COAL ENGINEERING ›› 2016, Vol. 48 ›› Issue (5): 115-118.doi: 10.11799/ce201605036

Previous Articles     Next Articles

A method of mine shaft disease recognition based on improved active contour model

  

  • Received:2016-02-01 Revised:2016-02-18 Online:2016-05-10 Published:2016-06-15

Abstract: In the images of mine shaft, there are many problems such as the low image contrast, the more image noises and the low efficiency of image segmentation accuracy. In order to solve these problems, we propose an improved active contour model based on image enhancement and regularization constraint. The image enhancement can improve the image contrast, expand the dynamic range of gray value, and reduce the noise effect. The regular constraints include the length constraint, the area constraint and the distance function constraint. They can reduce the influence of initial contour on the evolution of the curve, realize the contour curve to move quickly to the target boundary, and end up with the edge of the target. Experimental results show that the proposed model is superior to the C-V model and LBF model in the performance and segmentation results. This model can recognize the mine shaft diseases quickly and accurately, which can improve the degree of automation of mine shaft inspection.

CLC Number: