Detection and Extraction of Discontinuous Lines

A new algorithm for detecting and extracting discontinuous lines is presented against the shortcomings of the usual method for lines extraction. Firstly almost all of the line segments were acquired by the means of Hough transform, and then the line segments were grouped by the method of improved dynamic clustering algorithm. The improvement of the dynamic clustering algorithm are the initial cluster is based on the method of the standardized pattern transform and a kernel of every class replaces the centre of the class as the patterns of every class obey the norm distribution. In the next step the line segments belong to the same group are fitted into possible longer lines and the long lines´ existence is further defined by judging whether the total number of marginal points in the neighbourhood of the lines is large enough or not. At last, the redundant lines are also excluded by the means of dynamic clustering algorithm. Experiments demonstrate that the proposed algorithm is valid.