Image Co-Segmentation via Examples Guidance
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 1
Abstract
Given a collection of images which contains objects from the same category, the co-segmentation methods aim at simultaneously segmenting such common objects in each image. Most of existing co-segmentation approaches rely on comput-ing similarities inter-regions representing foregrounds in these images. However, region similarity measurement is challenging due to the large appearance variations among objects in the same category. In addition, for real-world images which have cluttered backgrounds, the existing co-segmentation approaches miss sufficient robustness to extract the common object from the background. In this paper, we propose a new co-segmentation method which takes advantage of the reliable segmentation of few selected images, in order to guide the segmentation of the remaining images in the collection. A random sample of images is first selected from the image collection. Then, the selected images are segmented using an interactive segmentation method. These segmentation results are used to construct positive/negative samples of the targeted common object and background regions respectively. Finally, these samples are propagated to the remain-ing images in the collection through computing both local and global consistency. The experiments on the iCoseg and MSRC datasets demonstrate the performance and robustness of the proposed method.
Authors and Affiliations
Rachida Es-Salhi, Imane Daoudi, Hamid El Ouardi
Keywords
Related Articles
- EP ID EP448925
- DOI 10.14569/IJACSA.2019.0100165
- Views 66
- Downloads 0
Modelling of Thermal Storage in Damaged Composite Structures using Time Displaced Gradient Field Technique (TDGF)
This paper presents a new approach to composite surface characterization using Gradient Field time displacement. The new technique employs calculation of thermally charged regions within a composite structure as a result...
Assessment of Potential Dam Sites in the Kabul River Basin Using GIS
The research focuses on Kabul River Basin (KRB) water resources infrastructure, management and development as there are many dams already in the basin and many dams are planned and are being studied with multi-purposes o...
A Study on the Effect of Learning Strategy using a Highlighter Pen on Gaze Movement
In this study, we propose a learning strategy using a highlighter pen to improve the learning efficiency of learners. This method makes the important information stand out by colouring text. It is known that highlighting...
A New Uncertainty Measure in Belief Entropy Framework
Belief entropy, which represents the uncertainty measure between several pieces of evidence in the Dempster-Shafer framework, is attracting increasing interest in research. It has been used in many applications and is ma...
Age Estimation Based on AAM and 2D-DCT Features of Facial Images
This paper proposes a novel age estimation method - Global and Local feAture based Age estiMation (GLAAM) - relying on global and local features of facial images. Global features are obtained with Active Appearance Model...