Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
8146632 | Infrared Physics & Technology | 2016 | 6 Pages |
Abstract
Image enhancement is an important technique in computer vision. In this paper, we propose a hierarchical image enhancement approach based on the structure layer and texture layer. In the structure layer, we propose a structure-based method based on GMM, which better exploits structure details with fewer noise. In the texture layer, we present a structure-filtering method to filter unwanted texture with keeping completeness of detected salient structure. Next, we introduce a structure constraint prior to integrate them, leading to an improved enhancement result. Extensive experiments demonstrate that the proposed approach achieves higher quality results than previous approaches.
Keywords
Related Topics
Physical Sciences and Engineering
Physics and Astronomy
Atomic and Molecular Physics, and Optics
Authors
Wei Qi, Jing Han, Yi Zhang, Lian-fa Bai,