Image Matting for Automatic Target Recognition

Abstract

Features used in the classification of targets are generally based on the shape or gray-level information of the preprocessed target chip. Consequently, the performance of an automatic target recognition (ATR) system critically depends on the preprocessing result. In this paper, we propose to apply recent advances in image matting to address these challenges. First, a trimap is automatically generated in an adaptive manner to assign appropriate known foreground and background constraints. Then modified geometric clustering, which estimates the target center robustly, is performed on the estimated trimap. Then propagation-based matting is used to remove nontarget regions while retaining target information. The proposed framework is evaluated using visual examination, ATR performance comparison, and constraints dependency analysis. Our method has robust capabilities and outperforms conventional schemes.