J4 ›› 2014, Vol. 41 ›› Issue (3): 103-109.doi: 10.3969/j.issn.1001-2400.2014.03.015

• 研究论文 • 上一篇    下一篇

一种结合直方图均衡化和MSRCR的图像增强新算法

李锦;王俊平;万国挺;李紫阳;许丹;曹洪花;张广燕   

  1. (西安电子科技大学 通信工程学院,陕西 西安  710071)
  • 收稿日期:2013-02-05 出版日期:2014-06-20 发布日期:2014-07-10
  • 通讯作者: 李锦
  • 作者简介:李锦(1987-),女,西安电子科技大学硕士研究生,E-mail:ljathere@163.com.
  • 基金资助:

    国家自然科学基金资助项目(61173088);西安市产业技术创新计划(CX1248⑤)

Novel algorithm for image enhancement with histogram equalization and MSRCR

LI Jin;WANG Junping;WAN Guoting;LI Ziyang;XU Dan;CAO Honghua;ZHANG Guangyan   

  1. (School of Telecommunication Engineering, Xidian Univ., Xi'an  710071, China)
  • Received:2013-02-05 Online:2014-06-20 Published:2014-07-10
  • Contact: LI Jin

摘要:

为便于集成电路(IC)真实缺陷形貌图的缺陷特征提取,提出了一种结合直方图均衡化(HE)和多尺度Retinex彩色恢复(MSRCR)算法的彩色图像增强新算法.用直方图均衡化对彩色图像进行增强,可以显著提高对比度,但会降低原图的信息熵;用Retinex算法对彩色图像进行增强,可以显著提高暗区域的细节,但会产生泛白、颜色失真和对比度低的现象.新算法根据两种算法处理结果的特点,将图像先分别进行HE增强和MSRCR增强,然后按照一定的图像融合规则进行加权融合,经过大量的测试统计,得到了一个最佳权重.实验证明,改进的算法使图像的亮度、对比度、细节等都有很大的增强,不仅改善了图像的整体视觉效果,而且得到了最大的信息熵,能更好地刻画IC缺陷细节,有利于后续的目标检测和缺陷特征提取,并验证了算法的通用性.

关键词: 图像增强, 直方图均衡化, Retinex算法, 图像融合, IC缺陷特征提取

Abstract:

In order to conveniently extract the extra material defect features from an IC real image, this paper proposes a new method for a color image enhancement combined with histogram equalization (HE) and Multi-Scale Retinex with Color Restoration (MSRCR). Using histogram equalization to color image enhancement can significantly improve the contrast but will reduce the original information entropy, the Retinex algorithm can improve the details of the dark area but will lead to the phenomena such as the white and color distortion, low contrast. The new algorithm, according to the characteristics of the processing results of the above two algorithms, weightily fusing the HE enhanced image and the MSRCR enhanced image, has been one of the best weighting factors after a lot of test statistics. Experimental results show that the improved algorithm produces greater enhancement in the image's brightness, contrast, detail, and others and that it not only improves the overall visual effect of the image, but also gives the maximum information entropy. Through objective and subjective evaluation, it is shown that the algorithm has a fantastic effect on enhancement of color image, compared to the HE and MSRCR algorithm that process separately, and that it can better describe IC defects in detail,  which is conducive to the detection and defect feature extraction of the subsequent target, and verify the versatility of the algorithm.

Key words: image enhancement, histogram equalization, Retinex algorithm, image fusion, IC defect feature extraction

中图分类号: 

  • TP391.4