A Conformal Mapping based Shape Signature for Object Recognition
نویسنده
چکیده
A novel method for designing a signature based on the conformal mapping is proposed. Conformal mapping function preserves the local angles of the shape of the object. Schwarz Christoffel mapping transformation is effectively implemented. A conformal transformation of the upper half plane onto the interior of a simple polygon is carried out. The widely used in 2-D potential flow for the computation of the complex potential of the flow by a line source located in a two dimensional channel is familiarized. A novel Complex Potential Source (CPS) descriptor for the shape based object recognition is designed. CPS is mediated through the Fourier transformation during the description stage, while the feature vector is generated. The CPS descriptor uses Chebyshev distance measure for the shape toning stage. It is experimented over the versatile MPEG7 CE-1 Set B database. The results witness the efficiency of the proposed method than that reported for other descriptors of contemporary interests. Key-Words: Schwarz Christoffel transformation, Fourier transformation, Distance, Feature Vector, Shape Toning and Performance Measures.
منابع مشابه
Conformal spherical representation of 3D genus-zero meshes
This paper describes an approach of representing 3D shape by using a set of invariant Spherical Harmonic (SH) coefficients after conformal mapping. Specifically, a genus-zero 3D mesh object is first conformally mapped onto the unit sphere by using a modified discrete conformal mapping, where the modification is based on Möbius Factorization and is aimed at obtaining a canonical conformal mappin...
متن کاملOptimization of Conformal Mapping Functions used in Developing Closed-Form Solutions for Underground Structures with Conventional cross Sections
Elastic solutions applicable to single underground openings usually suffer from geometry related simplification. Most tunnel shapes possess two axes of symmetry while a wide range of geometries used in tunneling practice involve only one symmetry axis. D-shape or horse-shoe shape tunnels and others with arched roof and floor are examples of the later category (one symmetry axis). In the present...
متن کامل3D Models Recognition in Fourier Domain Using Compression of the Spherical Mesh up to the Models Surface
Representing 3D models in diverse fields have automatically paved the way of storing, indexing, classifying, and retrieving 3D objects. Classification and retrieval of 3D models demand that the 3D models represent in a way to capture the local and global shape specifications of the object. This requires establishing a 3D descriptor or signature that summarizes the pivotal shape properties of th...
متن کاملA novel Local feature descriptor using the Mercator projection for 3D object recognition
Point cloud processing is a rapidly growing research area of computer vision. Introducing of cheap range sensors has made a great interest in the point cloud processing and 3D object recognition. 3D object recognition methods can be divided into two categories: global and local feature-based methods. Global features describe the entire model shape whereas local features encode the neighborhood ...
متن کاملShape representation via conformal mapping
Representation and comparison of shapes is a problem with many applications in computer vision and imaging, including object recognition and medical diagnosis. We will discuss some constructions from the theory of conformal mapping which provide ways to represent and compare planar shapes. It is a remarkable fact that conformal maps from the unit disk to a planar domain encode the geometry of t...
متن کامل