本征图像分解的可变尺度局部分析与集成方法

doi:10.16451/j.cnki.issn1003-6059.202104004

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (2252 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对自然图像与磁共振图像,提出本征图像分解的统一的数学模型与算法,解决这两类图像中的重要问题:1)自然图像的光照和反射图像的估计,2)磁共振图像中的偏移场估计与分割.文中数学模型只需要一个基本的假设,即观察到的图像可近似为两个具有不同特性的本征图像的乘积:一个光滑的图像,简称为S-图像;一个近似为分片常量的图像,简称为L-图像.为了充分利用本征图像的特性,提出可变尺度局部分析与集成的方法.由于S-图像的光滑性,使用低阶泰勒展开式或更一般的光滑基函数的线性组合以局部逼近.得到的局部光滑逼近可通过整个感兴趣区域(ROI)的局部区域覆盖及其对应的单位分解扩展成整个ROI上的光滑图像,同时得到图像分割结果和L-图像.实验表明,文中方法对图像的两个本征因子的假设较弱,适用于更广泛的图像.目前方法已在磁共振图像及自然图像中进行测试,得到较优结果.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	石雪
	徐海平
	李纯明

关键词 ：本征图像, 图像分割, 光照与反射图像, 磁共振成像

Abstract：A unified mathematical model and an algorithm are proposed to solve the problems of the estimation of illumination and reflectance images of a natural image and the segmentation and bias field estimation of a magnetic resonance image(MRI). The proposed model only requires a basic assumption that the observed image can be approximated by the product of two intrinsic images with different properties. One of the two intrinsic images is a smooth image, S-image, and the other is a piece-wise approximately constant image, L-image. To fully exploit the properties of the intrinsic images, a scalable local analysis and integration(SLAI) approach is proposed for the problem of intrinsic image estimation. Due to the smoothness of the S-image, a low order Taylor expansion or a linear combination of general smooth basis functions is utilized to locally approximate the S-image. The obtained local smooth approximation of the S-image can be extended to a smooth image on the entire region of interest(ROI) using partition of unity subordinate to a cover of ROI. Meanwhile, the segmentation result and the estimation of the L-image are obtained. The proposed method is based on a weaker assumption than the methods in the literature, and therefore it is applicable to more images. The proposed method produces satisfactory results on MR images and natural images.

Key words： Intrinsic Image Image Segmentation Illumination and Reflectance Image Magnetic Resonance Imaging

收稿日期: 2020-07-09

ZTFLH:

TP 391.41

基金资助:国家自然科学基金项目(No.G0561671135)资助

通讯作者: 李纯明,博士,教授,主要研究方向为计算机视觉、医学图像分析.E-mail:cmli@ieee.org.

作者简介: 石雪,博士研究生,主要研究方向为图像处理、医学图像分析.E-mail:xueshi@ieee.org. 徐海平,博士,讲师,主要研究方向为图像处理、机器学习.E-mail:haiping@mju.edu.cn.

引用本文:

石雪, 徐海平, 李纯明. 本征图像分解的可变尺度局部分析与集成方法[J]. 模式识别与人工智能, 2021, 34(4): 322-332. SHI Xue, XU Haiping, LI Chunming. A Scalable Local Analysis and Integration Approach to Intrinsic Image Decomposition. , 2021, 34(4): 322-332.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202104004 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2021/V34/I4/322

[1] BARROW H, TENENBAUM J M. Recovering Intrinsic Scene Cha-racteristics from Images // HANSON A, RISEMAN E, eds. Computer Vision Systems. New York, USA: Academic Press, 1978: 3-26.
[2] TAPPEN M F, ADELSON E H, FREEMAN W T. Estimating Intrinsic Component Images Using Non-linear Regression // Proc of the IEEE Computer Society Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2006, II: 1992-1999.
[3] BARRON J T, MALIK J. Shape, Illumination, and Reflectance from Shading. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(8): 1670-1687.
[4] BELL S, BALA K, SNAVELY N. Intrinsic Images in the Wild. ACM Transactions on Graphic, 2014, 33(4). DOI: 10.1145/2601097.2601206.
[5] WEISS Y. Deriving Intrinsic Images from Image Sequences // Proc of the 8th IEEE International Conference on Computer Vision. Washing-ton, USA: IEEE, 2001, II: 68-75.
[6] KIMMEL R, ELAD M, SHAKED D, et al. A Variational Framework for Retinex. International Journal of Computer Vision, 2003, 52(1): 7- 23.
[7] HORN B K P. Determining Lightness from an Image. Computer Gra-phics and Image Processing, 1974, 3: 277-299.
[8] LAND E H, MCCANN J J. Lightness and Retinex Theory. Journal of the Optical Society of America, 1971, 61(1): 1-11.
[9] BLAKE A. Boundary Conditions for Lightness Computation in Mondrian World. Computer Vision, Graphics and Image Processing, 1985, 32(3): 314-327.
[10] SHEN L, TAN P, LIN S. Intrinsic Image Decomposition with Non-local Texture Cues // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2008. DOI: 10.1109/CVPR.2008.4587660.
[11] ZHAO Q, TAN P, DAI Q, et al. A Closed-Form Solution to Re-tinex with Nonlocal Texture Constraints. IEEE Transactions on Pa-ttern Analysis and Machine Intelligence, 2012, 34(7): 1437-1444.
[12] BOUSSEAU A, PARIS S, DURAND F. User-Assisted Intrinsic Images. ACM Transactions on Graphics, 2009, 28(5). DOI: 10.1145/1618452.1618476.
[13] BARRON J T, MALIK J. Shape, Albedo, and Illumination from a Single Image of an Unknown Object // Proc of the IEEE Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 334-341.
[14] CHEN Q F, KOLTUN V. A Simple Model for Intrinsic Image Decomposition with Depth Cues // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2013: 241-248.
[15] SHEN L, YEO C H. Intrinsic Images Decomposition Using a Local and Global Sparse Representation of Reflectance // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2011: 697-704.
[16] LI C M, LI F, KAO C Y, et al. Image Segmentation with Simultaneous Illumination and Reflectance Estimation: An Energy Minimization Approach // Proc of the 12th IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2009: 702-708.
[17] YANG Y Y, JIA W J, WU B Y. Simultaneous Segmentation and Correction Model for Color Medical and Natural Images with Intensity Inhomogeneity. The Visual Computer, 2020, 36(4): 717-731.
[18] BASLAMISLI A S, GROENESTEGE T T, DAS P, et al. Joint Learning of Intrinsic Images and Semantic Segmentation // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 289-305.
[19] FAN Q N, YANG J L, HUA G, et al. Revisiting Deep Intrinsic Image Decompositions // Proc of the IEEE/CVF Conference on Com-puter Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 8944-8952.
[20] TAPPEN M F, FREEMAN W T, ADELSON E H. Recovering Intrinsic Images from a Single Image // Proc of the 15th International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2002: 1367-1374.
[21] JANNER M, WU J J, DULJARNI T D, et al. Self-supervised Intrinsic Image Decomposition // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2017: 5936-5946.
[22] CHANG J, CABEZAS R, FISHER III J W. Bayesian Nonparame-tric Intrinsic Image Decomposition // Proc of the European Confe-rence on Computer Vision. Berlin, Germany: Springer, 2014: 704-719.
[23] MA W C, CHU H, ZHOU B L, et al. Single Image Intrinsic Decomposition without a Single Intrinsic Image // Proc of the Euro-pean Conference on Computer Vision. Berlin, Germany: Springer, 2018: 211-229.
[24] LI C M, XU C Y, ANDERSON A W, et al. MRI Tissue Classification and Bias Field Estimation Based on Coherent Local Intensity Clustering: A Unified Energy Minimization Framework // Proc of the International Conference on Information Processing in Medical Imaging. Berlin, Germany: Springer, 2009: 288-299.
[25] LI C M, HUANG R, DING Z H, et al. A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities with Application to MRI. IEEE Transactions on Image Processing, 2011, 20(7): 2007-2016.
[26] WANG L, ZHU J B, SHENG M, et al. Simultaneous Segmentation and Bias Field Estimation Using Local Fitted Images. Pattern Re-cognition, 2018, 74: 145-155.
[27] CAI Q, LIU H Y, ZHOU S P, et al. An Adaptive-Scale Active Contour Model for Inhomogeneous Image Segmentation and Bias Field Estimation. Pattern Recognition, 2018, 82: 79-93.
[28] LI C M, GORE J C, DAVATZIKOS C. Multiplicative Intrinsic Component Optimization(MICO) for MRI Bias Field Estimation and Tissue Segmentation. Magnetic Resonance Imaging, 2014, 32(7): 913-923.
[29] YANG Y Y, WANG R F, FENG C. A New Method for Simulta-neous Moderate Bias Correction and Image Segmentation. IET Image Processing, 2019, 13(6): 939-945.
[30] WAN F K, SMEDBY Ö, WANG C L. Simultaneous MR Knee Image Segmentation and Bias Field Correction Using Deep Learning and Partial Convolution[C/OL]. [2020-06-12]. https://doi.org/10.1117/12.2512950.
[31] ZHANG Y, BRADY M, SMITH S. Segmentation of Brain MR Images through a Hidden Markov Random Field Model and the Expectation-Maximization Algorithm. IEEE Transactions on Medical Imaging, 2001, 20(1): 45-57.
[32] WELLS III W M, GRIMSON W E L, KIKINIS R, et al. Adaptive Segmentation of MRI Data. IEEE Transactions on Medical Imaging, 1996, 15(4): 429-442.
[33] PHAM D L, PRINCE J L. Adaptive Fuzzy Segmentation of Magnetic Resonance Images. IEEE Transactions on Medical Imaging, 1999, 18(9): 737-752.
[34] WARNER F W. Foundations of Differentiable Manifolds and Lie Group. Berlin, Germany: Springer-Verlag, 1983.
[35] WENDLAND H. Fast Evaluation of Radial Basis Functions: Me-thods Based on Partition of Unity // CHUI C K, SCHUMAKER L L, STÖCKLER J, eds. Approximation Theory X: Wavelets, Splines, and Applications. Nashville, USA: Vanderbilt University Press, 2002: 473-483.
[36] POWELL M J D. Approximation Theory and Methods. Cambridge, UK: Cambridge University Press, 1981.
[37] GROSSE R, JOHNSON M K, ADELSON E H, et al. Ground Truth Dataset and Baseline Evaluations for Intrinsic Image Algorithms // Proc of the 12th IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2009: 2335-2342.