Complex Network Construction for Interactive Image Segmentation using Particle Competition and Cooperation: A New Approach

TL;DR

This paper introduces a new method for constructing complex networks in interactive image segmentation that eliminates the need for a weight vector, resulting in significantly lower error rates and more consistent performance.

Contribution

The paper proposes a modified network construction approach for Particle Competition and Cooperation that removes the need for a weight vector, simplifying the process and improving accuracy.

Findings

Error rate of 0.49% with the new model

Compared to 3.14% error rate of the reference model

Less error variation across diverse images

Abstract

In the interactive image segmentation task, the Particle Competition and Cooperation (PCC) model is fed with a complex network, which is built from the input image. In the network construction phase, a weight vector is needed to define the importance of each element in the feature set, which consists of color and location information of the corresponding pixels, thus demanding a specialist's intervention. The present paper proposes the elimination of the weight vector through modifications in the network construction phase. The proposed model and the reference model, without the use of a weight vector, were compared using 151 images extracted from the Grabcut dataset, the PASCAL VOC dataset and the Alpha matting dataset. Each model was applied 30 times to each image to obtain an error average. These simulations resulted in an error rate of only 0.49\% when classifying pixels with the proposed model while the reference model had an error rate of 3.14\%. The proposed method also presented less error variation in the diversity of the evaluated images, when compared to the reference model.