Title :
Multi-scale adaptive segmentation using edge and region based attributes
Author :
McCane, Brendan ; Caelli, Terry
Author_Institution :
Dept. of Comput. Sci., James Cook Univ. of North Queensland, Townsville, Qld., Australia
Abstract :
The authors present an adaptive multi-scale algorithm using edge and region information for segmenting intensity images into closed regions. The need for segmentation is determined by region statistics and segmentation is actually performed using edge based information. Results are shown for a number of images displaying significant improvements over mono-scale segmentation
Keywords :
adaptive systems; edge detection; image segmentation; statistics; adaptive multi-scale algorithm; closed regions; edge based attributes; intensity image segmentation; multi-scale adaptive segmentation; region based attributes; region statistics; Australia; Character recognition; Computer science; Computer vision; Data mining; Image converters; Image segmentation; Layout; Object recognition; Statistics;
Conference_Titel :
Knowledge-Based Intelligent Electronic Systems, 1997. KES '97. Proceedings., 1997 First International Conference on
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-3755-7
DOI :
10.1109/KES.1997.616854
