effective solution for digital image edge detection based on artificial neural network

effective solution for digital image edge detection based on artificial neural network

in this paper, an artificial neural network system is used to identify the edges of digital images. in the proposed method, for each pair of image in the database (original image and real edge), a table containing edge and non-edge records is extracted.

then using the k-mean clustering algorithm, the average number of non-edge records should be reduced. by reducing the volume of records, the information in the tables is combined together and the training table for the neural network is created. to test the neural network by grabbing a gray image, it is divided block wise and each block is delivered to the neural network as an input, the neural network gives the output value as an edge or non-edge pixel. to analyze the results, different various metrics have been used to evaluate the result of the proposed method compared to other methods. the results of the implementation show that the proposed algorithm performs better than comparable methods.