Realization of within-class feature extracting based on Euclidean-like distance transform for traffic signs using simplied PCNN

WANG Meng-jun; YANG Lu; WANG Xia; LIU Jian-fei

doi:10.3788/OPE.20122012.2751

您当前的位置：

首页 >

文章列表页 >

Realization of within-class feature extracting based on Euclidean-like distance transform for traffic signs using simplied PCNN

Article | 更新时间：2020-08-13

- Realization of within-class feature extracting based on Euclidean-like distance transform for traffic signs using simplied PCNN
- Optics and Precision Engineering Vol. 20, Issue 12, Pages: 2751-2758(2012)
- 作者机构：
  
  1. 河北工业大学信息工程学院天津,300401
  2. 河北工业大学-Xilinx信号检测与处理联合实验室天津,300401
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20122012.2751
  CLC： TP391.41
- Received：19 July 2012，
  
  Revised：12 October 2012，
  
  Published：10 December 2012
- 稿件说明：
移动端阅览
王蒙军, 阳路, 王霞, 刘剑飞. 用简化脉冲耦合神经网络实现交通标志图像的类Euclidean距离变换类内特征提取[J]. 光学精密工程, 2012,20(12): 2751-2758

WANG Meng-jun, YANG Lu, WANG Xia, LIU Jian-fei. Realization of within-class feature extracting based on Euclidean-like distance transform for traffic signs using simplied PCNN[J]. Editorial Office of Optics and Precision Engineering, 2012,20(12): 2751-2758
王蒙军, 阳路, 王霞, 刘剑飞. 用简化脉冲耦合神经网络实现交通标志图像的类Euclidean距离变换类内特征提取[J]. 光学精密工程, 2012,20(12): 2751-2758 DOI： 10.3788/OPE.20122012.2751.

WANG Meng-jun, YANG Lu, WANG Xia, LIU Jian-fei. Realization of within-class feature extracting based on Euclidean-like distance transform for traffic signs using simplied PCNN[J]. Editorial Office of Optics and Precision Engineering, 2012,20(12): 2751-2758 DOI： 10.3788/OPE.20122012.2751.

摘要

脉冲耦合神经网络(PCNN)提取的特征序列的旋转不变性降低了道路交通标志类内匹配识别的准确性

为了提取更有利于形状分类的特征向量

本文利用PCNN的自动波扩散特性

简化了PCNN模型。采用简化PCNN模型产生的类Euclidean距离图像作为分类特征

利用最小方差值进行匹配分析

并通过实验选取了最佳PCNN参数。针对道路交通标志图像库GB5768-1999的实验结果表明

采用获得的类Euclidean距离图像作为特征向量进行分类匹配

在选定边缘图像的迭代次数

为16

反馈输入固有电势

为0.65

动态门限固有电势

为100

卷积核矩阵为55时

最小方差值均出现在对应的标准图像位置。结果表明

简化PCNN的类Euclidean距离变换能够有效提取二值边缘图像的形状信息。该方法优于传统PCNN熵序列的特征向量方法

类内区分效果更加明显。

Abstract

The recognition accuracy of with-in class matching traffic signs is dropped because of the rotation invariance in feature sequences extracted by conventional Pulse Coupled Neural Network(PCNN). In order to get a new feature vector with stronger classification ability

the PCNN mode was simplified according to its automatic wave diffusion characteristics. An Euclidean-like distance image was used as the new feature vector

and a match analysis was carried out by the minimum variance. Then

optimal parameters of PCNN were acquired through experiments. The experimental results based on GB5768-1999 traffic signs show that when the Euclidean-like distance transform based on simplified PCNN is used as the feature vector for classification matching

the variance of test image corresponding to standard images can achieve the minimum value in acquiring edge image with the number iterations of 16

magnitude adjustments of feeding input of 0.65

magnitude adjustments of dynamic threshold of 100

and convolution kernel matrix in 5 5. It concludes that the Euclidean-like distance transform based on simplified PCNN can expand the shape information of edge images effectively. It is superior to the feature vector based on entropy sequence

and is fit for the identification of target images in with-in classes.

关键词

Keywords

references

XU Q S, SU J, LIU T T. A detection and recognition method for prohibition traffic signs. Proceedings of IEEE International Conference on Image Analysis and Signal Processing, Xiamen, P.R. China: ICIASP, 2010: 583-586.[2] WANG Y P, SHI M P, WU T. A method of fast and robust for traffic sign recognition. Proceedings of 5th International Conference on Image and Graphics, Xi'an, P.R. China: ICIG, 2009:891-895.[3] GU Y L, YENDO T, TEHRANI M P, et al.. A new vision system for traffic sign recognition. Proceedings of IEEE Intelligent Vehicles Symposium, San Diego, CA: IVS, 2010: 7-12.[4] 陈洪波,王强,徐晓蓉,等. 用改进的Hough变换检测交通标志图像的直线特征[J]. 光学精密工程,2009,17(5):1111-1118. CHEN H B, WANG Q, XU X R, et.al.. Line detection in traffic sign image based on improved Hough transforms [J]. Opt. Precision Eng., 2009,17(5):1111-1118. (in Chinese)[5] TANG J, LIANG X, CHENG F Y, et al.. A method for traffic signs detection, tracking and recognition. Proceedings of 5th International Conference on Computer Science and Education, Changsha, P. R. China: ICCSE, 2010:189-194.[6] JOSHI M, GINGH M J, DALELA S. Automatic colored traffic sign detection using optoelectronic correlation architectures. Proceedings of IEEE International Conference on Vehicular Electronics and Safety, Columbus, OH: ICVES, 2008: 75-78. [7] ANDREY V, JO K H. Automatic detection and recognition of traffic signs using geometric structure analysis. Proceedings of International Joint Conference on SICE-ICASE, Busan, Korea:ICSCIE-ICASE, 2006:1451-1456.[8] RUGHOOPUTH S D D V, BUOOTUN H, RUGHOOPUTH H C S. Pulse coded neural networks for sign recognition for navigation. Proceedings of IEEE International Conference on Industrial Technology, Maribor, Slovenia:ICIT, 2003,1:89-94.[9] WANG ZH H, TIE Y, LIU Y P. Design and implementation of image fusion system. Proceedings of International Conference on Computer Application and System Modeling, Taiyuan, P.R. China: ICCASE, 2010,1:140-143.[10] 武治国,王延杰,李桂菊. 应用小波变换的自适应脉冲耦合神经网络在图像融合中的应用[J]. 光学精密工程,2010,18(3): 708-715. WU ZH G, WANG Y J, LI G J. Application of adaptive PCNN based on wavelet transform to image fusion [J]. Opt. Precision Eng., 2010, 18(3):708-715. (in Chinese)[11] WANG ZH B, MA Y D, CHENG F Y, et al.. Review of pulse-coupled neural networks [J]. Image and Vision Computing, 2010, 28 (10): 5-13.[12] 刘相滨,邹北骥,孙家广. 基于边界跟踪的快速欧氏距离变换算法[J]. 计算机学报,2006,29(2): 317-323. LIU X B, ZOU B J, SUN J G. Fast euclidean distance transform based on contour tracking [J]. Chinese Journal of Computers, 2006,29(2):317-323. (in Chinese)[13] 陆宗骐,朱煜. 用带形状校正的腐蚀膨胀实现Euclidean距离变换[J]. 中国图像图形学报,2010,15(2):294-300. LU Z Q, ZHU Y. Implementation of Euclidean distance transform using erosion and dilation with form correction [J]. Journal of Image and Graphics, 2010, 15(2):294-300. (in Chinese)

Views

269

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Hyperspectral images feature extraction and classification based on fractional differentiation

Lightweight deep global-local knowledge distillation network for hyperspectral image scene classification

Dense pedestrian detection algorithm in multi-branch non-anchor frame network

Application of SENet generative adversarial network in image semantics description

Semi-supervised dual path network for hyperspectral image classification

Related Author

LIU Jing

LI Yang

LIU Yi

LIU Yingxu

PU Chunyu

XU Diankun

YANG Yichuan

HUANG Hong

Related Institution

School of Electronic Engineering， Xidian University

School of Electronic Engineering， Xi’an University of Posts and Telecommunications

Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China， Chongqing University

Measurement and Control Technology and Instrument major， College of Optoelectronic Engineering， Chongqing University

School of Electrical Engineering， XinJiang University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰