Implementation of gray level error conpensation for optical 4f system

doi:10.11772/j.issn.1001-9081.2013.07.1973

Journal of Computer Applications ›› 2013, Vol. 33 ›› Issue (07): 1973-1975.DOI: 10.11772/j.issn.1001-9081.2013.07.1973

• Network and distributed techno • Previous Articles Next Articles

Implementation of gray level error conpensation for optical 4f system

HAN Liang,JIANG Ziqi,PU Xiujuan

College of Communication Engineering, Chongqing University, Chongqing 400030, China

Received:2013-01-07 Revised:2013-02-17 Online:2013-07-06 Published:2013-07-01
Contact: HAN Liang

光学4f系统灰度误差补偿的实现

韩亮,姜孜锜,蒲秀娟

重庆大学通信工程学院，重庆 400030

通讯作者: 韩亮
作者简介:韩亮(1975-)，男，陕西洛南人，副教授，博士，主要研究方向：图像处理、信息光学；姜孜锜(1988-)，女，湖北黄冈人，硕士研究生，主要研究方向：图像处理；蒲秀娟(1979-)，女，四川隆昌人，讲师，博士，主要研究方向：非线性估计方法。
基金资助:
国家自然科学基金资助项目(61171158, 61071190);中央高校基本科研业务费资助项目(CDJZR10160002)

Abstract

Abstract: To compensate the gray level error in optical 4f system, a method for gray level error compensation based on histogram matching and Radial Basis Function (RBF) neural network was proposed. The nonlinear transformation of histogram between input and output images in optical 4f System was fitted by RBF neural network, then the optimal estimation of curve for histogram matching between input and output images was obtained. The gray level error compensation image was obtained by utilizing histogram matching according to the optimal estimation of curve for histogram matching. The average Peak Signal-to-Noise Ratio (PSNR) gain achieved was 2.96dB and the visual effect of images processed was improved by utilizing the proposed method in actual optical 4f system. The experimental results show the gray level error in optical 4f system can be compensated effectively and the precision of optical information processing was improved by the proposed method.

Key words: optical 4f system, gray level error, Radial Basis Function (RBF) neural network, histogram matching

摘要： 为补偿光学4f系统灰度误差，提出基于直方图匹配和径向基函数(RBF)神经网络的灰度误差补偿方法。首先利用径向基函数神经网络拟合经光学4f系统输出图像的直方图与对应输入图像的直方图之间的非线性变换，得到输出图像与输入图像的直方图匹配变换曲线的最优估计；再依据直方图匹配曲线的最优估计对经光学4f系统的输出图像进行直方图匹配，得到灰度误差补偿后的图像。利用实际的光学4f系统进行光学实验，灰度误差补偿后图像的信噪比平均提高了2.96dB，视觉效果明显改善。实验结果表明，该方法能有效补偿光学4f系统灰度误差，提高基于光学4f系统的光学信息处理的精度。

关键词: 光学4f系统, 灰度误差, 径向基函数神经网络, 直方图匹配

CLC Number:

TN911.74

HAN Liang JIANG Ziqi PU Xiujuan. Implementation of gray level error conpensation for optical 4f system[J]. Journal of Computer Applications, 2013, 33(07): 1973-1975.

韩亮姜孜锜蒲秀娟. 光学4f系统灰度误差补偿的实现[J]. 计算机应用, 2013, 33(07): 1973-1975.

References

［1］王玉堂. 光子学与光子技术发展战略研究［J］. 光电子〖WW)〗·〖WW(〗激光，1998, 9(6):515-518.

［2］MENDLOVIC D, KONFORTI N. Optical realization of the wavelet transform for two-dimensional objects ［J］. Applied Optics,1993, 32 (32) :6542-6546.

［3］邓丽军，王辉，马利红. 基于滤波成像的大视角数字全息技术［J］. 光子学报，2010, 39(12): 2168-2173.

［4］万堃，曹益平，高志国，等. 基于空间滤波的工件在线检测方法［J］.光电工程，2006, 33(4): 136-140.

［5］MIGUKIN A, AGOUR M, KATKOVNIK V. Phase retrieval in 4f optical system: background compensation and sparse regularization of object with binary amplitude［J］. Applied Optics, 2013, 52(1): A269-A280.

［6］XU X. A novel image denoising method for matched filtering system［J］. Applied Mechanics and Materials, 2012, 265: 2469-2476.

［7］KATKOVNIK V, ASTOLA J. Phase retrieval via spatial light modulator phase modulation in 4f optical setup: numerical inverse imaging with sparse regularization for phase and amplitude［J］. Journal of the Optical Society of America A, 2012, 29(1):105-116.

［8］徐鑫，田逢春，姬艳丽，等. 利用阶跃响应的4f光学系统图像复原［J］. 光学精密工程，2010,18(4): 973-980.

［9］徐鑫，田逢春，陈建军，等.应用图像纹理连续性的4f系统图像非下采样轮廓波变换域降噪［J］.光学精密工程，2010,18(3): 748-755.

［10］李灿，田逢春，陈建军,等. 基于液晶纯相位光调制器的4f系统去噪方法［J］.光学技术，2011, 37(1): 14-18.

［11］OUZIELI I, MENDLOVIC D. Two-dimensional wavelet processor［J］. Applied Optics, 1996, 35(29): 5839-5846.

［12］GONZALES R C, FITTERS B A. Gray-level transformations for interactive image enhancement［J］. Mechanism and Machine Theory, 1977, 12(1):111-122.

［13］POGGIO T, GIROSI F. Networks for approximation and learning［J］.Proceedings of the IEEE, 1990,78(9):1481-1497.

［14］陈刚，田志平.基于FIS和RBFN的预想事故自动选择［J］.电力系统及其自动化学报，2011, 23(5): 80-85.

［15］DJARFOUR N, FARAHTIA J, BADDARI K. Tomographic velocity images by radial basis function artificial neural network［C］// 2011 International Conference on Communications, Computing and Control Applications. Piscataway: IEEE, 2011: 1-4.

[1]	HUA Ji-wei LU Yao LEI Zhao-ming XU Wei-xin. Hot rolling products quality test system based on neural network with function of quality-track [J]. Journal of Computer Applications, 2012, 32(12): 3561-3564.
[2]	ZHENG Yue CHENG Hong SUN Wen-bang. Seam-line removal method based on correctionratio of average value [J]. Journal of Computer Applications, 2012, 32(11): 3168-3170.
[3]	. Colorization method with optional number of cluster and histogram matching [J]. Journal of Computer Applications, 2010, 30(2): 351-353.
[4]	Fu-qiang XUE Lin-Dong GE Bin WANG. RBF equalizer based on adaptive niche hierarchy genetic algorithm [J]. Journal of Computer Applications, 2009, 29(4): 1043-1045.
[5]	. Short-term load forecasting method based on neural network hybrid algorithm of adaptive variable coefficients particle swarm optimization and radial basis function [J]. Journal of Computer Applications, 2009, 29(09): 2454-5458.
[6]	. Accurate allocation model of system reliability based on converse thinking [J]. Journal of Computer Applications, 2009, 29(09): 2468-2470.
[7]	. Grid method of data clustering based on RBF neural networks [J]. Journal of Computer Applications, 2007, 27(2): 333-336.
[8]	. Combined algorithms for training RBF neural networks based on genetic algorithms and gradient descent [J]. Journal of Computer Applications, 2007, 27(2): 366-368.

Implementation of gray level error conpensation for optical 4f system

光学4f系统灰度误差补偿的实现

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 8

Recommended Articles

Metrics