Title :
Detection the object figure in the line drawing by using cross correlation
Author_Institution :
Fac. of Eng., Kyushu Inst. of Technol., Kitakyushu, Japan
fDate :
6/21/1905 12:00:00 AM
Abstract :
The line figure is analyzed by cross correlation of complex valued function which represents line segment. The similarity of line figure is defined by cross correlation of the complex valued functions which represent the line figures. The similarity is invariant to the rotation of figure. The local feature of figure is also detected by using cross correlation of complex valued function which represent line segment. The local feature shows the feature of a part of the line figure, that is, the similarity to the line segment and the direction in which the similarity is the maximum. The local similarities of the object figure to the line figures in the line drawings are calculated. By using the local similarity and slant angle of line segment to the object, we make the composite figure similar to the object. We calculate the similarity of the object figure and the composite figure, and then detect the object figure in the line drawing by evaluating the similarities
Keywords :
computational geometry; image processing; object detection; complex valued functions; cross correlation; line drawing; line figure; local similarity; object figure detection; slant angle; Computer vision; Engineering drawings; Feature extraction; Image processing; Image recognition; Image segmentation; Metalworking machines; Object detection; Shape; Spline;
Conference_Titel :
Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7803-5731-0
DOI :
10.1109/ICSMC.1999.825379