Optimization of a hardware implementation for Pulse Coupled neural Networks for image applications

被引：0
|
作者：
Gimeno Sarciada, Jesus [1 ]
Lamela Rivera, Horacio [1 ]
Warde, Cardinal [2 ]
机构：
[1] Univ Carlos III Madrid, Grp Trabajo Optoelect & Tecnol Laser, C Butarque 15, Madrid 28911, Spain
[2] MIT, EECS Dept, Cambridge, MA 02139 USA
来源：
INDEPENDENT COMPONENT ANALYSES, WAVELETS, NEURAL NETWORKS, BIOSYSTEMS, AND NANOENGINEERING VIII | 2010年 / 7703卷
关键词：
Pulse Coupled Neural Networks; PCNN; image processing; Hardware implementation;
D O I：
10.1117/12.850778
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Pulse Coupled Neural Networks are a very useful tool for image processing and visual applications, since it has the advantages of being invariant to image changes as rotation, scale, or certain distortion. Among other characteristics, the PCNN changes a given image input into a temporal representation which can be easily later analyzed for pattern recognition. The structure of a PCNN though, makes it necessary to determine all of its parameters very carefully in order to function optimally, so that the responses to the kind of inputs it will be subjected are clearly discriminated allowing for an easy and fast post-processing yielding useful results. This tweaking of the system is a taxing process. In this paper we analyze and compare two methods for modeling PCNNs. A purely mathematical model is programmed and a similar circuital model is also designed. Both are then used to determine the optimal values of the several parameters of a PCNN: gain, threshold, time constants for feed-in and threshold and linking leading to an optimal design for image recognition. The results are compared for usefulness, accuracy and speed, as well as the performance and time requirements for fast and easy design, thus providing a tool for future ease of management of a PCNN for different tasks.
引用
收藏
页数：11
相关论文
共 50 条
  • [11] Pulse-coupled neural networks for medical image analysis
    Keller, PE
    McKinnon, D
    APPLICATIONS AND SCIENCE OF COMPUTATIONAL INTELLIGENCE II, 1999, 3722 : 444 - 451
  • [12] Image Denoising and Restoration Using Pulse Coupled Neural Networks
    Wen, Haijiao
    Wen, Jie
    2013 6TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING (CISP), VOLS 1-3, 2013, : 282 - 287
  • [13] Texture image segmentation using pulse coupled neural networks
    Yi, Li
    Qinye, Tong
    Yingle, Fan
    ICIEA 2007: 2ND IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS, VOLS 1-4, PROCEEDINGS, 2007, : 355 - +
  • [14] Contribution to Image Steganography Using Pulse Coupled Neural Networks
    Forgac, Radoslav
    Krakovsky, Roman
    2017 COMMUNICATION AND INFORMATION TECHNOLOGIES (KIT), 2017, : 37 - 42
  • [15] Pulse-coupled neural networks for medical image analysis
    Proc SPIE Int Soc Opt Eng, (444-451):
  • [16] Pulse-coupled neural networks and parameter optimization methods
    Xinzheng Xu
    Guanying Wang
    Shifei Ding
    Yuhu Cheng
    Xuesong Wang
    Neural Computing and Applications, 2017, 28 : 671 - 681
  • [17] Pulse-coupled neural networks and parameter optimization methods
    Xu, Xinzheng
    Wang, Guanying
    Ding, Shifei
    Cheng, Yuhu
    Wang, Xuesong
    NEURAL COMPUTING & APPLICATIONS, 2017, 28 : S671 - S681
  • [18] FPGA Implementation of Pulse Coupled Neural Network on for Time Series of an Image
    Zang, Xinzhe
    Gao, Zhenbin
    Li, Mengyuan
    Wang, Xia
    PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON ELECTRONICS AND ELECTRICAL ENGINEERING TECHNOLOGY (EEET 2018), 2018, : 212 - 216
  • [19] Pulse coupled neural networks (PCNN) and wavelets: Biosensor applications
    Padgett, ML
    Johnson, JL
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 2507 - 2512
  • [20] Hardware implementation of RAM neural networks
    Simes, ED
    Uebel, LF
    Augusto, D
    Barone, C
    PATTERN RECOGNITION LETTERS, 1996, 17 (04) : 421 - 429
12345