高级检索
    赵华夏, 禹晶, 肖创柏. 基于目的性优化及改进直方图均衡化的夜间彩色图像增强[J]. 计算机研究与发展, 2015, 52(6): 1424-1430. DOI: 10.7544/issn1000-1239.2015.20140067
    引用本文: 赵华夏, 禹晶, 肖创柏. 基于目的性优化及改进直方图均衡化的夜间彩色图像增强[J]. 计算机研究与发展, 2015, 52(6): 1424-1430. DOI: 10.7544/issn1000-1239.2015.20140067
    Zhao Huaxia, Yu Jing, Xiao Chuangbai. Night Color Image Enhancement via Optimization of Purpose and Improved Histogram Equalization[J]. Journal of Computer Research and Development, 2015, 52(6): 1424-1430. DOI: 10.7544/issn1000-1239.2015.20140067
    Citation: Zhao Huaxia, Yu Jing, Xiao Chuangbai. Night Color Image Enhancement via Optimization of Purpose and Improved Histogram Equalization[J]. Journal of Computer Research and Development, 2015, 52(6): 1424-1430. DOI: 10.7544/issn1000-1239.2015.20140067

    基于目的性优化及改进直方图均衡化的夜间彩色图像增强

    Night Color Image Enhancement via Optimization of Purpose and Improved Histogram Equalization

    • 摘要: 夜间图像由于照明不足,存在图像对比度、亮度偏低,细节不可见,导致图像质量下降.大多夜间彩色图像增强算法往往在高对比度边缘区域存在“光晕伪影”现象,针对这些问题提出了一种基于目的性优化及改进直方图均衡化的图像增强算法.该算法通过目的性优化增强原图像对比度,最大程度地保留细节;然后采用改进的保留细节的直方图均衡化增强图像;最后采用改进的Gamma校正对图像进行增强.算法结果通过主观视觉效果以及客观质量评价2方面验证,实验结果表明该算法能够有效地增强图像对比度、亮度,恢复图像细节,并消除了“光晕伪影”.

       

      Abstract: Due to the uneven distribution of light at night, the quality of night color image is usually poor, such as low image contrast, low brightness and less texture. Most of existing night color image enhancement algorithms can’t preserve the details and eliminate the “halo effect” at the edge areas of high contrast in the nighttime image processing. To solve these problems, we propose an image enhancement algorithm based on purposeful optimization and improved histogram equalization. The process of the algorithm is conducted in the luminance channel of the HSV color space: 1)enhance the contrast of the source image and reserve details furthest through improving the image gradient values using the method of optimization; 2)enhance the image by the improved histogram equalization which increases the probability of pixel values of small probability; 3)enhance the image brightness through gamma correction. Subjective and objective evaluation shows that our algorithm greatly enhances the image contrast and brightness, recovers the image details, and eliminates the “halo effect” efficiently. Experiments on the different nighttime images demonstrate the effectiveness of our approach. In summary, our algorithm is effective to complete the challenging task of enhancing the nighttime image.

       

    /

    返回文章
    返回