A Study of Image Weak-Edge Detection Combination of BP Neural Networks
This paper proposes an image weak-edge detection method based on the combination of edge features and BP neural networks. Through analyzing the basic characteristics of the image edge points, we construct 8 groups 3-D feature vectors as the training sample set, combining with the learning function based on gradient descent momentum and the Levenberg-Marquardt training function, to train the BP neural network, further complete the image edge detection. Finally, compared with the traditional edge detection methods, the experimental results show that this method can detect the weak-edge and corner-edge much better.
Helen Zhang, Gang Shen and David Jin
J. B. Yang et al., "A Study of Image Weak-Edge Detection Combination of BP Neural Networks", Advanced Materials Research, Vols. 225-226, pp. 21-25, 2011