Title :
Modified edge detection for segmentation
Author :
Baydoun, Mohammed ; Al-Alaoui, Mohamad Adnan
Author_Institution :
Electr., Comput. & Commun. Eng., American Univ. of Beirut, Beirut, Lebanon
Abstract :
Image segmentation is one of the major methods of image processing. Several techniques exist to tackle segmentation related ideas based on the targeted area of interest. Edge detection is another important area in image processing that can be used for segmentation. This paper presents an edge based segmentation approach that relies on applying standard edge detection algorithms followed by connecting the discontinuous edges in an efficient manner. This leads to a new segmented image with more complete edges and better distinguishable objects. This is verified by comparing the obtained edge images and the resulting segmentation with the regular edge images and their corresponding segmentation results.
Keywords :
edge detection; image segmentation; image processing; image segmentation; modified edge detection; standard edge detection algorithms; Computer vision; Image edge detection; Image segmentation; Kernel; Pattern analysis;
Conference_Titel :
Signals, Circuits and Systems (ISSCS), 2015 International Symposium on
Conference_Location :
Iasi
Print_ISBN :
978-1-4673-7487-3
DOI :
10.1109/ISSCS.2015.7204001