摘要
针对红外图像"高背景、低反差"的特点,在传统的分段线性变换的基础上,提出了一种自适应的算法。通过对原始图像的直方图统计得到该图像的背景阈值,再通过对原始图像上目标区域的灰度估算得到该图像的目标阈值,由此将图像分解成背景、目标和不感兴趣的区域三部分,然后通过分段线形变换将背景和不感兴趣的区域进行灰度压缩,同时将目标区域进行灰度拉伸,从而达到有效的抑制背景、增强目标的目的。通过实验结果比较,该算法无论在阈值的自适应方面或者是图像增强的效果,都优于传统的直方图均衡和双直方图均衡算法。
A conventional piecewise linear grey transformation based self-adaptive contrast enhancement algorithm is proposed for infrared laser measuring system, in which the global image is divided into three parts： back- ground area, objectives area, and uninterested area. The background and noise containing in the image will be restrained, and the targets will be highlighted. A comprehensive qualitative and quantitative performance evaluation has been carried out and the experimental results indicate that the proposed algorithm can greatly improve the global and local contrast for both near infrared images and far infrared laser images while efficiently reducing noise in the infrared images. Experimental results presented demonstrate that the algorithm performs well when compared with several approaches to image enhancement, such as histogram equalization, double plateaus histogram equalization and so on, which are available in the literature.
出处
《科学技术与工程》
2010年第4期922-927,共6页
Science Technology and Engineering
基金
国家重点基础研究项目(2007CB714107)
国家自然科学基金(10971225)
教育部留学回国人员科研启动基金
华中科技大学科学研究基金联合资助
关键词
红外激光图像
灰度变换
图像质量评估
自适应阈值
infrared laser images grey transformation evaluation of image quality self-adaptive threshold
