The optical character recognition (OCR) is known to be one of the earliest applications of artificial intelligence. Genetic algorithm, which partially emulate human thinking in the domain of artificial intelligence, has been used in this study for OCR. Dealing with hundreds of features in character recognition systems is not unusual. This large number of features leads to the increase of computational workload of recognition process. There have been many methods which try to remove unnecessary or redundant features and reduce feature dimensionality. Experimental results show that application of genetic algorithms (GA) to features selection in a Marathi OCR results in lower computational complexity and enhanced recognition rate.