为了改善微光情况下可见光图像传感器输出图像的质量,提出了一种基于高斯混合模型的自适应微光图像增强算法.对图像的直方图进行混合高斯建模,应用改进的期望最大化算法对直方图拟合,从而获取高斯混合模型的最优参数,然后根据各个聚类的交点将直方图分区,最后确定输出图像所属聚类的映射关系,同时应用保持最大熵方法逼近人类视觉特性映射函数得到最终的增强图像.实验结果表明,此图像增强模型能自适应确定最佳聚类个数,提高直方图拟合的运算速度,一帧图像平均处理时间为0．37 s,在相关信息熵和纹理信息等的客观评价中,增强结果明显优于传统方法,有效地提高了微光图像的对比度,同时保持了图像的细节.
In order to improve the output quality of visible light sensor in low-light environment,an adaptive image enhancement algorithm using Gaussian mixture modeling is proposed in this paper. The histogram of image is modeled with Gaussian mixture modeling and the improved EM algorithm is used to fit the histogram and get the best parameters.Then,the histogram is separated into sub-his-tograms based on the intersections of Gaussian components.Finally,the mapping is achieved accord-ing to the parameters of output image,and the final enhanced image is obtained by the maximum en-tropy preserving method which tends to the characteristics of human visual.The experimental results show that the algorithm can determine the optimal number of clusters adaptively and improve the speed of the histogram fitting which costs 0.37 s averagely.Comparing with traditional methods,the enhancement result is superior in terms of objective evaluations of related information entropy and tex-ture information.It can improve the contrast of the low light level image and maintain the details.
参考文献
| [1] | 贺柏根;刘剑;马天玮.基于 DSP + FPGA 的实时图像去雾增强系统设计[J].液晶与显示,201328(06):968-972. |
| [2] | 史继芳;杨斌;韩占锁.基于双重模型客观评价微光像增强器的分辨力[J].光学精密工程,201319(03):2260-2265. |
| [3] | Gonzalez R C;Woods R E.Digital Image Processing[M].Upper Saddle River,NJ:Prentice Hall,2006 |
| [4] | 尹传历;王啸哲.机载嵌入式图像增强系统设计与实现[J].液晶与显示,201328(04):604-607. |
| [5] | 樊博;王延杰;孙宏海.FPGA 实现高速实时多端口图像处理系统的研究[J].液晶与显示,201328(04):620-625. |
| [6] | Kim T K;Paik J K;Kang B S.Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering[J].IEEE Transactions on Consumer Electronics,199844(01):82-87. |
| [7] | Iwanami T;Goto T;Hirano S.An adaptive contrast enhancement using regional dynamic histogram equaliza-tion[A].,2012:719-722. |
| [8] | Ooi C H;Isa N A M.Quadrants dynamic histogram equalization for contrast enhancement[J].IEEE Transactions on Consumer Electronics,201056(04):2552-2559. |
| [9] | 卢清华;吴志伟;范彦斌.基于混合高斯模型的运动车辆检测方法[J].光电子,201324(04):751-757. |
| [10] | 聂宏宾;侯晴宇;赵明.基于似然函数 EM 迭代的红外与可见光图像配准[J].光学精密工程,201121(09):657-663. |
| [11] | 穆为磊;高建民;陈富民.符合人眼视觉特性的焊缝射线数字图像增强方法[J].西安交通大学学报,201246(03):90-93. |
| [12] | Chen S D;Ramli A R.Minimum mean brightness error bi-histogram equalization in contrast enhancement[J].IEEE Transactions on Consumer Electronics,200349(04):1310-1319. |
| [13] | 宋磊;郑宝忠;张莹.一种基于高斯混合模型的改进 EM 算法研究[J].应用光学,201334(06):985-989. |
| [14] | Figueiredo M;Jain A.Unsupervised learning of finite mixture models[J].IEEE Transactions on Pattern Analy-sis and Machine Intelligence,200224(03):381-396. |
| [15] | 韩希珍;赵建.结合偏微分方程增强图像纹理及对比度[J].光学精密工程,201218(06):1382-1388. |
| [16] | Menotti D;Najman L;Facon J.Multi-histogram equalization methods for contrast enhancement and bright-ness preserving[J].IEEE Transactions on Consumer Electronics,200753(03):1186-1194. |
| [17] | 谢凤英;赵丹培.Visual C++数字图像处理[M].北京:电子工业出版社,2008 |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%