Screen Content Image Segmentation Using Sparse-Smooth Decomposition

TL;DR

This paper introduces a sparse-smooth decomposition method for segmenting screen content images, effectively separating background and foreground, and demonstrating superior performance over existing techniques in various applications.

Contribution

The paper presents a novel sparse-smooth decomposition algorithm specifically designed for screen content image segmentation, improving accuracy over traditional clustering methods.

Findings

Superior segmentation accuracy on HEVC test images

Effective separation of background and foreground

Potential applications in text extraction and medical imaging

Abstract

Sparse decomposition has been extensively used for different applications including signal compression and denoising and document analysis. In this paper, sparse decomposition is used for image segmentation. The proposed algorithm separates the background and foreground using a sparse-smooth decomposition technique such that the smooth and sparse components correspond to the background and foreground respectively. This algorithm is tested on several test images from HEVC test sequences and is shown to have superior performance over other methods, such as the hierarchical k-means clustering in DjVu. This segmentation algorithm can also be used for text extraction, video compression and medical image segmentation.