Logo image
Unsupervised Figure-ground Segmentation using Saliency Detection and Boundary Detection
Thesis

Unsupervised Figure-ground Segmentation using Saliency Detection and Boundary Detection

Hsueh, Lie Yun
Masters, 國立清華大學, 資訊工程學系
2014

Abstract

影像切割 非使用者監督 Segmentation Unsupervised
Image segmentation is an essential and challenging problem in computer vision and image processing. Figure-ground segmentation is one of image segmentation that separate image into two labels, which are foreground and background. It can be used in object detection or many other applications. Recently, a lot of methods have been proposed for solving figure-ground segmentation problems. However, most of them are supervised approaches. In other words, the procedures of those methods need some interactions of users. It makes those methods unfavorable. Also, there are some disadvantage in traditional unsupervised image segmentation methods. We proposed an unsupervised figure-ground approach. It uses the saliency detection method to indicate the position of the foreground, and use the boundary detection method to obtain a suitable threshold for image segmentation automatically. According to our experiment results, our method does not need user interaction and performs well compared with the previous saliency-based segmentation method for segmentation of iCoseg dataset and MSRA-1000 dataset.

Metrics

1 Record Views

Details

Logo image