Authors:
Thanh-Khoa Nguyen
1
;
Mickael Coustaty
2
and
Jean-Loup Guillaume
2
Affiliations:
1
L3i Laboratory, University of La Rochelle, France, Ca Mau Community College and Vietnam
;
2
L3i Laboratory, University of La Rochelle and France
Keyword(s):
Image Segmentation, Complex Networks, Modularity, Superpixels, Louvain Algorithm, Community Detection.
Related
Ontology
Subjects/Areas/Topics:
Color and Texture Analyses
;
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Segmentation and Grouping
Abstract:
This paper presents an image segmentation strategy using histograms of oriented gradients (HOG), color features and Louvain method, a community detection on graphs algorithm, to tackle the image segmentation problem. This strategy relies on the use of community detection based image segmentation which often leads to over-segmented results. To address this problem, we propose an algorithm that agglomerates homogeneous regions using texture and color features properties. The proposed algorithm is tested on the publicly available Berkeley Segmentation Dataset (BSDS300 and BSDS500), and the Microsoft Research Cambridge Object Recognition Image Database (MSRC) datasets. The experimental results point out that our method produces sizable segmentation and outperforms almost other known methods in terms of accuracy and comparative metrics scores.