Screen Content Image Segmentation Using Least Absolute Deviation Fitting

TL;DR

This paper introduces a novel segmentation algorithm for screen content images that effectively separates smoothly varying backgrounds from sharp foreground text and graphics using least absolute deviation fitting.

Contribution

The proposed method uniquely models the background with smooth basis functions and employs least absolute deviation fitting to improve segmentation accuracy over existing techniques.

Findings

Superior performance over k-means and SPEC algorithms

Effective separation of foreground and background in test images

Applicable to screen content coding and compression

Abstract

We propose an algorithm for separating the foreground (mainly text and line graphics) from the smoothly varying background in screen content images. The proposed method is designed based on the assumption that the background part of the image is smoothly varying and can be represented by a linear combination of a few smoothly varying basis functions, while the foreground text and graphics create sharp discontinuity and cannot be modeled by this smooth representation. The algorithm separates the background and foreground using a least absolute deviation method to fit the smooth model to the image pixels. This algorithm has been tested on several images from HEVC standard test sequences for screen content coding, and is shown to have superior performance over other popular methods, such as k-means clustering based segmentation in DjVu and shape primitive extraction and coding (SPEC) algorithm. Such background/foreground segmentation are important pre-processing steps for text extraction and separate coding of background and foreground for compression of screen content images.