针对彩色直方图均衡化算法颜色易失真的缺点，提出了一种基于暗原色先验的快速图像增强算法。首先求取全局暗原色图，然后估计透过率图和大气光成分图，最后根据大气散射模型恢复出图像中所有像素的灰度值。结合实际应用，以高性能DSP芯片TMS320DM6437作为中央处理器，结合现场可编程门阵列FPGA构成外围电路逻辑控制，搭建了嵌入式高速图像增强处理平台。基于该平台用真实图像验证了本文提出的算法。实验结果表明，本系统在提高色彩和对比度的同时，有效地还原了场景中物体的颜色，获得了较好的增强效果，同时算法运行时间少，能够满足工程项目的要求。

According to the disadvantage of color distortion of color histogram equalization algorithm, a new image enhancement algorithm based on dark channel prior is presented. First, the dark channel image is done. Then the transmission map and the atmospheric optical components map are estimated. Finally the bright values of the pixels of the image are calculated according to the atmospheric model. An embedded high speed image enhancement processing system on high performance DSP TMS320DM6437 and FPGA was designed. Experimental results with real images shown that the system can improve the contrast and color of the image, restore the real color of the image, and effectively enhance the image, the running time of the program is shorter, so it can meet the requirements in the project.