A Riemanian Approach to Blob Detection in Manifold-Valued Images
This work addresses a domain-specific problem in image processing for manifold-valued data, presenting an incremental extension of grayscale blob detection techniques.
The paper tackles blob detection in manifold-valued images by introducing Riemannian blob response functions based on image graph curvatures, and demonstrates its application in chemical compounds classification.
This paper is devoted to the problem of blob detection in manifold-valued images. Our solution is based on new definitions of blob response functions. We define the blob response functions by means of curvatures of an image graph, considered as a submanifold. We call the proposed framework Riemannian blob detection. We prove that our approach can be viewed as a generalization of the grayscale blob detection technique. An expression of the Riemannian blob response functions through the image Hessian is derived. We provide experiments for the case of vector-valued images on 2D surfaces: the proposed framework is tested on the task of chemical compounds classification.