Multi-scale image analysis for detection of characteristic component figure shapes and sizes

A method which detects the characteristic shapes and sizes of image structures is proposed. The method first blurs an image by Gaussian filters with various scales. Then, at every scale, principal curvatures of the image gray-level profile are calculated for every position. As the scale changes, the principal curvatures change. We detect the inherent shapes and sizes of the image structures by characterizing the type of the change of the principal curvatures. For the detection, we introduce the idea of principal curvature plane spanned by the two principal curvatures as its Cartesian coordinates