欢迎访问《图学学报》 分享到:

图学学报

• 图像技术 • 上一篇    下一篇

基于双边滤波的Retinex图像增强算法

  

  • 出版日期:2010-04-30 发布日期:2015-08-11

Retinex Algorithm for Image Enhancement Based on Bilateral Filtering

  • Online:2010-04-30 Published:2015-08-11

摘要: 针对Retinex图像增强技术在高对比度边缘区域存在“光晕伪影”这一缺点,提出了一种基于双边滤波的Retinex算法。该算法先使用带有边缘保存功能的双边滤波将原图像分解成照度图像和反射图像,再分别采用不同的策略压缩照度图像和增强反射图像,最后把两部分图像合成为新的图像。通过从主观视觉效果和客观质量评价两方面对该算法进行检验,实验结果表明它有较好的增强效果,解决了“光晕伪影”问题。

关键词: 计算机应用, 图像增强, 双边滤波, Retinex技术

Abstract: A Retinex algorithm based on bilateral filtering is proposed to the question of the apparition of halo artifacts in the presence of high contrast edges using exiting Retinex image enhancement. Firstly, this algorithm decomposes the original image into the illuminant image and the reflectance image using the bilateral filter which has the function of edge-preserving, then different strategies are used to compress the illuminant image and to enhance the reflectance image. At last, it composes the two part images to a new image. The algorithm can be verified from subjective visual effects and objective image quality assessment. The experimental results show that it has good enhancement result and can avoid halo artifacts.

Key words: computer application, image enhancement, bilateral filtering, Retinex