Convolutional neural image recognition algorithm based on LeNet-5

Wan-zheng ZHANG; Zhi-kun HU; Xiao-long LI

doi:10.3788/YJYXS20203505.0486

您当前的位置：

首页 >

文章列表页 >

Convolutional neural image recognition algorithm based on LeNet-5

Image Processing | 更新时间：2020-08-12

- Convolutional neural image recognition algorithm based on LeNet-5
- Chinese Journal of Liquid Crystals and Displays Vol. 35, Issue 5, Pages: 486-490(2020)
- 作者机构：
  
  智洋创新科技股份有限公司, 山东淄博 255086
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20203505.0486
  CLC： TP391.41
- Received：25 October 2019，
  
  Revised：06 January 2020，
  
  Accepted：06 January 2020，
  
  Published：05 May 2020
- 稿件说明：
移动端阅览
Wan-zheng ZHANG, Zhi-kun HU, Xiao-long LI. Convolutional neural image recognition algorithm based on LeNet-5[J]. Chinese journal of liquid crystals and displays, 2020, 35(5): 486-490.
DOI：

Wan-zheng ZHANG, Zhi-kun HU, Xiao-long LI. Convolutional neural image recognition algorithm based on LeNet-5[J]. Chinese journal of liquid crystals and displays, 2020, 35(5): 486-490. DOI： 10.3788/YJYXS20203505.0486.

摘要

为了提升道路交通标志的识别准确率以及实施性能，本文提出一种改进的LeNet-5卷积神经网络结构对交通标志图像进行训练。首先在检测阶段，采用基于颜色的轻量级分割算法和Hough变换算法提取交通标志的目标区域，并控制算法复杂度使该识别系统基本满足实时性要求，再利用LeNet-5对交通标志进行分类识别。在实际的校园道路在线识别试验中进行检测，结果表明，18个交通标志通过驾驶均在本文的算法中成功识别，其运行速率达到16.9 Hz，基本满足交通标志识别稳定、实时等性能要求。

Abstract

In order to improve the recognition accuracy and implementation performance of road traffic signs

an improved LeNet-5 convolutional neural network structure is proposed to train 18 kinds of traffic sign images. Firstly

in the detection phase

the light-weight segmentation algorithm based on color and Hough transform algorithm is used to extract the target area of traffic signs

and the complexity of the control algorithm makes the recognition system basically meet the real-time requirements

and then LeNet-5 is used to classify and recognize traffic signs. The results show that the traffic signs are successfully identified by driving in the algorithm of this paper

and the running speed reaches 16.9 Hz

which basically meets the performance requirements of traffic sign recognition

such as stability

real-time and so on.

关键词

Keywords

references

吕能超 , 段至诚 , 吴超仲 . 驾驶经验对先进驾驶辅助系统的作用研究 . 交通运输系统工程与信息 , 2017 . 17 ( 6 ): 48 - 55 . http://d.old.wanfangdata.com.cn/Periodical/jtysxtgcyxx201706008 http://d.old.wanfangdata.com.cn/Periodical/jtysxtgcyxx201706008 .

N C LV , Z C DUAN , C Z WU . The impact of driving experience on advanced driving assistant systems . Journal of Transportation Systems Engineering and Information Technology , 2017 . 17 ( 6 ): 48 - 55 . http://d.old.wanfangdata.com.cn/Periodical/jtysxtgcyxx201706008 http://d.old.wanfangdata.com.cn/Periodical/jtysxtgcyxx201706008 .

孙涛 , 张志伟 . 基于Kalman滤波器的车道保持辅助系统研究 . 计算机应用与软件 , 2014 . 31 ( 1 ): 54 - 56, 68 . DOI: 10.3969/j.issn.1000-386x.2014.01.015 http://doi.org/10.3969/j.issn.1000-386x.2014.01.015 .

T SUN , Z W ZHANG . On lane-keeping-assist system based on Kalman filter . Computer Applications and Software , 2014 . 31 ( 1 ): 54 - 56, 68 . DOI: 10.3969/j.issn.1000-386x.2014.01.015 http://doi.org/10.3969/j.issn.1000-386x.2014.01.015 .

朱双东 , 张懿 , 陆晓峰 . 三角形交通标志的智能检测方法 . 中国图象图形学报 , 2006 . 11 ( 8 ): 1127 - 1131 . DOI: 10.3969/j.issn.1006-8961.2006.08.013 http://doi.org/10.3969/j.issn.1006-8961.2006.08.013 .

S D ZHU , Y ZHANG , X F LU . Intelligent approach for triangle traffic sign detection . Journal of Image and Graphics , 2006 . 11 ( 8 ): 1127 - 1131 . DOI: 10.3969/j.issn.1006-8961.2006.08.013 http://doi.org/10.3969/j.issn.1006-8961.2006.08.013 .

张邯.基于卷积神经网络的交通标志图像识别方法研究[D].桂林: 广西师范大学, 2018.

ZHANG H.Traffic sign image recognition method based on convolution neural network[D]. Guilin: Guangxi Normal University, 2018. (in Chinese)

Y LECUN , L BOTTOU , Y BENGIO , 等 . Gradient-based learning applied to document recognition . Proceedings of the IEEE , 1998 . 86 ( 11 ): 2278 - 2324 . DOI: 10.1109/5.726791 http://doi.org/10.1109/5.726791 .

吴银花 , 金龙旭 , 张柯 . 应用 J mode 值单调性的快速P帧模式选择算法 . 液晶与显示 , 2012 . 28 ( 2 ): 266 - 272 . http://yjyxs.com/CN/abstract/abstract9399.shtml http://yjyxs.com/CN/abstract/abstract9399.shtml .

Y H WU , L X JIN , K ZHANG . Fast P-frame mode decision algorithm using monotonicity of J mode . Chinese Journal of Liquid Crystals and Displays , 2012 . 28 ( 2 ): 266 - 272 . http://yjyxs.com/CN/abstract/abstract9399.shtml http://yjyxs.com/CN/abstract/abstract9399.shtml .

代勤 , 王延杰 , 韩广良 . 基于改进Hough变换和透视变换的透视图像矫正 . 液晶与显示 , 2012 . 27 ( 4 ): 552 - 556 . http://yjyxs.com/CN/abstract/abstract9208.shtml http://yjyxs.com/CN/abstract/abstract9208.shtml .

Q DAI , Y J WANG , G L HAN . Perspective image rectification based on improved Hough transformation and perspective transformation . Chinese Journal of Liquid Crystals and Displays , 2012 . 27 ( 4 ): 552 - 556 . http://yjyxs.com/CN/abstract/abstract9208.shtml http://yjyxs.com/CN/abstract/abstract9208.shtml .

钱晓亮 , 郭雷 , 余博 . 基于目标尺度的自适应高斯滤波 . 计算机工程与应用 , 2010 . 46 ( 12 ): 14 - 16, 20 . DOI: 10.3778/j.issn.1002-8331.2010.12.004 http://doi.org/10.3778/j.issn.1002-8331.2010.12.004 .

X L QIAN , L GUO , B YU . Adaptive Gaussian filter based on object scale . Computer Engineering and Applications , 2010 . 46 ( 12 ): 14 - 16, 20 . DOI: 10.3778/j.issn.1002-8331.2010.12.004 http://doi.org/10.3778/j.issn.1002-8331.2010.12.004 .

孟立娜 , 韩其睿 . 一种全局和局部相结合的二值化方法研究 . 计算机技术与发展 , 2012 . 22 ( 11 ): 116 - 119 . http://d.old.wanfangdata.com.cn/Periodical/wjfz201211031 http://d.old.wanfangdata.com.cn/Periodical/wjfz201211031 .

L N MENG , Q R HAN . An improvedbinarization method combined global thresholding with local thresholding . Computer Technology and Development , 2012 . 22 ( 11 ): 116 - 119 . http://d.old.wanfangdata.com.cn/Periodical/wjfz201211031 http://d.old.wanfangdata.com.cn/Periodical/wjfz201211031 .

张帆 , 韩树奎 , 张立国 , 等 . Canny算法的GPU并行加速 . 中国光学 , 2017 . 10 ( 6 ): 737 - 743 . http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201706006 http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201706006 .

F ZHANG , S K HAN , L G ZHANG , 等 . Parallel acceleration of Canny algorithm based on GPU . Chinese Optics , 2017 . 10 ( 6 ): 737 - 743 . http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201706006 http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201706006 .

芦碧波 , 扈天卿 , 刘甜甜 . 面向线束端子显微图像分割的变指数色度滤波 . 光学精密工程 , 2019 . 27 ( 8 ): 1894 - 1900 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201908025 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201908025 .

B B LU , T Q HU , T T LIU . Variable exponential chromaticity filtering for microscopic image segmentation of wire harness terminals . Optics and Precision Engineering , 2019 . 27 ( 8 ): 1894 - 1900 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201908025 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201908025 .

吴阳阳 , 彭广德 , 吴相飞 . 基于LeNet-5改进的卷积神经网络图像识别方法 . 信息与电脑 , 2018 . ( 7 ): 127 - 130 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xxydn201807052 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xxydn201807052 .

Y Y WU , G D PENG , X F WU . An improved connetal neural network image recognition method based on LeNet-5 . China Computer & Communication , 2018 . ( 7 ): 127 - 130 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xxydn201807052 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xxydn201807052 .

李培秀 , 李致金 , 韩可 , 等 . 基于Caffe深度学习框架的标签缺陷检测应用研究 . 中国电子科学研究院学报 , 2019 . 14 ( 2 ): 118 - 122 . http://d.old.wanfangdata.com.cn/Periodical/dzkxjspl201902002 http://d.old.wanfangdata.com.cn/Periodical/dzkxjspl201902002 .

P X LI , Z J LI , K HAN , 等 . Application research of label defect detection based on Caffe deep learning framework . Journal of China Academy of Electronics and Information Technology , 2019 . 14 ( 2 ): 118 - 122 . http://d.old.wanfangdata.com.cn/Periodical/dzkxjspl201902002 http://d.old.wanfangdata.com.cn/Periodical/dzkxjspl201902002 .

JIA Y Q, SHELHAMER E, DONAHUE J, et al . Caffe: convolutional architecture for fast feature embedding[C]// Proceedings of the 22 nd ACM International Conference on Multimedia . Orlando, Florida: ACM, 2014: 675-678.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Design of heterogeneous FPGA hardware accelerator based on CNN

Lightweight image super-resolution combining residual learning and layer attention

Remote sensing image change detection based on CNN-Transformer structure

Wavefront correction method based on P-U-net for pyramid wavefront detector

Image rain removal algorithm based on multi-cascade progressive convolution structure

Related Author

JI Haolin

XU Wei

PIAO Yongjie

WU Xiaobin

GAO Tan

WU Difan

ZHANG Xuande

PAN Mengyang

Related Institution

Key Laboratory of Space-based Dynamic & Rapid Optical Imaging Technology， Chinese Academy of Sciences

Changchun Institute of Optics， Fine Mechanics and Physics， Chinese Academy of Sciences

University of Chinese Academy of Sciences

School of Electronic Information and Artificial Intelligence， Shaanxi University of Science & Technology， Xi′an

Key Laboratory of Electro-Optical Countermeasure Test & Evaluation Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@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