Improving classification of neural networks by reducing lens aperture

被引：0
|
作者：
Stainvas, I [1 ]
Zalevsky, Z [1 ]
Mendlovic, D [1 ]
Intrator, N [1 ]
机构：
[1] Tel Aviv Univ, Sch Comp Sci, IL-69978 Tel Aviv, Israel
来源：
APPLICATIONS AND SCIENCE OF NEURAL NETWORKS, FUZZY SYSTEMS, AND EVOLUTIONARY COMPUTATION V | 2002年 / 4787卷
关键词：
classification network; face recognition; network ensembles; image blur; lens aperture; artificial neural networks; hybrid architecture;
D O I：
10.1117/12.453545
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Image blur strongly degrades object recognition. We propose a mechanism to reduce defocus blur by reducing the aperture of the camera lens, and show that it leads to a far more robust recognition. The recognition is demonstrated via a Neural Network architecture that we have previously proposed for blurred face recognition.
引用
收藏
页码：267 / 276
页数：10
相关论文
共 50 条
  • [1] Convolutional Neural Networks for Synthetic Aperture Radar Classification
    Profeta, Andrew
    Rodriguez, Andres
    Clouse, H. Scott
    ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY XXIII, 2016, 9843
  • [2] Improving the Performance of Convolutional Neural Networks for Image Classification
    Optical Memory and Neural Networks, 2021, 30 : 51 - 66
  • [3] Improving the Performance of Convolutional Neural Networks for Image Classification
    Giveki, Davar
    OPTICAL MEMORY AND NEURAL NETWORKS, 2021, 30 (01) : 51 - 66
  • [4] Improving prediction performance of neural networks in pattern classification
    Kim, D
    INTERNATIONAL JOURNAL OF COMPUTER MATHEMATICS, 2005, 82 (04) : 391 - 399
  • [5] Train Fast While Reducing False Positives: Improving Animal Classification Performance Using Convolutional Neural Networks
    Moreni, Mael
    Theau, Jerome
    Foucher, Samuel
    GEOMATICS, 2021, 1 (01): : 34 - 49
  • [6] Improving code readability classification using convolutional neural networks
    Mi, Qing
    Keung, Jacky
    Xiao, Yan
    Mensah, Solomon
    Gao, Yujin
    INFORMATION AND SOFTWARE TECHNOLOGY, 2018, 104 : 60 - 71
  • [7] Improving Multilabel Text Classification with Stacking and Recurrent Neural Networks
    Mansueli, Rodrigo
    Domingues, Marcos Aurelio
    Feltrim, Valeria Delisandra
    PROCEEDINGS OF THE 28TH BRAZILIAN SYMPOSIUM ON MULTIMEDIA AND THE WEB, WEBMEDIA 2022, 2022, : 117 - 122
  • [8] Improving disturbance classification by combining multiple artificial neural networks
    Lira, Milde M. S.
    de Aquino, Ronaldo R. B.
    Ferreira, Aida A.
    Carvalho, Manoel A., Jr.
    Lira, Carlos A. B. O.
    2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10, 2006, : 3436 - +
  • [9] Improving ECG diagnostic classification by combining multiple neural networks
    de Chazal, P
    Celler, B
    COMPUTERS IN CARDIOLOGY 1997, VOL 24, 1997, 24 : 473 - 476
  • [10] Optimal linear combination of neural networks for improving classification performance
    Ueda, N
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (02) : 207 - 215
12345