Handwritten Amharic Text Recognition Applied To The Processing Of Bank Cheques

The advent and wide application of Information Technology (IT) has brought changes onrnthe way we perform things. One area where IT particularly computers has showedrnsignificant improvement in efficiency and effectiveness of activities is by handling routine,rnrepetitive, boring and error prone tasks. Among such tasks bank check reading is the onernthat can be handled by computers in a stable manner using the OCR technology.rnIn this piece of work an attempt was made to adopt a recognition algorithm forrnhandwritten Amharic text. To achieve this target some preprocessing. segmentation andrnnormalization techniques implemented for other scripts were reviewed. The Feature ojrnhand printed Amharic text in general and hand printed legal amounts in particular werernstudied. Based on the identified Features some of the preprocessing. segmentation andrnnormalization algorithms were implemented and tested on a set of hand printed datarncollected using sample checks. In addition, different feed forward neural networks withrnback-propagation learning algorithm were implemented and the test results as well as thernprocedure of the test are recorded. Finally recommendations are forwarded pointing outrnsome points for further consideration.

Get Full Work

Report copyright infringement or plagiarism