Sketch Segmentation Using m-Adjacency

Abstract

Abstract: Sketches are hand-drawn informal sketch often created as a way of thinking about or working through a problem. Sketch recognition requires real time processing; where the speed of the classifier is an important parameter. Image or sketch segmentation is an important step in any image processing application. Extensive research has been done in creating different approaches and algorithms for image segmentation, but it is still difficult to find out that one algorithm produces more accurate segmentations result than other, whether it will be for a particular image or set of images, or more generally, for a whole class of images. In this study, we have proposed m-adjacency technique for image or sketch segmentation. In the proposed technique, filtering is not required, which reduces the pre-processing time to a great extent.

Keywords: Sketch segmentation, m-adjacency, classification, ROI (Reason of Interest), sketch recognition

Cite this Article: Bhupesh Kumar Singh, Dimpy Gambhir. Sketch Segmentation Using m-Adjacency. Journal of Advancements in Robotics. 2019; 6(3): 29–40p.