Title :
A novel method for detecting and localising of reflectional and rotational symmetry under weak perspective projection
Author :
Yiwu, Lei ; Cheong, Wong Kok
Author_Institution :
Sch. of Appl. Sci., Nanyang Technol. Univ., Singapore
Abstract :
A novel method is proposed for detecting and recovering the pose of a reflectional and rotational symmetry from a single weak perspective image. In our paradigm, an effective and novel Hough-based approach is proposed for extracting skew symmetric axes from edge contours. For each of the detected skew symmetric axes and its corresponding skew angle, an intuitive mathematical formulation is devised for evaluating the geometric relationships between an orthogonal junction formed by a symmetric axis and its perpendicular axis in an original plane and its corresponding skew angle in an affine plane. The derived geometric formulation is integrated into an effective voting scheme for estimating the projective parameters of a reflectional and rotational planar shape using the information of the plausible skew symmetry axes. Experimental results are presented to verify the computational performance of the proposed paradigm
Keywords :
Hough transforms; computational geometry; computer vision; edge detection; feature extraction; image reconstruction; object recognition; Hough transform; edge detection; feature extraction; geometry; image recovery; localisation; orthogonal junction; reflectional symmetry; rotational symmetry; skew symmetric axes; weak perspective projection; Application software; Computer vision; Graphics; Image analysis; Image edge detection; Image storage; Object detection; Parameter estimation; Shape; Voting;
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-8186-8512-3
DOI :
10.1109/ICPR.1998.711170