Apply Neural Networks to Morse Code Recognition

Abstract

Computer has been successfully used as a tool in a variety of fields. However, most applications of computer products are designed for able persons, and are inaccessible to the disabled. Since the unadapted computer keyboard is not a suitable communication tool for physically disabled persons with such disabilities as muscle atrophy, cerebral palsy, and severe handicap. In this paper, the Morse code is selected as a communication adaptive device for entering Mandarin chanjei symbols into a computer. Although a stable typing rate is strictly required for an accurate recognition of Mandarin chanjei Morse code, maintaining this rate is a challenge for the disabled. Therefore, a suitable adaptive automatic recognition method is needed. The method presented here is divided into five stages: space recognition, tone recognition, learning process, adaptive processing, and character recognition. Experimental results revealed that the proposed method generated high recognition rate.