基于环形特征的卷积神经网络轮毂识别

doi:10.3969/j.issn.1000-1158.2022.06.05

摘要
图/表
参考文献(16)
相关文章 (15)

全文: PDF (2630 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对实际生产中不同种类轮毂的混流生产问题,提出了一种基于环形特征的卷积神经网络轮毂识别算法。将直角坐标下的环形轮毂映射到极坐标中,归一化为标准形式的矩形,提取轮毂图像的环形特征信息,减少冗余特征产生的影响;设计了一种改进的VGG网络架构,利用深度可分离卷积打破输出通道维度与卷积核大小的联系,在不损失网络性能的同时降低了计算量,能够在实际生产中轮毂识别任务在有限的算力情况下实时进行计算;从有效性和实时性两个方面对轮毂识别算法进行评估,且通过Inception V3、SVM、KNN等模型的对比实验,验证了该算法可以实时地对轮毂自适应分类。实验表明: 该方法对轮毂图像的处理精度达到99%以上,单幅图像平均处理时间降低至11.78ms。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	程淑红
	芦嘉鑫
	张典范
	徐南

关键词 ：计量学, 轮毂识别, 环形特征, 图像归一化, 卷积神经网络, 深度可分离卷积

Abstract：Aiming at the mixed-flow production of different types of wheels, a wheel hub identification algorithm of convolutional neural networks based on ring features is proposed. The circular hub in rectangular coordinates is mapped to polar coordinates, normalized to a rectangle in standard form, and the feature information is extracted by rotation to reduce the influence of redundant features. An improved VGG network architecture is designed, which uses depthwise separable convolution to break the relationship between the output channel dimension and the size of the convolution kernel. It reduces the computation without losing the network performance. The hub recognition algorithm is evaluated in terms of effectiveness and real-time performance, and through comparative experiments of models such as Inception V3, SVM, and KNN etc. The experiment shows that the method has a processing accuracy of more than 99%, and the processing time of a single image is reduced to 11.78ms.

Key words： metrology wheel model identification ring features image normalization convolutional neural networks depthwise separable convolution

收稿日期: 2021-01-07 发布日期: 2022-06-30

PACS:

TB96

基金资助:国家自然科学基金(61601400);河北省重点研发计划(20371801D)

作者简介: 程淑红(1978-),女,河北秦皇岛人,燕山大学教授,博士,主要从事计算机视觉、水质检测方面的研究。Email: shhcheng@ysu.edu.cn

引用本文:

程淑红,芦嘉鑫,张典范,徐南. 基于环形特征的卷积神经网络轮毂识别[J]. 计量学报, 2022, 43(6): 729-735.
CHENG Shu-hong,LU Jia-xin,ZHANG Dian-fan,XU Nan. Wheel Hub Identification of Convolutional Neural Networks Based on Ring Features. Acta Metrologica Sinica, 2022, 43(6): 729-735.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2022.06.05 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2022/V43/I6/729

［1］程淑红, 管永来, 张典范. 基于形状匹配及纹理筛选的汽车轮毂型号识别［J］. 仪器仪表学报, 2017, 38(9): 2299-2306.
Cheng S H, Guan Y L, Zhang D F. Wheel model identification based on shape recognition and texture filtering ［J］. Chinese Journal of Scientific Instrument, 2017, 38(9): 2299-2306.
［2］朱焜, 董选普, 王铁林, 等. 铝合金轮毂图像识别分类技术研究［J］. 特种铸造及有色合金, 2017, 37(6): 619-621.
Zhu K, Dong X P, Wang T L, et al. The Research on Recognition and Classification Technology of Aluminum Alloy Wheel Hub ［J］. Special Casting & Nonferrous Alloys, 2017, 37(6): 619-621.
［3］郭智杰, 王明泉, 张俊生, 等. 基于机器视觉的轮毂在线识别分类技术研究［J］. 测试技术学报, 2019, 33(3): 233-237.
Guo Z J, Wang M Q, Zhang J S, et al. The Research on Online Recognition and Classification Technology of Wheel Hub Based on Machine Vision ［J］. Journal of test and measurement technology, 2019, 33(3): 233-237.
［4］张典范, 管永来, 张丽, 等. 基于指数权重局部聚合向量特征的轮毂型号识别［J］. 计量学报, 2019, 40(4): 670-675.
Zhang D F, Guan Y L, Zhang L, et al. Wheel Model Identification Based on Index Weight Vector of Aggragate Locally Descriptor Features ［J］. Acta Metrologica Sinica, 2019, 40(4): 670-675.
［5］Chen G C, Liu Y, Ge Z Q.
K-means Bayes algorithm for imbalanced fault classification and big data application ［J］. Journal of Process Control, 2019, 81:54-64.
［6］Sahari Moghaddam A, Rezazadeh Azar E, Mejias Y, et al. Estimating Stripping of Asphalt Coating Using k-Means Clustering and Machine Learning-Based Classification ［J］. Journal of Computing in Civil Engineering, 2020, 34(1): 04019044.1-04019044.11.
［7］Faragallah O S. Enhancing multispectral imagery spatial resolution using optimized adaptive PCA and high-pass modulation ［J］. International journal of remote sensing, 2018, 39(19-20): 6572-6586.
［8］He F, Zhang L Y. Prediction model of end-point phosphorus content in BOF steelmaking process based on PCA and BP neural network ［J］. Journal of Process Control, 2018, 66: 51-58.
［9］刘岩松, 苗立刚, 刘译彭. 基于环投影特征的汽车轮毂定位与识别［J］. 机床与液压, 2020, 48(14): 73-77.
Liu Y S, Miao L G, Liu Y P. Positioning and Identification of Automobile Wheel Hub Based on Ring Projection Feature ［J］. Machine Tool & Hydraulics, 2020, 48(14): 73-77.
［10］Lane N D, Warden P.
The Deep (Learning) Transformation of Mobile and Embedded Computing ［J］. Computer, 2018, 51(5): 12-16.
［11］Yao J C, Wang J J, Tsang I, et al. Deep Learning From Noisy Image Labels With Quality Embedding ［J］. Journal of LATEX Class Files, 2015, 14(8): 1-12.
［12］程淑红, 张仕军, 赵考鹏. 基于卷积神经网络的生物式水质监测方法［J］. 计量学报, 2019, 40(4): 721-727.
Cheng S H, Zhang S J, Zhao K P. Biological water quality monitoring method based on convolutional neural network ［J］. Acta Metrologica Sinica, 2019, 40(4): 721-727.
［13］Li Z, Teng N, Jin M, et al. Building Efficient CNN Architecture for Offline Handwritten Chinese Character Recognition ［J］. International Journal on Document Analysis & Recognition, 2018, 21(4): 233-240.
［14］Liang F, Shen C, Wu F. An Iterative BP-CNN Architecture for Channel Decoding ［J］. IEEE Journal of Selected Topics in Signal Processing, 2018, 12(1):144-159.
［15］刘庆民, 张蕾, 吴立群, 等. 基于机器视觉的非均匀分布点圆度误差评定［J］. 计量学报, 2016, 37(6): 567-570.
Liu Q M, Zhang L, Wu L Q,et al. Roundness Error Evaluation of Non-uniformly Distributed Data Points Based on Machine Vision ［J］. Acta Metrologica Sinica, 2016, 37(6): 567-570.
［16］Ilhan H O, Sigirci I O, Serbes G, et al. A fully automated hybrid human sperm detection and classification system based on mobile-net and the performance comparison with conventional methods ［J］. Medical & Biological Engineering & Computing, 2020, 58(5): 1047-1068.