Efficient Method to Segment Objects from Images Based on Enhanced Connected Component Labeling algorithm

  • Asma Ibrahim Hussein Ministry of Higher Education and Scientific Research/Baghdad, Iraq
  • Mayada Jabbar Kelain AL-MustansiriyahUniversity, Baghdad, Iraq

Abstract

This paper include the problem of segmenting an image into regions represent (objects), segment this object by define boundary between two regions using a connected component labeling. Then develop an efficient segmentation algorithm based on this method, to apply the algorithm to image segmentation using different kinds of images, this algorithm consist four steps at the first step convert the image gray level the are applied on the image, these images then in the second step convert to binary image, edge detection using Canny edge detection in third Are applie the final step is images. Best segmentation rates are (90%) obtained when using the developed algorithm compared with (77%) which are obtained using (ccl) before enhancement.

Published
Mar 4, 2018
How to Cite
HUSSEIN, Asma Ibrahim; KELAIN, Mayada Jabbar. Efficient Method to Segment Objects from Images Based on Enhanced Connected Component Labeling algorithm. Iraqi Journal of Science, [S.l.], p. 420-425, mar. 2018. ISSN 2312-1637. Available at: <http://scbaghdad.edu.iq/eijs/index.php/eijs/article/view/125>. Date accessed: 19 sep. 2018.
Section
Computer Science