摘要
为了克服粉尘环境给图像造成的退化问题,首先建立了一种考虑粉尘多散射因素的图像退化模型,该模型使用一级多散射方法推导得出;其次在图像退化模型基础上采用暗元色先验知识原理提出了图像恢复算法;最后在基于kirsch算子的自动阈值图像质量评价标准下,通过遗传算法(GA)对模型中的大气光与曝光参数自动优化,实现粉尘图像恢复的最优结果.实验证明此方法不但能有效地去除粉尘对图像的影响,增强图像色彩与对比度,而且揭示了更多的边缘信息,为粉尘环境下图像中的目标识别提供了判别依据.
In order to solve the problem of degraded images by dust environment, an image degradation model considering multiple scattering factors caused by dust was established by first-order multiple scattering method. On the basis of image degradation model a dark channel prior principle was applied to present an image restoration algorithm. Genetic algorithm （GA） was applied to optimize atmospheric light and exposure parameters in the model according to the criterion of the image evaluation based on kirsch operator with automatic threshold. By using the method an optimistic result of image restoration was obtained. The experimental result is proven that the method not only enhances luminance and contrast, but discovers more detail edges information. The method would provide the foun dation for target recognition in dust environment.
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2010年第8期42-44,48,共4页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
基金
国家自然科学基金资助项目(60736010)
关键词
图像处理
粉尘
图像质量
多散射
暗元色先验知识
遗传算法
image processing
dust
image quality
multiple scattering
dark channel prior
genetic al gorithm
