Registration of infrared transmission images using squared-loss mutual information

被引:2
作者
Sakai, Tomoya [1 ]
Sugiyama, Masashi [1 ]
Kitagawa, Katsuichi [2 ]
Suzuki, Kazuyoshi [2 ]
机构
[1] Tokyo Inst Technol, Meguro Ku, Tokyo 1528552, Japan
[2] Toray Engn Co Ltd, Otsu, Shiga 5202141, Japan
来源
PRECISION ENGINEERING-JOURNAL OF THE INTERNATIONAL SOCIETIES FOR PRECISION ENGINEERING AND NANOTECHNOLOGY | 2015年 / 39卷
关键词
Infrared transmission image; Image registration; Squared-loss mutual information;
D O I
10.1016/j.precisioneng.2014.09.001
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Infrared light allows us to measure the inner structure of opaque samples such as a semi-conductor. In this paper, we propose a method of registering multiple infrared transmission images obtained from different layers of a sample for 3D reconstruction. Since an infrared transmission image obtained from one layer is contaminated with defocused images coming from other layers, registration with a standard similarity metric such as the squared error and the cross correlation does not perform well. To cope with this problem, we propose to use the squared-loss mutual information as an alternative similarity measure for registration, which is more robust against noise than ordinary mutual information. The practical usefulness of the proposed method is demonstrated in simulated and actual experiments. (C) 2014 Elsevier Inc. All rights reserved.
引用
收藏
页码:187 / 193
页数:7
相关论文
共 17 条
  • [1] A SURVEY OF IMAGE REGISTRATION TECHNIQUES
    BROWN, LG
    [J]. COMPUTING SURVEYS, 1992, 24 (04) : 325 - 376
  • [2] Deshmukh M., 2011, International Journal of Image Processing, V5, P245
  • [3] A SURVEY OF AUTOMATED VISUAL INSPECTION
    NEWMAN, TS
    JAIN, AK
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 1995, 61 (02) : 231 - 262
  • [4] Computationally Efficient Estimation of Squared-Loss Mutual Information with Multiplicative Kernel Models
    Sakai, Tomoya
    Sugiyama, Masashi
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2014, E97D (04): : 968 - 971
  • [5] A MATHEMATICAL THEORY OF COMMUNICATION
    SHANNON, CE
    [J]. BELL SYSTEM TECHNICAL JOURNAL, 1948, 27 (03): : 379 - 423
  • [6] Sims V, 1996, ALGORITHMS LINEAR QU
  • [7] Slonaker S., 1988, Proceedings of the SPIE - The International Society for Optical Engineering, V922, P73
  • [8] Deformable Medical Image Registration: A Survey
    Sotiras, Aristeidis
    Davatzikos, Christos
    Paragios, Nikos
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2013, 32 (07) : 1153 - 1190
  • [9] Sugiyama M, 2012, DENSITY RATIO ESTIMATION IN MACHINE LEARNING, P1, DOI 10.1017/CBO9781139035613
  • [10] Machine Learning with Squared-Loss Mutual Information
    Sugiyama, Masashi
    [J]. ENTROPY, 2013, 15 (01) : 80 - 112