Edge Detection Based On Machine Learning

Edge Detection is one important part of computer vision. This paper show a effective edge detection technique based on machine learning. This technique is build on Bayesian theory. Combining probability statistical learning and scene estimating, it can generate a complexing edge detection pattern. We call this technique EDBML. It is a Markov network, we confirm the transfer rule of this network based on two kind of relationship, one is the image and the scene, the other is the current scene and its neighbour. Learning parameters of this network come from training examples, we can obtain a exact local maximum of the posterior probability for the scene, thereby we generate a effective edge detection result for original blurry importing image.