Pavement distress detection is the base of highway maintenance. With crack being the main distress in the actual pavement surface, digital image processing has been widely applied to cracking recognition recently. This paper presents a novel artificial neural network based pavement cracking recognition method in the area of image processing. The novelty of our approach is to utilize self-studying feature of neural network to complete the cracking identification. By converting cracking recognition to the cracking probability judgment for every sub-block image, cracking trend could be calculated, and a method for revising the neural network output is proposed to increase accuracy of identification. Actual pavement images are used to verify the performance of this method, and the results show that the surface crack could be identified correctly and automatically.