摘要：Nowadays, the applications developed in the imaging area have focused on image measurement and compression, facial recognition, blurring, or image enhancement, to name a few. Among these activities, shape descriptors play an important role in describing the topology of an object and determining its general and local characteristics. Despite the large number of studies carried out, the idea of a robust shape descriptor remains a difficult problem, the challenges that hinder shape recognition are due to transformations such as rotations, scaling, deformations caused by noise or occlusions. This article presents the development of a descriptor based on the use of curvature, with this procedure, the dimensionality of the data is reduced so that the variability of the shapes can be described or explained by means of characteristics, and through neural networks associates these features and thus discriminates one type of object from another.
