Home // MMEDIA 2016, The Eighth International Conferences on Advances in Multimedia // View article

Automatic Labelling of Seeds Based on Saliency Detection and Edge Detection for Image Segmentation

Authors:
Long-Wen Chang
Cheng-Mao Wu

Keywords: egmentation;supervised segmentation; unsupervised segmentation; saliency detecion; edge detection

Abstract:
In computer vision, image segmentation transforms an input image into a more meaningful form which is easier to analyze. It can be used in the applications such as medical imaging, object detection, face recognition, etc. Generally, image segmentation can be distinguished as supervised and unsupervised categories. The result of supervised image segmentation is greatly affected by a user. Therefore, we propose an unsupervised method of image segmentation. We use saliency detection to label some informative and significant parts of the image, and then, we apply edge detection to label some details of the image and use the labelled image for image segmentation by Kim’s method. In this way, we can automatically label the seeds to get the scribble and then segment the image into the foreground and the background. The simulation results show that our method is feasible for image segmentation.

Pages: 8 to 11

Copyright: Copyright (c) IARIA, 2016

Publication date: February 21, 2016

Published in: conference

ISSN: 2308-4448

ISBN: 978-1-61208-452-7

Location: Lisbon, Portugal

Dates: from February 21, 2016 to February 25, 2016