| Summary: | Optical character recognition is the process of converting characters from image format to text format. The process includes four main stages namely: pre-processing, feature extraction, character recognition, and post-processing. The success is mainly based on the feature extraction method and the character recognition algorithm. When optical character recognition systems are developed for mobile devices, two main constraints must be addressed. They are the system’s size and speed. In this research, both were considered. A small feature dataset was created using polar histogram of x and y projections of the character image. In addition, a simple character recognition algorithm based on Euclidean distance was adapted. An accuracy of over 99.9% was achieved in near microsecond scale recognizing execution time on the development system.
|
|---|