基于改进自适应直方图均衡化的红外图像增强算法研究  

Research on Infrared Image Enhancement Algorithm Based on Improved Local Histogram

作　　者：温雅 WEN Ya(School of Computer Science,Xi’an Shiyou University,Xi’an 710065,China)

机构地区：[1]西安石油大学计算机学院,陕西西安710065

出　　处：《长江信息通信》2025年第1期87-90,共4页Changjiang Information & Communications

摘　　要：针对传统的直方图均衡化算法对红外图像进行增强时忽略图像的局部特征而导致细节丢失的问题,提出一种改进的自适应直方图均衡化算法。将自适应直方图均衡化与局部分割相结合,把图像分割为前景和背景两部分,前景区域的分布函数使用伽马校正减小灰度跳变,背景区域使用线性插值确保灰度级的分布平滑且均匀。通过实验表明,该文提出的改进算法可以更好的提升红外图像的局部细节和对比度,有效避免均衡化过程中出现的细节丢失。To address the issue of detail loss caused by traditional histogram equalization algorithms when enhancing infrared images due to their neglect of local features,an improved adaptive histogram equalization algorithm is proposed.This approach combines adaptive histogram equalization with local segmentation,dividing the image into foreground and background regions.For the foreground region,the distribution function is adjusted using gamma correction to reduce gray-level jumps,while linear interpolation is used for the background region to ensure a smooth and uniform distribution of gray levels.Experiments demonstrate that the proposed improved algorithm better enhances local details and contrast in infrared images,effectively avoiding detail loss during the equalization process.

关 键 词：红外图像 直方图均衡化 线性插值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]