Segmentation of large images based on super-pixels and community detection in graphs

Linares, Oscar A.; Botelho, Glenda Michele; Rodrigues, Francisco A.; Neto, João Batista Soares

doi:10.48550/arxiv.1612.03705

Cited by 1 publication

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea of using graphs as an approach for segmentation was brought by Wu et al [9]. From then on, the study of optimization techniques on the graph attracted much research attention [10,11,12,13,14]. Our work is in this line.…”

Section: Introductionmentioning

confidence: 91%

“…Linares et al [14] proposed also an algorithm based on community detection algorithms. They start first by an initial segmentation using superpixels method, and then, they consider pixels on the image as nodes on the graph.…”

Section: Related Workmentioning

confidence: 99%

“…A connection between two nodes is considered only if the weight is smaller than a threshold t. Finally, when the graph of superpixels is constructed, they apply the fast greedy algorithm which is a hierarchical agglomerative algorithm for community detection. However, the proposed approach in [14] uses an unweighted network instead of a weighted network which means that some important informations of the image are lost, which affects the network performance.…”

Section: Related Workmentioning

confidence: 99%

“…Then, we associate a weight between them. Unlike the proposed approach in [14] where authors built a graph by considering each node as a connected super-pixel according to a weight function, based only on color. In this work, the similarity is computed using a combination of the LAB and HOG features.…”

Section: Weighting the Ragmentioning

confidence: 99%

See 3 more Smart Citations

A general framework for complex network-based image segmentation

Mourchid

Cherifi

2019

Multimed Tools Appl

View full text Add to dashboard Cite

With the recent advances in complex networks theory, graph-based techniques for image segmentation has attracted great attention recently. In order to segment the image into meaningful connected components, this paper proposes an image segmentation general framework using complex networks based community detection algorithms. If we consider regions as communities, using community detection algorithms directly can lead to an over-segmented image. To address this problem, we start by splitting the image into small regions using an initial segmentation. The obtained regions are used for building the complex network. To produce meaningful connected components and detect homogeneous communities, some combinations of color and texture based features are employed in order to quantify the regions similarities. To sum up, the network of regions is constructed adaptively to avoid many small regions in the image, and then, community detection algorithms are applied on the resulting adaptive similarity matrix to obtain the final segmented image. Experiments are conducted on Berkeley Segmentation Dataset and four of the most influential community detection algorithms are tested. Experimental results have shown that the proposed general framework increases the segmentation performances compared to some existing methods.

show abstract