A BLOBS DETECTION ALGORITHM BASED ON A SIMPLIFIED FORM OF THE FAST RADIAL SYMMETRY TRANSFORM

Automatic blobs detection constitutes a basic but difficult problem. In this work a new fast blobs detection technique based on a scale-space representation of the original image, is proposed. The scale-space representation is constructed by using a new simplified form of the Fast Radial Symmetry Transform to precisely detect the essential blobs. From the experiments we have conducted, the proposed technique seems to outperform well known blobs detection methods such as the conventional FRST, Hough and SIFT based techniques, in both accuracy and detection rate. In addition, the proposed technique can be used for the automatic and perfect elimination of the well known Moire effect which substantially degrades the quality of radiography (x-ray) images.