Answers are grounded in this paper and cite their sources.
This method enhances image quality under low illumination conditions, improving brightness and contrast in diverse environments.
针对真实环境下采集的图像可能存在亮度和对比度低、照度非均匀等质量退化问题,提出了一种基于Retinex理论的非均匀低照度图像增强方法。该方法首先将输入图像从RGB(red, green, blue)空间转换至HSV(hue, saturation, value)空间,选取V分量进行增强处理;然后对V分量通过组合窗口滤波实现Retinex分解,分别采用侧窗滤波和全窗滤波处理图像的边缘和纹理,从而获得局部平滑且结构保留的照度分量;接着对于照度分量,设计了一种基于二次曲线形式的亮度变换方法进行间接调整,以有效增强低照度并校正非均匀照度;对于反射分量,采用混合滤波实现噪声抑制和边缘细节锐化;最后将增强后的照度分量和反射分量重新组合得到增强后的V分量,并转换回RGB空间获得最终的增强图像。实验结果表明,该方法的NIQE(natural image qualityevaluator)、NIQMC(no-reference image quality metric)、CEIQ(content-enhanced image quality)和Entropy评价指标分别为2.747、5.380、3.432和7.476,优于现有大多数图像增强算法。该方法具有更好的亮度和对比度增强性能,同时能够有效校正图像照度的非均匀性,使得增强图像视觉效果更清晰,纹理细节更丰富。
No takes yet. Share an insight, caveat, or question.
ZHANG et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: