دانلود رایگان مقاله انگلیسی تشخیص پلاک خودرو با استفاده از شبکه عصبی بازگردنده به عقب و الگوریتم ژنتیک - الزویر 2017

Abstract

Plate recognizer system is an important system. It can be used for automatic parking gate or automatic ticketing system. The purpose of this study is to determine the effectiveness of Genetic Algorithms (GA) in optimizing the number of hidden neurons, learning rate and momentum rate on Backpropagation Neural Network (BPNN) that is applied to the Automatic Plate Number Recognizer (APNR). Research done by building a GA optimized BPNN (GABPNN) and APNR system using image processing methods, including grayscale conversion, top-hat transformation, binary morphological, Otsu threshold and binary image projection. The tests conducted with backpropagation training and recognition test. The result shows that GA optimized backpropagation neural network requires 2230 epochs in the training process to be convergent, which is 36.83% faster than nonoptimal backpropagation neural network, while the accuracy is 1,35% better than non-optimized backpropagation neural network.

8. Conclusion

In this paper, genetic algorithm was used to find the optimal number of hidden neuron, learning rate, and momentum rate. GABPNN has faster training time and require less epoch in the training process to reach the designated mean square error than BPNN, therefore, it needs less CPU time in the training process, leads to efficiency of CPU time. GABPNN also has a better recognition accuracy. Despite of the speed, it has slower feedforward time due to the number of hidden neuron.

Further research is needed to determine which variables of the BPNN or combination of those variables should be optimized and what methods and operations should be used in the GA process to find better and optimal result. We suggest the researchers to implement more robust pre-processing methods that can locate the number plate adaptively.