Method of Blob detection based on radon transform

Blob has been widely used in image matching, target identification, and target tracking, etc., which makes efficient Blob detection a fundamental research subject in computer vision applications. Inspired by Radon transform and taking the geometric characteristics of Blob into account, a Blob detection method is proposed in this paper. Firstly, a definition of the Blob response function is given, which is used to implement the statistics of intensity variations along the edges on both sides of the Blob. Then taking the calculated function value as the energy of the Blob center, the Blob is extracted by comparing the empirical threshold with the function value. Some experiments are carried out, and the results indicate that the proposed method can not only locate the position of Blobs with speed and accuracy, but also possess a good robustness to noises.