In order to overcome the drawback of the existing image enhancement technologies and further consider the pixel intensity expression error caused by imaging, a novel fuzzy inference‐based contextual dissimilarity histogram equalization (FICDHE) algorithm is proposed. The proposed algorithm is composed of three modules. In the first module, according to the calculated probable intensity intervals, the membership functions of intensity are generated. In the second one, fuzzy inference systems are established and the contextual dissimilarity of each pixel is calculated. In the third module, the contextual dissimilarity histograms are clipped and equalized. The fuzzy system established in this paper not only fully considers the uncertainty source of pixel gray level expression, but also has adaptability. The parameter selection of fuzzy inference system membership function in this algorithm does not need human intervention, but is automatically obtained based on the statistical information of image pixel gray. Its adaptability makes the algorithm more widely used and convenient. Experiments are conducted using four typical medical images and 800 images from the KNIX dataset and BrainWeb dataset. The performance of the proposed method was compared to a series of enhancement algorithms based on both subjective judgment and image quality measurement indexes. Experimental results demonstrate that the proposed algorithm has a better contrast enhancement ability and yields better performance.

中文翻译：

---

基于模糊推理的上下文不相似直方图均衡算法的图像增强

为了克服现有图像增强技术的弊端，并进一步考虑成像引起的像素强度表达误差，提出了一种基于模糊推理的上下文不相似直方图均衡化算法。所提出的算法由三个模块组成。在第一模块中，根据计算出的可能的强度间隔，生成强度的隶属函数。在第二种方法中，建立了模糊推理系统，并计算了每个像素的上下文不相似性。在第三个模块中，上下文不相似直方图被裁剪和均衡。本文建立的模糊系统不仅充分考虑了像素灰度表达的不确定性来源，而且具有适应性。该算法中模糊推理系统隶属度函数的参数选择不需要人工干预，而是根据图像像素灰度的统计信息自动获得。它的适应性使该算法得到更广泛的使用和方便。使用四个典型医学图像和来自KNIX数据集和BrainWeb数据集的800个图像进行实验。将该方法的性能与一系列基于主观判断和图像质量测量指标的增强算法进行了比较。实验结果表明，该算法具有较好的对比度增强能力，并具有较好的性能。它的适应性使该算法得到更广泛的使用和方便。使用四个典型医学图像和来自KNIX数据集和BrainWeb数据集的800个图像进行实验。将该方法的性能与一系列基于主观判断和图像质量测量指标的增强算法进行了比较。实验结果表明，该算法具有较好的对比度增强能力，并具有较好的性能。它的适应性使该算法得到更广泛的使用和方便。使用四个典型医学图像和来自KNIX数据集和BrainWeb数据集的800个图像进行实验。将该方法的性能与基于主观判断和图像质量测量指标的一系列增强算法进行了比较。实验结果表明，该算法具有较好的对比度增强能力，并具有较好的性能。