An Image Segmentation Algorithm based on Community Detection

With the recent advances in complex networks, image segmentation becomes one of the most appropriate application areas. In this context, we propose in this paper a new perspective of image segmentation by applying two efficient community detection algorithms. By considering regions as communities, these methods can give an over-segmented image that has many small regions. So, the proposed algorithms are improved to automatically merge those neighboring regions agglomerative to achieve the highest modularity/stability. To produce sizable regions and detect homogeneous communities, we use the combination of a feature based on the Histogram of Oriented Gradients of the image, and feature based on color to characterize the similarity of two regions. By constructing the similarity matrix in an adaptive manner, we avoid the problem of the over-segmentation. We evaluate the proposed algorithms for Berkeley Segmentation Dataset, and we show that our experimental results can outperform other segmentation methods in terms of accuracy and can achieve much better segmentation results.