| 基于神经网络的图像亮度和对比度自适应增强 |
| |
| 引用本文： | 谭海曙. 基于神经网络的图像亮度和对比度自适应增强[J]. 上海电力学院学报, 2010, 0(12) |
| |
| 作者姓名： | 谭海曙 |
| |
| 作者单位： | 佛山科学技术学院电子信息工程系; |
| |
| 基金项目： | 国家自然科学基金资助项目(61072134); 天津大学精密测试技术及仪器国家重点实验室开放基金资助项目 |
| |
| 摘 要： | 提出一种高频增强与神经网络相结合的图像亮度和对比度自适应增强方法。利用均值滤波获取原始图像的低频分量,由原始图像与低频分量的差值获取图像的高频分量。同时引入神经网络方法,建立图像的灰度均值、标准偏差与亮度和对比度两个增强系数的非线性映射关系,根据图像本身的均值与标准偏差自动获取增强系数,从而实现图像的亮度和对比度的自适应增强。该方法计算量小,实时性强,对亮度和对比度都较低的图像增强效果较好,可用于图像动态检测系统。为了验证算法的可行性,将所提出的方法应用到货车故障动态图像检测系统(TFDS)所采集的动态图像处理中,获得了好的效果。
|
| 关 键 词： | 自适应增强 神经网络 高频增强 |
Adaptive enhancement of image brightness and contrast based on neural networks |
| |
| TAN Hai-shu. Adaptive enhancement of image brightness and contrast based on neural networks[J]. Journal of Shanghai University of Electric Power, 2010, 0(12) |
| |
| Authors: | TAN Hai-shu |
| |
| Affiliation: | Department of Electronic Information Engineering,Foshan University,Foshan 528000,China, |
| |
| Abstract: | A novel adaptive image brightness and contrast enhancement method combining high-frequency emphasis with neural networks is proposed.First,the low frequency components of the image are obtained by average filter,then the high frequency components of the image can be obtained by subtracting the low frequency components from the original image,and the nonlinear mapping relation between the enhanced factors of image brightness and contrast,the mean and standard deviation of the original image is established ba... |
| |
| Keywords: | adaptive enhancement neural networks high-frequency emphasis |
|
| 点击此处可从《上海电力学院学报》浏览原始摘要信息 |
|
点击此处可从《上海电力学院学报》下载全文 |
|
