DocumentCode
3307428
Title
2D still-image segmentation with CNN-Amoeba
Author
Iannizzotto, Giancarlo ; La Rosa, Francesco ; Rizzo, Alessandro ; Xibilia, Maria Gabriella
Author_Institution
Dept. of Math., Messina Univ.
fYear
2003
fDate
12-16 May 2003
Lastpage
31
Abstract
This paper introduces a still image segmentation technique based on an active contour obtained via single-layer CNNs. The contour initially laid on the frame of the image shrinks, deforms and multiplies until it matches the edges of each of the objects present in the scene. The shape of each object in the image is accurately extracted and nested objects, if any, are correctly detected. Experimental measures of the accuracy of the segmentation were carried out using the Hausdorff distance
Keywords
cellular neural nets; image segmentation; 2D still image segmentation; CNN-Amoeba; Hausdorff distance; active contour; image shrinks; Active contours; Cellular neural networks; Hardware; Image edge detection; Image processing; Image segmentation; Layout; Mathematics; Object detection; Shape; 2-D image segmentation; CNNs; active contours;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Architectures for Machine Perception, 2003 IEEE International Workshop on
Conference_Location
New Orleans, LA
Print_ISBN
0-7803-7970-5
Type
conf
DOI
10.1109/CAMP.2003.1598145
Filename
1598145
Link To Document