Foreground Extraction Using Hilbert-Schmidt Independence Criterion and Particle Swarm Optimization Independent Component Analysis

Document Type: Original Article


1 Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

2 Machine Learning and Computational Modeling Labruatory, College of Engineering, University of Tehran, Tehran, Iran


Foreground extraction is one of the crucial subjects in image processing, which drives different applications in industry. The reality behind the continuous research in this area is the various challenging problems we encounter during the separation process of foreground and background images. Among the source separation approaches, the independent component analysis (ICA) is the most prevalent, being involved in different areas of signal separation applications. Despite the improvements being achieved in foreground extraction, the sudden luminance variations and background movements adversely impact the results of techniques in this regard. In this paper, a novel structure called HSIC_ICA is introduced to address the mentioned problem using a modified version of the ICA algorithm which, leverages the Hilbert-Schmidt Independence Criterion (HSIC) instead of the common objective functions.  Moreover, the unmixing matrix elements of ICA are extracted through a Particle Swarm Optimization (PSO) evolutionary algorithm in a much faster way. The experimental results clearly show that the proposed method outperforms over the significant works being cited among the references, using Wallflower dataset.