TY - JOUR
T1 - Scale Invariance Based Salient Contour Detection
AU - Wang, Jing
AU - Ikenaga, Takeshi
AU - Goto, Satoshi
PY - 2007
Y1 - 2007
N2 - Contour detection is a fundamental step to scene analysis and interpretation. However, because contours often locate in rich texture background it is still a difficult task in realistic vision. Through multi-scale analysis, it becomes clear that edge responses of real object contours are relatively stable across scales, while those from noise or texture background are not. In this paper, a salient contour detection method is proposed based on the scale invariance of piecewise linear approximation of real object contours. Firstly, an image pyramid is efficiently constructed by repeatedly smoothing and sub-sampling the image. Secondly, the piecewise linear approximation of contours in multiple scales are extracted and then a collinear line grouping process is implemented to improve the connectivity of the contours. Thirdly, the new salient line segments are generated based on the analysis on the stability of line segments across scales. Experimental results show that the proposed method can effectively improve the connectivity and saliency of the contour detection compared with the former method.
AB - Contour detection is a fundamental step to scene analysis and interpretation. However, because contours often locate in rich texture background it is still a difficult task in realistic vision. Through multi-scale analysis, it becomes clear that edge responses of real object contours are relatively stable across scales, while those from noise or texture background are not. In this paper, a salient contour detection method is proposed based on the scale invariance of piecewise linear approximation of real object contours. Firstly, an image pyramid is efficiently constructed by repeatedly smoothing and sub-sampling the image. Secondly, the piecewise linear approximation of contours in multiple scales are extracted and then a collinear line grouping process is implemented to improve the connectivity of the contours. Thirdly, the new salient line segments are generated based on the analysis on the stability of line segments across scales. Experimental results show that the proposed method can effectively improve the connectivity and saliency of the contour detection compared with the former method.
KW - Piecewise Linear Approximation
KW - Salient Contour Detection
KW - Scale Invariance
KW - Texture Background
UR - http://www.scopus.com/inward/record.url?scp=85024732533&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85024732533&partnerID=8YFLogxK
U2 - 10.11371/iieej.36.710
DO - 10.11371/iieej.36.710
M3 - Article
AN - SCOPUS:85024732533
VL - 36
SP - 710
EP - 720
JO - Journal of the Institute of Image Electronics Engineers of Japan
JF - Journal of the Institute of Image Electronics Engineers of Japan
SN - 0285-9831
IS - 5
ER -