改进的CLAHE无芒隐子草叶切片图像增强

Method for Intensification of Cleistogenes Songorica Leaf Slices Image Based on Improved CLAHE

无芒隐子草叶切片图像在获取过程中不可避免产生低对比度图像,对后续处理产生影响。为此,针对传统的限制对比度自适应直方图均衡化方法(contrast-limited adaptive histogram equalization,CLAHE)对较暗图像处理效果不佳的问题,提出了基于自适应亮度调整的CLAHE图像增强算法。该算法首先将图像RGB空间转换到HSV空间,提取图像的亮度分量,再根据图像的亮度值,自适应调整RGB通道图像整体亮度,最后应用CLAHE算法实现图像增强。采用50张无芒隐子草叶切片图像为样本进行试验,结果表明:该算法相比于传统的CLAHE算法,图像信息熵、图像对比度、图像平均梯度和图像的峰值信噪比均显著提高,有效克服了传统CLAHE算法对过暗图像增强效果不佳问题,能使图像局部细节信息和清晰程度得到明显提高,不仅适合无芒隐子草叶切片低对比度图像增强,也可为其他植物叶切片图像增强提供参考。

The microscopic images from leaf slices of Cleistogenes Songorica has the weaknesses of low contrast inevitably in obtaining,which will have a negative effect on its subsequent processes.This paper proposed a method called a contrast-limited adaptive histogram equalization(CLAHE)of adaptive brightness adjustment to solve the weakness of traditional CLAHE has weak effective for Over-dark image.The image enhancement algorithm used in the article has the following steps:Firstly,transformed the original images from RGB space to HSV space.Secondly,we decomposed the luminance component of the image in HSV space,and based on this value to adjusted the overall luminance of the image adaptively.Finally,the enhancement of Cleistogenes Songorica leaf slices images was finished by using the method of Contrast-limited Adaptive Histogram Equalization,and we also used other image processing methods(such as:histogram equalization,traditional CLAHE)dealing with slices images.Then through subjective judgment(observe the change of processed image and its histogram,compare the changes and find out which method is the best one),we found out that images processed by HE had the shortcoming of noise over-enhancement and turn up color distortion,processed by CLAHE had luminance enhancement limited For over-dark images,proposed method showed better performance in improving the quality of image and the details of the images than the other methods.Also by evaluation functions:Average gradient(AG),Contrast(C),Information entropy(E),and Peak signal to noise rate(PSNR)were used for objectively evaluated the method used in this paper and the other methods.We got the average value of AG,C,E and PSNR by processing 50 images,and it turned out that the values of the method proposed in this paper was better than the other methods.The study showed that the pro-posed method in this paper took great advantages of several other methods to achieve good results,and effectively over-come the problem that the traditional CLAHE algorithm is not good for over-dark image.In conclusion,the algorithm in this paper is more suitable for the low contrast images of Cleistogenes Songorica leaf slices and can also provide a reference for other plant leaf slice images.