). The AMN employed in this work is largely motorcar associative. The implementation is applied utterly in ‘C’ language. to form the system perform to its best with stripped computation time, a Parallel algorithmic program is additionally developed using associate API package OpenMP. Characters ar in the main English alphabets (Small (26), Capital (26)) collected from system (52) and from totally different persons (52). The characters collected from system ar accustomed train the AMN and characters collected from totally different persons ar used for testing the recognition ability of cyberspace. The careful analysis showed that the network recognizes the hand written characters with recognition rate of seventy two.20% in average case. However, in best case, it acknowledges the collected hand written characters with eighty eight.5%. The developed network consumes three.57 sec (average) in Serial implementation and one.16 sec (average) in Parallel implementation using OpenMP.
Other Latest Articles
- Importance of Information classification in the Data Manning
- Optimization of CMOS based Analog Circuit Using Particle Swarm Optimization Algorithm
- Case study of routing protocol in MANET
- Importance of Search Engine Optimization in online business growth
- A study of Software Prevention technique based on mutation testing
Last modified: 2015-09-05 14:04:23