Precision assessment in tracking of moving vehicle using region based convolutional neural network compared over convolutional neural network

Aim: Licence Plate detection is a challenging task as it plays a significant role in applications like security and traffic control. To detect the number plate of the vehicles which violate the traffic rules using Region based convolutional networks compared over Convolutional Neural Network. Materials and methods: In this work Number plates are identified by Regi on based convolutional neural networks with the sample size of 22 and convolutional neural networks of sample size 22. The number plate of the vehicle will be detected and converted into string format. Results: A prediction accuracy of 97.7% using the method region based convolutional neural network was achieved while the convolutional neural network was 93.5%. The significance value obtained in statistical analysis is 0.01(p<0.05). Conclusion: The results show that identification of number plates is significantly better in Convolutional Neural Network than in Region based convolutional neural networks.