Blob indentation identification via curvature measurement
This addresses a specific shape analysis problem in computer vision or image processing, likely for applications like object recognition or quality inspection, and appears incremental as it builds on existing curvature-based methods with a tuning parameter.
The paper tackles the problem of identifying indentations on 2D shape boundaries by using signed curvature measurements, with an efficient Fourier transform-based implementation for calculating curvature from binary blob data.
This paper presents a novel method for identifying indentations on the boundary of solid 2D shape. It uses the signed curvature at a set of points along the boundary to identify indentations and provides one parameter for tuning the selection mechanism for discriminating indentations from other boundary irregularities. An efficient implementation is described based on the Fourier transform for calculating curvature from a sequence of points obtained from the boundary of a binary blob.