计算机与现代化

• 算法设计与分析 • 上一篇    下一篇

基于NSCT和PCNN的彩色图像增强方法

  

  1. (咸阳师范学院图形图像处理研究所,陕西咸阳712000)
  • 收稿日期:2015-06-11 出版日期:2015-11-12 发布日期:2015-11-16
  • 作者简介:段群(1980-),女,陕西礼泉人,咸阳师范学院图形图像处理研究所讲师,硕士,研究方向:图像增强与降噪,并行计算; 韩丽娜(1976-),女,陕西富平人,副教授,博士,研究方向:视频图像增强,雨雾图像清晰。
  • 基金资助:
    陕西省教育厅基金资助项目(14JK1802); 咸阳师范学院基金资助项目(12XSYK072)
     

An Enhanced Method of Color Image Based on NSCT and PCNN

  1. (Institute of Graphics and Image Processing, Xianyang Normal University, Xianyang 712000, China)
  • Received:2015-06-11 Online:2015-11-12 Published:2015-11-16

摘要: 根据人类对颜色的感知特性,本文在彩色图像的HSV空间,提出一种基于非下采样Contourlet变换(Non-subsampled Contourlet Transform, NSCT)和脉冲耦合神经网络(Pulse Coupled Neural Networks, PCNN)模型相结合的彩色图像增强算法。首先对HSV空间亮度分量V做NSCT分解,得到低频子带系数和高频方向子带系数,对低频子带系数做PCNN增强,并对处理后的系数做修正,再对高频子带系数做线性变换处理,将处理后的V分量做逆NSCT以重构;然后对饱和度分量S做幂次微调。最后,将HSV颜色空间变换到RGB空间得到增强后的图像。实验结果表明,本增强方法在视觉效果和客观评价指标上都优于比较算法,不仅增加了彩色图像的亮度,而且颜色保持较好,边缘更清晰。

关键词: 非下采样Contourlet变换, 脉冲耦合神经网络, HSV颜色模型, 彩色图像增强

Abstract:

Abstract: This paper presents a new enhanced method of color image based on Nonsubsampled Contourlet Transform (NSCT) and Pulse Coupled Neural Networks (PCNN), according to the porceptual character of human visual system in HSV space. First, luminance V is decomposed to low frequency coefficients and high frequency coefficients by NSCT, the low frequency coefficients are enhanced by PCNN and corrected, the high frequency coefficients are linear transformed and inverse NSCT is performed to reconstruct the enhanced luminance V. Then, the saturation S is slightly enhanced by power to increase image contrast. Last, the color image is transformed from HSV color space to RGB color space. Experiments illustrate that the proposed method can retain a visual quality and objective evaluation index, this algorithm can not only correct nonuniform illumination in images, but also maintain a good image color and the local details.

Key words: Non-subsampled Contourlet Transform (NSCT), Pulse Coupled Neural Networks(PCNN), Hue Saturation Value space(HSV), color image enhancement

中图分类号: