Building Networks for Image Segmentation using Particle Competition and Cooperation
This work addresses the challenge of improving semi-supervised image segmentation for computer vision applications, but it is incremental as it builds on existing PCC methods.
The paper tackles the problem of building optimal networks for image segmentation using particle competition and cooperation by proposing an index to evaluate candidate networks and optimizing feature weights, achieving effective segmentation results on real-world images from the Microsoft GrabCut database.
Particle competition and cooperation (PCC) is a graph-based semi-supervised learning approach. When PCC is applied to interactive image segmentation tasks, pixels are converted into network nodes, and each node is connected to its k-nearest neighbors, according to the distance between a set of features extracted from the image. Building a proper network to feed PCC is crucial to achieve good segmentation results. However, some features may be more important than others to identify the segments, depending on the characteristics of the image to be segmented. In this paper, an index to evaluate candidate networks is proposed. Thus, building the network becomes a problem of optimizing some feature weights based on the proposed index. Computer simulations are performed on some real-world images from the Microsoft GrabCut database, and the segmentation results related in this paper show the effectiveness of the proposed method.