Title : 
A novel approach based on saliency edges to contour detection
         
        
            Author : 
Dou, Yan ; Kong, Lingfu
         
        
            Author_Institution : 
Coll. of Inf. Sci. & Eng., Yanshan Univ., Qinhuangdao
         
        
        
        
        
        
            Abstract : 
A novel approach based on saliency edges to detect contour is presented. It included two components. One was edges detection and edges linking based on Gestalt rules; the other was contour detection based on saliency edges. The approach had three advantages, it was very simple to compute; it was very robust to noise, and it was easy to extend to a high stage of computer vision. A lot of experiments in real images show that the proposed approach works reasonably.
         
        
            Keywords : 
computer vision; edge detection; Gestalt rules; computer vision; contour detection; edge detection; edge linking; real images; saliency edges; Brightness; Computer vision; Detectors; Image edge detection; Image segmentation; Noise reduction; Noise robustness; Object detection; Object recognition; Shape;
         
        
        
        
            Conference_Titel : 
Audio, Language and Image Processing, 2008. ICALIP 2008. International Conference on
         
        
            Conference_Location : 
Shanghai
         
        
            Print_ISBN : 
978-1-4244-1723-0
         
        
            Electronic_ISBN : 
978-1-4244-1724-7
         
        
        
            DOI : 
10.1109/ICALIP.2008.4590011