Line detection of parts using local uncertainty measure and local RHT in noised images

The integration of local uncertainty measure with local randomized Hough transform (RHT) is proposed for line detection in the paper to tackle the problems of decrease in detection accuracy in noised images for line detection of complicated parts. The proposed scheme firstly partitions a machine-part into several regions. Then a probability model of uncertainty that an edge pixel belongs to a line is built and accumulated uncertainty measures for lines, formed by any random selected pair of two edge points, are computed according to two point combination and Bayesian rule. Lines are finally detected using soft voting in parameter spaces. The capability of anti-noise and fast processing speed is the key feature of the algorithm. Experimental results show that accuracy error of proposed method less than 1% when noise variance equals to 0.06 and detection accuracy could reach 90%.