The effect of structure on image classification using signatures

被引：0
|
作者：
Raymond Roccaforte
Florian Raudies
机构：
[1] Hewlett Packard Labs,
来源：
Biological Cybernetics | 2018年 / 112卷
关键词：
Image classification; Invariance; Signature;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Humans recognize transformed images from a very small number of samples. Inspired by this idea, we evaluate a classification method that requires only one sample per class, while providing invariance to image transformations generated by a compact group. This method is based on signatures computed for images. We test and illustrate this theory through simulations that highlight the role of image structure and sampling density, as well as how the signatures are constructed. We extend the existing theory to account for variations in recognition accuracy due to image structure.
引用
收藏
页码：415 / 425
页数：10
相关论文
共 50 条
  • [1] The effect of structure on image classification using signatures
    Roccaforte, Raymond
    Raudies, Florian
    BIOLOGICAL CYBERNETICS, 2018, 112 (05) : 415 - 425
  • [2] Image classification using pseudo power signatures
    Venkatachalam, V
    2000 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL I, PROCEEDINGS, 2000, : 796 - 799
  • [3] Discriminative signatures for image classification
    Zhang, Ziming
    Chan, Syin
    Chia, Liang-Tien
    2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7, 2007, : 761 - 764
  • [4] Polarimetric image classification using optimal decomposition of radar polarization signatures
    Dong, YH
    Forster, B
    Ticehurst, C
    IGARSS '96 - 1996 INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM: REMOTE SENSING FOR A SUSTAINABLE FUTURE, VOLS I - IV, 1996, : 1556 - 1558
  • [5] Natural scene classification and retrieval using ridgelet-based image signatures
    Le Borgne, H
    O'Connor, N
    ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, PROCEEDINGS, 2005, 3708 : 116 - 122
  • [6] Textural classification using textural signatures
    Kourgli, A
    Belhadj-Aissa, A
    REMOTE SENSING IN THE 21ST CENTURY: ECONOMIC AND ENVIRONMENTAL APPLICATIONS, 2000, : 557 - 561
  • [7] Ships classification using hydroacoustic signatures
    Zak, Andrzej
    CIMMACS '07: PROCEEDINGS OF THE 6TH WSEAS INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, MAN-MACHINE SYSTEMS AND CYBERNETICS, 2007, : 111 - +
  • [8] Textural classification using textural signatures
    Kourgli, A
    Belhadj-Aissa, A
    REMOTE SENSING IN THE 21ST CENTURY: ECONOMIC AND ENVIRONMENTAL APPLICATIONS, 2000, : 293 - 297
  • [9] RCC classification using miRNA signatures
    Annette Fenner
    Nature Reviews Urology, 2011, 8 (3) : 120 - 120
  • [10] Electronic Medical Record Context Signatures Improve Diagnostic Classification Using Medical Image Computing
    Chaganti, Shikha
    Mawn, Louise A.
    Kang, Hakmook
    Egan, Josephine
    Resnick, Susan M.
    Beason-Held, Lori L.
    Landman, Bennett A.
    Lasko, Thomas A.
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2019, 23 (05) : 2052 - 2062
12345