Feasibility of Efficient Number Plate Recognition using Morphological Dilation and Support Vector Machine

Abstract

Intelligent data acquisition of vehicle number plate plays a significant role to recognize a vehicle and it automatic parking, traffic movement and scheduling, tracking of stolen vehicle, and many more. Although different methodologies of automatic number plate reading have developed alongwith their algorithms, still an efficient number plate recognition technique for better segmentation and recognition of the captured number plate using Morphological Dilation and Support Vector Machine (SVM) are expected to be helpful. In this paper, we present a modified method for recognition of contents of number plate using morphological dilation and SVM. We have compared our results with those from the existing models using Wavelet Transform and Artificial Neural Network techniques. Superiority of present methodology is established using parameters like image segmentation and recognition.