Recognition of Wood Defects Based on Artificial Neural Network

被引：0
|
作者：
Mu, Hongbo [1 ]
Qi, Dawei [1 ]
机构：
[1] NE Forestry Univ, Dept Phys, Harbin, Heilongjiang Pr, Peoples R China
来源：
2008 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS, VOLS 1-3 | 2008年
关键词：
Artificial neural network; Nondestructive testing; Image processing;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The recognition model of wood defects based on artificial neural network (ANN) was presented for classifying the defects effectively. X-ray was adopted as a measure method for log nondestructive testing. Applying MATLAB and VC++ image processing program processed the image of log with defects and extracted the characters of the image. The mathematic model of defects recognition was established according to characteristic parameters. So back propagating networks was constructed. In this paper, three common defects which are knot, grub-hole and rot were studied. The experimental results show that ANN is an effective method for the nondestructive testing and classifying of three defects. This method also can be used in other log defects nondestructive testing and classifying.
引用
收藏
页码：1232 / 1237
页数：6
相关论文
共 50 条
  • [1] Pattern recognition of wood material defects using wavelet and artificial neural network
    Key Laboratory of Bio-Based Material Science and Technology of Ministry of Education, Northeast Forestry University, Harbin 150040, China
    Zhendong Ceshi Yu Zhenduan, 2009, 3 (274-277):
  • [2] Wood Defects Classification Using Artificial Neural Network
    de Jesus Ramirez Alonso, Graciela Maria
    Chacon Murguia, Mario Ignacio
    COMPUTACION Y SISTEMAS, 2005, 9 (01): : 17 - 27
  • [3] Wood Defects Classification Using Artificial Metaplasticity Neural Network
    Marcano-Cedeno, Alexis
    Quintanilla-Dominguez, J.
    Andina, D.
    IECON: 2009 35TH ANNUAL CONFERENCE OF IEEE INDUSTRIAL ELECTRONICS, VOLS 1-6, 2009, : 3246 - +
  • [4] Research on Edge Defects Image Recognition Technology Based on Artificial Neural Network
    Chen, Naijian
    Men, Xiuhua
    Hua, Cheng
    Wang, Xu
    Han, Xiangdong
    Chen, Hui
    PROCEEDINGS OF THE 2018 13TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA 2018), 2018, : 1929 - 1933
  • [5] Automated Recognition of Wood Damages using Artificial Neural Network
    Dong, Zhao
    2009 INTERNATIONAL CONFERENCE ON MEASURING TECHNOLOGY AND MECHATRONICS AUTOMATION, VOL III, 2009, : 195 - 197
  • [6] Leaf Recognition based on Artificial Neural Network
    Ayaz, Furkan
    Ari, Ali
    Hanbay, Davut
    2017 INTERNATIONAL ARTIFICIAL INTELLIGENCE AND DATA PROCESSING SYMPOSIUM (IDAP), 2017,
  • [7] Wood Defect Identification Based on Artificial Neural Network
    Zhu, Xiao-dong
    Cao, Jun
    Wang, Feng-hu
    Sun, Jian-ping
    Liu, Yu
    COMPUTATIONAL INTELLIGENCE AND INTELLIGENT SYSTEMS, 2009, 51 : 207 - 214
  • [8] Artificial Neural Network Based Sinhala Character Recognition
    Premachandra, H. Waruna H.
    Premachandra, Chinthaka
    Kimura, Tomotaka
    Kawanaka, Hiroharu
    COMPUTER VISION AND GRAPHICS, ICCVG 2016, 2016, 9972 : 594 - 603
  • [9] Recognition of partial discharge based on artificial neural network
    Tan, Kexiong
    Zhu, Deheng
    Wang, Zhenyuan
    Zeng, Dongsong
    Gaodianya Jishu/High Voltage Engineering, 1996, 22 (01): : 21 - 24
  • [10] Hyperspectral Image Recognition Based on Artificial Neural Network
    Liang, Feng
    Liu, Hanhu
    Wang, Xiao
    Liu, Yanyan
    NEUROQUANTOLOGY, 2018, 16 (05) : 699 - 705
12345