Title :
Object identification by Hough data verification
Author :
Ueno, Kazuki ; Yamaguchi, Jun´ichi
Author_Institution :
Fac. of Eng., Kagawa Univ., Takamatsu, Japan
Abstract :
In this paper, the authors describe on the method of object identification by verification of Hough data. In this study, for corresponding to three-dimension change of camera, we pay attention to the distribution pattern of Hough data. A positional relationship of the peaks as Hough data shows tendency to be kept, in case of camera shooting condition change. Using the characteristic of Hough data, it is possible to verify the three dimensional object with lines. In this study, distribution pattern of Hough data is verified by Matched filter. A simple test on object identification using house images is performed. As a result, it was confirmed that our method is useful for identification of three-dimensional object.
Keywords :
Hough transforms; image recognition; matched filters; object recognition; Hough data verification; camera shooting condition; distribution pattern; house image; matched filter; object identification; three dimensional object; Accuracy; Cameras; Correlation; Fourier transforms; Matched filters; Object recognition; Camera shooting condition; Hough transform; Image verification; Matched filter;
Conference_Titel :
SICE Annual Conference 2010, Proceedings of
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-7642-8