Title :
Boundary Driven Interactive Segmentation
Author_Institution :
Dept. of Comput. Sci., Weizmann Inst. of Sci., Rehovot, Israel
Abstract :
This paper presents a novel approach and interface to interactive image segmentation. Our interface uses sparse and inaccurate boundary cues provided by the user to produce a multi-layer segmentation of the image. Using boundary cues allows our interface to utilize a single "boundary brush" to produce a multi-layer segmentation, making it appealing for devices with touch screen user interface. Our method utilizes recent advances in clustering to automatically recover the underlying number of layers without explicitly requiring the user to specify this input.
Keywords :
image segmentation; interactive systems; pattern clustering; touch sensitive screens; user interfaces; boundary brush; boundary driven interactive segmentation; clustering; image multilayer segmentation; inaccurate boundary cues; interactive image segmentation; sparse boundary cues; touch screen user interface; Brushes; Clustering algorithms; Correlation; Image segmentation; Partitioning algorithms; Switches; Vectors;
Conference_Titel :
Information Science and Applications (ICISA), 2012 International Conference on
Conference_Location :
Suwon
Print_ISBN :
978-1-4673-1402-2
DOI :
10.1109/ICISA.2012.6220955