基于卷积神经网络干制哈密大枣纹理分级

doi:10.6048/j.issn.1001-4330.2018.12.008

新疆农业科学 ›› 2018, Vol. 55 ›› Issue (12): 2220-2227.DOI: 10.6048/j.issn.1001-4330.2018.12.008

基于卷积神经网络干制哈密大枣纹理分级

罗秀芝¹,马本学^{1, 2},李小霞¹,胡洋洋¹,王文霞¹,雷声渊¹

1.石河子大学机械电气工程学院,新疆石河子 832000;
2.农业部西北农业装备重点实验室,新疆石河子 83200

收稿日期:2018-10-09 发布日期:2019-04-18
通信作者: 马本学(1970-),男,山东人,教授,博士生导师,研究方向为图像光谱信息采集与处理技术、智能检测技术,(E-mail)mbx_shz@163.com
作者简介:罗秀芝(1992-),女,湖南衡阳人,硕士研究生,研究方向为农产品检测,(E-mail)296513547@qq.com
基金资助:
国家自然科学基金项目“基于近红外光谱与机器视觉信息融合的干制哈密大枣多品质无损检测机理研究”(61763043)

Research on the Texture Classification of Dried Hami Jujube Based on Convolutional Neural Network

LUO Xiu-zhi¹, MA Ben-xue^1,2, LI Xiao-xia¹, HU Yang-yang¹, WANG Wen-xia¹, LEI Sheng-yuan¹

1.College of Mechanical and Electrical Engineering, Shihezi University, Shihezi Xinjiang 832000, China; 2. Key Laborqtory of Northwest Agricultural Equipment, Ministry of Agriculure, P. R. China, Shihezi Xinjiang 832000, China

Received:2018-10-09 Published:2019-04-18
Correspondence author: MA Ben-xue(1970-),male,master's degree, professor, doctoral supervisor. Research field: Image spectral information collection and processing technology, intelligent detection technology, (E-mail)mbx_shz@163.com
Supported by:
The National Natural Science Foundation of China “ Study on the comprehensive quality evaluation model of Lycium barbarum in Ningxia based on the relationship between water and quality ”（41661108）；Innovation Program of Regional Cooperation of Xinjiang(Science and Technology Supporting Xinjiang Proguam) “Introduction and application of effective water and fertilizer management technology of Lycium barbarum in southern Xinjiang ”（2016E02025）; Science and Technology Innovation Fund Project in Ningxia Academy of Agriculture and Forestry Sciences (NKYJ-13-25) “Research on the effect of water deficit on the growth and quality of Lycium barbarum”

摘要/Abstract

摘要： 【目的】研究一种基于卷积神经网络干制哈密大枣纹理分级的方法。利用卷积神经网络解决干制哈密大枣的纹理分类问题。【方法】将大小统一的彩色图片输入网络,卷积核自动提取其纹理特征,进行分类。【结果】分类准确率达到了97.7%。【结论】与常用的灰度共生矩阵提取干制哈密大枣纹理特征(最大概率,相关性,对比度、能量、同质性和熵),再用BP神经网络和支持向量机(SVM)分类准确率相比的方法,避免了复杂纹理提取和图片预处理的过程,在测试时间相近的情况下识别率更高。

关键词: 卷积神经网络; 干制哈密大枣; 纹理特征; 分级

Abstract: 【Objective】 Texture detection and grading of dried Hami jujube is a difficult problem to realize the automatic classification of the dried date appearance quality, therefore, a method of texture classification of Hami jujube based on convolutional neural network was proposed.【Method】In this method, color images of uniform size were input into the network, and the convolutional kernel automatically extracted its texture features, and then classified them.【Result】Experimental results showed that the CNN could solve the problem of texture classification of Hami dried jujube, and the accuracy rate of the classification was up to 97.7%.【Conclusion】Compared with the commonly used gray level co-occurrence matrix (GLCM) to extract the texture characteristics (maximum probability, correlation, contrast, energy, homogeneity and entropy) of Hami dried jujube, and then compared with the accuracy classified by BP neural network (BP) and aupport vector machines (SVM), this method avoided complicated texture extraction and image preprocessing, and the recognition rate was higher when the test time was similar.

Key words: convolutional neural network; dried Hami jujube; texture feature; classification

中图分类号:

S665.1
S126

罗秀芝, 马本学, 李小霞, 胡洋洋, 王文霞, 雷声渊. 基于卷积神经网络干制哈密大枣纹理分级[J]. 新疆农业科学, 2018, 55(12): 2220-2227.

LUO Xiu-zhi, MA Ben-xue, LI Xiao-xia, HU Yang-yang, WANG Wen-xia, LEI Sheng-yuan. Research on the Texture Classification of Dried Hami Jujube Based on Convolutional Neural Network[J]. Xinjiang Agricultural Sciences, 2018, 55(12): 2220-2227.

参考文献

[1] 李功燕,任亦立,马丽艳.基于梯度分布不均匀性的干瘪红枣识别[J].农业机械学报,2016,47(11):213-218.
LI Gong-yan, REN Yi-li, MA Li-yan. (2016). Identification of Dried Jujube Based on Gradient Distribution Inhomogeneity [J]. Journal of Agricultural Machinery, 47(11):213-218. (in Chinese)
[2]张萌,许敏.红枣表面缺陷快速检测方法研究[J].江苏农业科学,2015,43(7):331-334.
ZHANG Meng, XU Min. (2015). Study on Rapid Detection Method of Surface Defects in Jujube [J]. Jiangsu Agricultural Sciences, 43(7):331-334.(in Chinese)
[3]王松磊,刘民法,何建国,等.红枣自动快速无损检测分级研究[J].农业机械学报, 2014,45(9):79-83, 95.
WANG Song-lei, LIU Min-fa, HE Jian-guo, et al.(2014).Automatic and non-destructive testing and classification of jujube[J]. Journal of Agricultural Machinery, 45(9):79-83, 95. (in Chinese)
[4]王斌,薛建新,张淑娟.基于高光谱成像技术的腐烂、病害梨枣检测[J].农业机械学报,2013,44(S1):205-209.
WANG Bin, XUE Jian-xin, ZHANG Shu-juan. (2013). Detection of decay and disease pear dates based on hyperspectral imaging technology [J]. Journal of Agricultural Machinery, 44(S1):205-209. (in Chinese)
[5]康宁波,强锋,吴龙国,等.基于电磁式同步执行机构的鲜枣分级机设计与试验[J].农业工程学报,2017,33(7):254-260.
KANG Ning-bo, QIANG-Feng, WU Long-guo, et al. (2017). Design and experiment of fresh jujube classifier based on electromagnetic synchronous actuator [J]. Journal of Agricultural Machinery, 33(7):254-260.(in Chinese)
[6]蒋伟.基于OpenCV的红枣纹理检测研究[D].新疆石河子:石河子大学,2017:34-43.
JIANG-Wei. (2017). Research on red jujube texture detection based on Open CV [D]. Master Dissertation. Shihezi University, Shihezi.(in Chinese)
[7]柴春花,黄智英,李忠,等.红枣纹理分级方法的研究[J].中国农机化学报,2016,37(3):201-204.
CHAI Chun-hua, HUANG Zhi-ying, LI-Zhong, et al. (2016). Study on Grading Method of Jujube Texture [J]. Chinese Journal of Agricultural Mechanization, 37(3):201-204. (in Chinese)
[8]周军,郭俊先,张静,等.基于机器视觉的核桃仁动态分级研究[J].新疆农业科学,2018,55(5):901-911.
ZHOU Jun, GUO Jun-xian, ZHANG Jing, et al. (2018). Dynamic grading of walnut kernel based on machine vision [J]. Xinjiang Agricultural Science, 55(5):901-911.(in Chinese)
[9] Wachinger, C. , Reuter, M. , & Klein, T. . (2017). Deepnat: deep convolutional neural network for segmenting neuroanatomy. NeuroImage, 170: 434-445. doi.org/10.1016/j.neuroimage.2017.02.035
[10]袁文浩,孙文珠,夏斌,等.利用深度卷积神经网络提高未知噪声下的语音增强性能[J].自动化学报,2018,44(4):751-759.
YUAN Wen-hao, SUN Wen-zhu, XIA Bin, et al. (2017). Improving the speech enhancement performance under unknown noise by using deep convolutional neural network [J]. Journal of Automation, 44(4):751-759. (in Chinese)
[11]白琮,黄玲,陈佳楠,等.面向大规模图像分类的深度卷积神经网络优化[J].软件学报,2018,29(4):1 029-1 038.
BAI Cong, HUANG-Ling,CHEN Jia-nan,et al. (2018).Deep Convolutional Neural Network Optimization for Large Scale Image Classification [J]. Journal of Software, 29(4), 29(4):1,029-1,038. (in Chinese)
[12] Trevor Hastie, Robert Tibshirani, J Friedmman, The elements of statistical learning [M]. New York: Springer, 2001:45-65.
Hastie, T. J. . (2015). The elements of statistical learning.
[13] Krizhevsky, A., Sutskever, I., & Hinton, G. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25(2). DOI: 10.1145/3065386
[14]MITCHELL T M.机器学习[M].曾华军,张银奎,译.北京: 机械工业出版社,2012:56-59.
MITCHELL T M. (2012). Machine learning translated by ZENG Hua-jun, ZHANG Yin-kui[M]. Beijing: Mechanical Industry Press: 56-59. (in Chinese)
[15]Behbahan Navid Samimi, Mousavinasab Zohreh. (2012). Presenting a method based on back-propagation neural network for recognition of handwritten digits.International Journal of Management, IT and Engineering, 2(12): 63-73.
[16] Jia, W., Zhao, D., & Ding, L. (2016). An optimized rbf neural network algorithm based on partial least squares and genetic algorithm for classification of small sample. Applied Soft Computing, (48): 373-384.

基于卷积神经网络干制哈密大枣纹理分级

Research on the Texture Classification of Dried Hami Jujube Based on Convolutional Neural Network

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	冯倩, 何齐, 李雪, 易鸳鸯, 孙建, 朱静, 顾美英, 谭慧林, 张志东. 阿克苏野生牛肝菌多糖提取优化及不同组分抗氧化活性分析[J]. 新疆农业科学, 2023, 60(7): 1813-1820.
[2]	王迎超, 张婧婧, 达新民, 耿新雪. 基于K-means与KNN的多特征苹果在线分级[J]. 新疆农业科学, 2023, 60(3): 643-650.
[3]	户金鸽, 白世践, 陈光, 赵荣华, 蔡军社. 不同级别无核白葡萄果实外观与品质差异特征及分级[J]. 新疆农业科学, 2022, 59(3): 567-577.
[4]	杨波, 郭春苗, 木巴热克·阿尤普, 龚鹏. 扁桃种质资源坚果数量性状遗传多样性和概率分级[J]. 新疆农业科学, 2021, 58(7): 1297-1305.
[5]	李飞, 李彩红, 赵瑞元, 梅正鼎, 郭莉莉, 刘冰蕾, 何叔军, 张志刚. 湖南省油后直播棉花测土配方施肥指标体系[J]. 新疆农业科学, 2020, 57(11): 1961-1970.
[6]	雷声渊, 马本学, 王文霞, 罗秀芝, 李玉洁, 戴建国. 基于微调卷积神经网络迁移学习模式下被害棉叶图像的识别[J]. 新疆农业科学, 2019, 56(7): 1294-1302.
[7]	周军, 郭俊先, 张静, 姜彦武, 艾力·哈斯木, 蔡建. 基于机器视觉的核桃仁动态分级研究[J]. 新疆农业科学, 2018, 55(5): 901-911.
[8]	郭政;史建新;周军;蔡建;刘航. 机器视觉在线检测核桃大小软件设计[J]. , 2017, 54(3): 538-545.
[9]	沈从举;郑炫;贾首星;史建新;张景;周艳;代亚猛. 6FGH-800型滚杠式红枣分级机研制[J]. , 2015, 52(3): 535-0.
[10]	李俊伟;郭俊先;胡光辉;刘军;虞飞宇. 基于机器视觉技术的单粒葡萄质量与果径预测分级研究[J]. , 2014, 51(10): 1862-1868.
[11]	郭俊先;李俊伟;胡光辉;刘军;虞飞宇. 新疆冰糖心红富士苹果RGB图像多指标分析[J]. , 2013, 50(3): 509-517.
[12]	周勃;马雪琴;陈署晃;谭新霞;王新勇. 吉尔吉斯斯坦土壤的微量元素评价[J]. , 2013, 50(11): 2152-2156.
[13]	刘向东;梁勤安;高连兴;王学农;刘小龙;李胜. 双螺旋等径不等螺距分级装置的设计及运动仿真[J]. , 2011, 48(11): 2083-2088.
[14]	何天明;黎秀丽;吴玉霞;张峰;李世强;李疆. 库尔勒香梨在疆内市场的商品分级与价格形成调查[J]. , 2010, 47(3): 461-465.
[15]	高文彬;江东;杨小唤. 伊犁河谷土地利用结构与高程的相关关系研究[J]. , 2008, 45(z3): 44-47.