This paper proposes an image-preprocessing method combined with a fuzzy clustering algorithm and new validity measure to detect the vanishing point in an image. The proposed method segments the object in an image by using the clustering algorithm and then extracts critical vanishing lines. By examining the intersection of the vanishing lines, the vanishing point is located. To locate the vanishing point accurately, the initial cluster number of the fuzzy clustering algorithm should be provided correctly. Therefore, the study proposes a new clustering validity measure, the area measure, to estimate the initial cluster number according to the information of cluster areas. Experimental results on 29 images show that the proposed preprocessing method and validity measure can accurately identify the location of the vanishing point and vanishing lines. In addition, compared with several validity measures, the new validity measure achieves satisfactory experimental results and outperforms six other validity measures.
Journal of Applied Science and Engineering 18(2), pp.105-116