高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于虚拟光学的视觉显著目标可控放大重建

陈家祯 吴为民 郑子华 叶锋 连桂仁 许力

陈家祯, 吴为民, 郑子华, 叶锋, 连桂仁, 许力. 基于虚拟光学的视觉显著目标可控放大重建[J]. 电子与信息学报, 2020, 42(5): 1209-1215. doi: 10.11999/JEIT190469
引用本文: 陈家祯, 吴为民, 郑子华, 叶锋, 连桂仁, 许力. 基于虚拟光学的视觉显著目标可控放大重建[J]. 电子与信息学报, 2020, 42(5): 1209-1215. doi: 10.11999/JEIT190469
Jiazhen CHEN, Weimin WU, Zihua ZHENG, Feng YE, Guiren LIAN, Li XU. Controllable Magnification for Visual Saliency Object Based on Virtual Optics[J]. Journal of Electronics & Information Technology, 2020, 42(5): 1209-1215. doi: 10.11999/JEIT190469
Citation: Jiazhen CHEN, Weimin WU, Zihua ZHENG, Feng YE, Guiren LIAN, Li XU. Controllable Magnification for Visual Saliency Object Based on Virtual Optics[J]. Journal of Electronics & Information Technology, 2020, 42(5): 1209-1215. doi: 10.11999/JEIT190469

基于虚拟光学的视觉显著目标可控放大重建

doi: 10.11999/JEIT190469
基金项目: 福建省自然科学基金(2018J01779, 2017J01739)
详细信息
    作者简介:

    陈家祯:女,1971年生,副教授,研究方向为信号与信息处理、信息安全

    吴为民:男,1970年生,副教授,研究方向为计算机视觉、人工智能

    郑子华:女,1976年生,副教授,研究方向为数字图像处理

    叶锋:男,1978年生,副教授,研究方向为视频图像处理

    连桂仁:男,1963年生,副教授,研究方向为数字图像处理、电路与系统

    许力:男,1970年生,教授,研究方向为网络与信息安全、智能信息处理

    通讯作者:

    叶锋 yef279@sina.com

  • 中图分类号: TN911.73; TP391.41

Controllable Magnification for Visual Saliency Object Based on Virtual Optics

Funds: The Natural Science Foundation of Fujian Province of China (2018J01779, 2017J01739)
  • 摘要:

    该文提出一种基于虚拟光学的视觉显著目标高分辨率可控放大重建方法。原始图像放置于虚拟光路物平面,首先通过衍射逆计算获得原始图像在虚拟衍射面的光波信号,再对虚拟衍射面光波用球面波照射后作正向衍射计算,通过改变观测平面位置可重建出不同放大率的原始图像。仿真测试结果表明,与一般的插值放大方法相比,所获得的放大后的图像特别是在显著性区域表示出良好的视觉感知效果。将包含人脸的低分辨率降质图像作为待重建信号,所重建人脸的显著性区域如眼睛、鼻子等比一般重建方法更清晰。用水平集方法结合显著图分割出原始图像中的局部显著区域并作放大重建和轮廓提取,轮廓表现出良好的光滑性。

  • 图  1  数字图像可控放大虚拟光路图

    图  2  元胞自动机显著性检测算法流程图

    图  3  基于虚拟光学的放大重建

    图  4  包含人物的场景及谱残差方法计算得到的显著图

    图  5  不同放大方法下眼睛部分的放大重建效果

    图  6  眼睛区域的过零点检测结果

    图  7  降质图像及8倍放大重建

    图  8  结合显著图与水平集方法的局部显著目标分割

    图  9  局部显著目标放大4倍后的轮廓

    图  10  部分目标轮廓斜率及离散曲率比较

    表  1  放大重建像质量指标

    测试图像NMSENLVESFM归一化相关系数
    Mola0.10570.01570.00420.9977
    Barbara0.11060.01450.00190.9963
    Couple0.10450.00210.00220.9956
    平均值0.07690.01080.00270.9965
    下载: 导出CSV
  • PARK S C, PARK M K, and KANG M G. Super-resolution image reconstruction: A technical overview[J]. IEEE Signal Processing Magazine, 2003, 20(3): 21–36. doi: 10.1109/msp.2003.1203207
    LI Xin and ORCHARD M T. New edge-directed interpolation[J]. IEEE Transactions on Image Processing, 2001, 10(10): 1521–1527. doi: 10.1109/83.951537
    ASUNI N and GIACHETTI A. Accuracy improvements and artifacts removal in edge based image interpolation[C]. The 3rd International Conference on Computer Vision Theory and Applications, Funchal, Portugal, 2008: 58–65.
    ZHANG Yunfeng, FAN Qinglan, BAO Fangxun, et al. Single-image super-resolution based on rational fractal interpolation[J]. IEEE Transactions on Image Processing, 2018, 27(8): 3782–3797. doi: 10.1109/TIP.2018.2826139
    YANG Wenhan, FENG Jiashi, YANG Jianchao, et al. Deep edge guided recurrent residual learning for image super-resolution[J]. IEEE Transactions on Image Processing, 2017, 26(12): 5895–5907. doi: 10.1109/TIP.2017.2750403
    MORSE B S and SCHWARTZWALD D. Image magnification using level-set reconstruction[C]. 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, USA, 2001: 333–340. doi: 10.1109/CVPR.2001.990494.
    RATAKONDA K and AHUJA N. POCS based adaptive image magnification[C]. 1998 IEEE International Conference on Image Processing, Chicago, USA, 1998: 203–207. doi: 10.1109/ICIP.1998.727167.
    CAI Qing, LIU Huiying, QIAN Yiming, et al. Saliency-guided level set model for automatic object segmentation[J]. Pattern Recognition, 2019, 93: 147–163. doi: 10.1016/j.patcog.2019.04.019
    李俊昌, 樊则宾. 彩色数字全息的非插值波面重建算法研究[J]. 物理学报, 2010, 59(4): 2457–2461. doi: 10.7498/aps.59.2457

    LI Junchang and FAN Zebin. Algorithm of the non-interpolation wave-front reconstruction of the color digital holography[J]. Acta Physica Sinica, 2010, 59(4): 2457–2461. doi: 10.7498/aps.59.2457
    李俊昌, 熊秉衡. 信息光学教程[M]. 北京: 科学出版社, 2011: 45–57.

    LI Junchang and XIONG Bingheng. Information Optics[M]. Beijing: Science Press, 2011: 45–57.
    LI Junchang, PENG Zujie, TANKAM P, et al. Digital holographic reconstruction of a local object field using an adjustable magnification[J]. Journal of the Optical Society of America A, 2011, 28(6): 1291–1296. doi: 10.1364/JOSAA.28.001291
    RESTREPO J F and GARCIA-SUCERQUIA J. Magnified reconstruction of digitally recorded holograms by Fresnel-Bluestein transform[J]. Applied Optics, 2010, 49(33): 6430–6435. doi: 10.1364/AO.49.006430
    GOODMAN J W. Introduction to Fourier Optics[M]. 2nd ed. New York: McGraw-Hill Editions, 1996: 88–110.
    SCHNARS U and JÜPTNER W P O. Digital recording and numerical reconstruction of holograms[J]. Measurement Science and Technology, 2002, 13(9): R85–R101. doi: 10.1088/0957-0233/13/9/201
    QIN Yao, LU Huchuan, XU Yiqun, et al. Saliency detection via cellular automata[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 110–119. doi: 10.1109/CVPR.2015.7298606.
    LI Chunming, XU Chenyang, GUI Changfeng, et al. Distance regularized level set evolution and its application to image segmentation[J]. IEEE Transactions on Image Processing, 2010, 19(12): 3243–3254. doi: 10.1109/TIP.2010.2069690
    CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6): 679–698. doi: 10.1109/TPAMI.1986.4767851
    吴援明, 梁恩志. 一种基于熵的放大后图像质量的评价方法[J]. 信号处理, 2004, 20(2): 201–203. doi: 10.3969/j.issn.1003-0530.2004.02.022

    WU Yuanming and LIANG Enzhi. A new method of zoomed images evaluation[J]. Signal Processing, 2004, 20(2): 201–203. doi: 10.3969/j.issn.1003-0530.2004.02.022
    HOU Xiaodi and ZHANG Liqing. Saliency detection: A spectral residual approach[C]. 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, USA, 2007: 1–8. doi: 10.1109/CVPR.2007.383267.
    QIN Yi, GONG Qiong, WANG Zhipeng, et al. Optical multiple-image encryption in diffractive-imaging-based scheme using spectral fusion and nonlinear operation[J]. Optics Express, 2016, 24(23): 26877–26886. doi: 10.1364/OE.24.026877
  • 加载中
图(10) / 表(1)
计量
  • 文章访问数:  2439
  • HTML全文浏览量:  1110
  • PDF下载量:  45
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-06-25
  • 修回日期:  2019-10-30
  • 网络出版日期:  2019-11-04
  • 刊出日期:  2020-06-04

目录

    /

    返回文章
    返回