一种红外图像坏点与热噪声抑制及增强方法
By constructing multiple infrared image separation and enhancement methods, the problems of point defects, structured noise, and low-frequency thermal bias in infrared images were solved, thereby improving the clarity and recognizability of infrared images.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UNIV OF JINAN
- Filing Date
- 2026-04-24
- Publication Date
- 2026-07-17
AI Technical Summary
Existing infrared image enhancement methods struggle to simultaneously address dot-like defects, structured stripe noise, and low-frequency thermal bias, and are prone to misjudging real small thermal targets, resulting in blurred target edges, distorted background textures, and reduced thermal difference between thermal targets and the background.
We construct a thermal consistency-guided sparse separation term for point-like defects, a direction-aware structured thermal noise separation term, a background-gated low-frequency thermal bias separation term, an anisotropic edge-preserving enhancement term for thermal target protection, and a multi-scale local thermal contrast preservation term. By jointly decomposing and enhancing point-like anomalies, structured noise, and low-frequency non-uniform background in infrared images, we achieve the following:
It effectively suppresses dead pixels and thermal noise, maintains the target outline and local thermal difference, and improves the clarity and recognizability of infrared images.
Smart Images
Figure CN122089604B_ABST