Recognition of English Handwritten Characters and Digits using Genetic Algorithm

Abstract

Many researchers have worked on recognition of printed characters, numerals but a very little amount of
work is available on handwritten character recognition. Handwritten Character Recognition is one of the most complex
and tricky field in the field of pattern recognition. Variety of works has been done for English languages having various
recognition rates because of different shape and writing styles of individuals. There are enumerable styles in which a
character may be written. The idea of genetic algorithm comes from the fact that it can be used as an outstanding means
of combining various styles of writing a character and generates new styles. Closely observing the ability of human mind
in the recognition of handwriting, it is found that humans are able to recognize characters even though they might be
seeing that style for the first time. This is possible because of their power to visualize parts of the known styles into the
unknown character. In the proposed work, the same power is represent into the machines by using genetic algorithm.