Image classification technology based on inception V3

ni WANG-Yi

doi:10.3788/YJYXS20203504.0389

您当前的位置：

首页 >

文章列表页 >

Image classification technology based on inception V3

Image Processing | 更新时间：2020-07-05

- Image classification technology based on inception V3
- Chinese Journal of Liquid Crystals and Displays Vol. 35, Issue 4, Pages: 389-394(2020)
- 作者机构：
  
  重庆商务职业学院, 重庆 401331
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20203504.0389
  CLC： TP391.4
- Received：26 September 2019，
  
  Revised：04 November 2019，
  
  Accepted：04 November 2019，
  
  Published：05 April 2020
- 稿件说明：
移动端阅览
ni WANG-Yi. Image classification technology based on inception V3[J]. Chinese journal of liquid crystals and displays, 2020, 35(4): 389-394.
DOI：

ni WANG-Yi. Image classification technology based on inception V3[J]. Chinese journal of liquid crystals and displays, 2020, 35(4): 389-394. DOI： 10.3788/YJYXS20203504.0389.

摘要

为了实现对物体状态的分类识别，本文在GoogLeNet的Inception V3模块基础上进行了优化，使用Tanh作为激活函数并结合RMSprop，SGD优化器提升了模型的准确率。首先采用三次卷积插值，GAN对图像集进行预处理，再利用Inception对图像进行训练，最后结合RMSprop和SGD优化器对模型进行优化。用本文提出的模型在20个烹饪对象的图像上进行实验，结果表明，本文优化的Inception V3模型能够以71.5%的准确度对这些图像的状态进行分类，与对比算法相比，在分类准确度、训练损失上都有明显提升，可以满足图像分类的可靠性、稳定性等要求。

Abstract

In order to realize the classification and recognition of object state

the Inception V3 module on the basis of GoogLeNet is optimized Using Tanh as the activation function and RMSprop

the SGD optimizer improves the accuracy of the model. Firstly

using cubic convolution interpolation

GAN preprocesses the image set. Then

the Inception is used to train the image. Finally

the SGD optimizer is combined with RMSprop to optimize the model. Experiments on the images of 20 cooking objects using the model proposed in this paper show that the optimized Inception V3 model can classify the state of these images with 71.5% accuracy. Compared with the comparison algorithm

the classification accuracy and training loss are obviously improved

which can meet the requirements of reliability and stability of image classification.

关键词

Keywords

references

郭敬明 , 何昕 , 魏仲慧 . 基于在线支持向量机的Mean Shift彩色图像跟踪 . 液晶与显示 , 2014 . 29 ( 1 ): 120 - 128 . http://yjyxs.com/CN/abstract/abstract9642.shtml http://yjyxs.com/CN/abstract/abstract9642.shtml .

J M GUO , X HE , Z H WEI . New mean shift tracking for color image based on online support vector machine . Chinese Journal of Liquid Crystals and Displays , 2014 . 29 ( 1 ): 120 - 128 . http://yjyxs.com/CN/abstract/abstract9642.shtml http://yjyxs.com/CN/abstract/abstract9642.shtml .

李彦冬 , 郝宗波 , 雷航 . 卷积神经网络研究综述 . 计算机应用 , 2016 . 36 ( 9 ): 2508 - 2515 . http://d.old.wanfangdata.com.cn/Periodical/jsjxb201706001 http://d.old.wanfangdata.com.cn/Periodical/jsjxb201706001 .

D LIY , Z B HAO , H LEI . Survey of convolutional neural network . Journal of Computer Applications , 2016 . 36 ( 9 ): 2508 - 2515 . http://d.old.wanfangdata.com.cn/Periodical/jsjxb201706001 http://d.old.wanfangdata.com.cn/Periodical/jsjxb201706001 .

黄伟国 , 顾超 , 朱忠奎 . 用于目标识别的PCA-SC形状匹配算法 . 光学精密工程 , 2013 . 21 ( 8 ): 2103 - 2110 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201308026 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201308026 .

W G HUANG , C GU , Z K ZHU . PCA-SC shape matching for object recognition . Optics and Precision Engineering , 2013 . 21 ( 8 ): 2103 - 2110 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201308026 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201308026 .

王飞 , 李定主 . 模式识别中贝叶斯决策理论的研究 . 科技情报开发与经济 , 2007 . 17 ( 7 ): 165 - 166 . DOI: 10.3969/j.issn.1005-6033.2007.07.095 http://doi.org/10.3969/j.issn.1005-6033.2007.07.095 .

F WANG , D Z LI . Research on Bayesian decision-making theory in pattern recognition . Sci-Tech Information Development & Economy , 2007 . 17 ( 7 ): 165 - 166 . DOI: 10.3969/j.issn.1005-6033.2007.07.095 http://doi.org/10.3969/j.issn.1005-6033.2007.07.095 .

刘成颖 , 吴昊 , 王立平 , 等 . 基于PSO优化LS-SVM的刀具磨损状态识别 . 清华大学学报:自然科学版 , 2017 . 57 ( 9 ): 975 - 979 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb201709014 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb201709014 .

C Y LIU , H WU , L P WANG , 等 . Tool wear state recognition based on LS-SVM with the PSO algorithm . Journal of Tsinghua University:Science and Technology , 2017 . 57 ( 9 ): 975 - 979 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb201709014 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=qhdxxb201709014 .

杨昌其 , 谭娟 , 仇争平 . 基于BP神经网络的管制员疲劳状态识别研究 . 航空计算技术 , 2018 . 48 ( 1 ): 17 - 20, 25 . DOI: 10.3969/j.issn.1671-654X.2018.01.005 http://doi.org/10.3969/j.issn.1671-654X.2018.01.005 .

C Q YANG , J TAN , Z P QIU . Controller's fatigue recognition based on BP neural network . Aeronautical Computing Technique , 2018 . 48 ( 1 ): 17 - 20, 25 . DOI: 10.3969/j.issn.1671-654X.2018.01.005 http://doi.org/10.3969/j.issn.1671-654X.2018.01.005 .

刘建伟 , 刘媛 , 罗雄麟 . 深度学习研究进展 . 计算机应用研究 , 2014 . 31 ( 7 ): 1921 - 1930, 1942 . DOI: 10.3969/j.issn.1001-3695.2014.07.001 http://doi.org/10.3969/j.issn.1001-3695.2014.07.001 .

J W LIU , Y LIU , X L LUO . Research and development on deep learning . Application Research of Computers , 2014 . 31 ( 7 ): 1921 - 1930, 1942 . DOI: 10.3969/j.issn.1001-3695.2014.07.001 http://doi.org/10.3969/j.issn.1001-3695.2014.07.001 .

X WANG , Y DING , M Y LIU , 等 . Efficient implementation of a cubic-convolution based image scaling engine . Journal of Zhejiang University Science C , 2011 . 12 ( 9 ): 743 - 753 . DOI: 10.1631/jzus.C1100040 http://doi.org/10.1631/jzus.C1100040 .

李俭川 , 秦国军 , 温熙森 , 等 . 神经网络学习算法的过拟合问题及解决方法 . 振动、测试与诊断 , 2002 . 22 ( 4 ): 260 - 264 . DOI: 10.3969/j.issn.1004-6801.2002.04.003 http://doi.org/10.3969/j.issn.1004-6801.2002.04.003 .

J C LI , G J QIN , X S WEN , 等 . Over-fitting in neural network learning algorithms and its solving strategies . Journal of Vibration Measurement & Diagnosis , 2002 . 22 ( 4 ): 260 - 264 . DOI: 10.3969/j.issn.1004-6801.2002.04.003 http://doi.org/10.3969/j.issn.1004-6801.2002.04.003 .

A RADFORD , L METZ , S CHINTALA . Unsupervised representation learning with deep convolutional generative adversarial networks . ArXiv , 2015 . 1511 06434 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=aab7df43d42b6a78906b2e140bef7751 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=aab7df43d42b6a78906b2e140bef7751 .

CHEN J C, PATEL V M, CHELLAPPA R. Unconstrained face verification using deep CNN features[C]// Proceedings of 2016 IEEE Winter Conference on Applications of Computer Vision . Lake Placid, NY, USA: IEEE, 2016: 1-9.

G KRON . Tensor analysis of networks . Students' Quarterly Journal , 1996 . 36 ( 143 ): 171 http://d.old.wanfangdata.com.cn/OAPaper/oai_pubmedcentral.nih.gov_3116899 http://d.old.wanfangdata.com.cn/OAPaper/oai_pubmedcentral.nih.gov_3116899 .

E G FAN . Extended Tanh-function method and its applications to nonlinear equations . Physics Letters A , 2000 . 277 ( 4-5 ): 212 - 218 . DOI: 10.1016/S0375-9601(00)00725-8 http://doi.org/10.1016/S0375-9601(00)00725-8 .

杨江涛 , 唐军 , 王玉波 , 等 . 用于应力测量的可调谐光栅 . 光学精密工程 , 2018 . 26 ( 7 ): 1596 - 1603 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201807005 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201807005 .

J T YANG , J TANG , Y B WANG , 等 . Tunable grating for stress measurement . Optics and Precision Engineering , 2018 . 26 ( 7 ): 1596 - 1603 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201807005 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201807005 .

郁晓晖 , 高志山 , 袁群 . 宽光谱长工作距弱荧光信号检测显微物镜设计 . 光学精密工程 , 2018 . 26 ( 7 ): 1588 - 1595 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201807004 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201807004 .

X H YU , Z S GAO , Q YUAN . Design of board spectrum and long work distance microscope objective for weak fluorescence signal detection . Optics and Precision Engineering , 2018 . 26 ( 7 ): 1588 - 1595 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201807004 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201807004 .

林旭东 , 刘欣悦 , 王帅 , 等 . 桌面97单元自适应光学系统性能测试 . 光学精密工程 , 2016 . 24 ( 6 ): 1272 - 1280 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201606006 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201606006 .

X D LIN , X Y LIU , S WANG , 等 . Performance testing of a desk-top 97-element adaptive optical system . Optics and Precision Engineering , 2016 . 24 ( 6 ): 1272 - 1280 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201606006 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201606006 .

CHEN A J H, WANG B C W, JENG C J H. A preliminary study of ANN implementing image filters[C]// Proceedings of 2013 International Symposium on Next-generation Electronics . Kaohsiung, China: IEEE, 2013: 181-184.

KESKAR N S, SOCHER R. Improving generalization performance by switching from Adam to SGD[J]. arXiv , 2017, 712: 07628.

Views

160

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

High-throughput blue phase liquid crystal recognition based on convolutional neural network

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

Related Author

Ya-qian ZHANG

Yong-feng CUI

Hao WANG

Wan-li HE

Lei ZHANG

Zhou YANG

Hui CAO

Dong WANG

Related Institution

School of materials science and engineering， University of science and Technology Beijing

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

University of Chinese Academy of Sciences

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

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

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