Vehicle number plate identification (VNPI) is an imperative task for resolving the increasing traffic issues around the world. Although many studies were conducted in the past, there are still many challenges to be answered where noisy image acquisition conditions, improper illumination or poor quality images, are a few to name. In the light of the same, an efficient vehicle number plate classification model is the need of the hour. Since, image processing techniques are best suited for resolving the problems of noisy dataset; these are used for noise elimination, image segmentation, feature extraction, and classification purposes in this research. So, in this article, a two-step approach, using region based segmentation and feature extraction to feed as input to the system for classifying the vehicle number plates, has been designed.  The proposed bi-step VNPI model very well extracted the segments around the characters with extraction rate of 96.69% and recognition rate of 95.34%. Experimental results show that the proposed technique is simple and robust. The results are comparable with the results of the state-of-art methods available in the literature.