Pixel distribution density based character recognition for vehicle license plate

In this paper, we present a new methodology for the image segmentation and character recognition from standard Indian number plates. This method differentiates between the characters on the basis of difference in pixel distribution density in different regions of the alphabets and numeric characters. It first recognizes character is belong to which group using Euler technique and which subgroup does the input belongs to and then tries recognizes the input by comparing the input with the critical regions that differentiate among the elements of the same subgroup. This method eliminates the problem of confusion between similar looking elements like C, G and T, I, 1, J etc by exploiting the small but important differences among them.