Title :
Planar shape recognition across multiple views
Author :
Kuthirummal, Sujit ; Jawahar, C.V. ; Narayanan, P.J.
Author_Institution :
Centre-for Visual Inf. Technol., Int. Inst. of Inf. Technol., Hyderabad, India
Abstract :
Multiview studies in computer vision have concentrated on the constraints satisfied by individual primitives such as points and lines. Not much attention has been paid to the properties of a collection of primitives in multiple views, which could be studied in the spatial domain or in an appropriate transform domain. We derive an algebraic constraint for planar shape recognition across multiple views based on the rank of a matrix of Fourier domain descriptor coefficients of the shape in different views. We also show how correspondence between points on the boundary can be computed for matching shapes using the phase of a measure for recognition.
Keywords :
computer vision; image recognition; matrix algebra; object recognition; Fourier domain descriptor coefficients; algebraic constraint; computer vision; multiple views; planar shape recognition; shapes matching; spatial domain; transform domain; Calibration; Computer vision; Fourier transforms; Geometry; Information technology; Layout; Marine vehicles; Object recognition; Shape; Transmission line matrix methods;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1044757