基于图像处理技术和神经网络实现机采茶分级

茶叶科学 ›› 2017, Vol. 37 ›› Issue (2): 182-190.

基于图像处理技术和神经网络实现机采茶分级

吴正敏, 曹成茂^*, 谢承健, 吴佳胜, 胡汪洋, 汪天宇

安徽农业大学工学院,安徽合肥 230036

收稿日期:2016-12-30 修回日期:2017-02-26 出版日期:2017-04-15 发布日期:2019-08-22
通讯作者: *caochengmao@sina.com
作者简介:吴正敏,女,硕士,主要从事智能检测与控制技术研究。
基金资助:
科技部科技型中小企业技术创新基金项目（14C26213401694）

Grading of Machine Picked Tea Based on Image Processing Technology and Neural Network

WU Zhengmin, CAO Chengmao^*, XIE Chengjian, WU Jiasheng, HU Wangyang, WANG Tianyu

College of Engineering, Anhui Agricultural University, Hefei 230036, China

Received:2016-12-30 Revised:2017-02-26 Online:2017-04-15 Published:2019-08-22

摘要/Abstract

摘要： 为解决名优绿茶采摘环节的瓶颈问题,提出对机采大宗绿茶进行分级的思路。现有绿茶机采设备采摘的鲜叶一般只能制作普通的大宗绿茶,鲜叶存在混杂、破碎率高和老梗叶等问题,本文基于Labview vision、图像处理技术和神经网络算法分析机采绿茶成品的凸包面积、凸包周长、长轴长度、短轴长度等形态特征并对样本进行分类,实现从机采大宗绿茶中分选出名优绿茶。其中样本的形态特征采用工业CCD摄像头获取;用户界面用Labview自定义开发设计,数据交互方便,开发周期短。茶叶样本试验结果表明：该方案机采绿茶成品的分级正确率可以稳定在90%以上。本研究为进一步研究机采茶分级设备提供了良好的理论基础。

关键词: 机采绿茶, 分级, 神经网络, 图像处理技术

Abstract: To solve the picking problem of famous green tea, a new technology was proposed to classify machine picked tea in this paper. Fresh tea leaves plucked by machine are often mixed, with tea stalks and have a high broken rate and thereby only suitable for making general green tea. The convex hull area, convex hull perimeter, long axial length, short axial length and other morphological features of machine plucked tea leaves were analyzed by Labview vision, image processing technology and neural network to screen high quality tea. Industrial CCD camera with appropriate optical system was used to collect object classification features. User interface was developed by Labview, which can realize the data interaction, convenient operation, short development cycle and meet different users’ requirements. Finally, sample test showed that the correct rate of tea classification could reach about 90%, which provides a good theoretical basis for further research of tea grading equipment.

Key words: machine plucked tea, grading, neural network, image processing technology

中图分类号:

TS272.3
S23

吴正敏, 曹成茂, 谢承健, 吴佳胜, 胡汪洋, 汪天宇. 基于图像处理技术和神经网络实现机采茶分级[J]. 茶叶科学, 2017, 37(2): 182-190.

WU Zhengmin, CAO Chengmao, XIE Chengjian, WU Jiasheng, HU Wangyang, WANG Tianyu. Grading of Machine Picked Tea Based on Image Processing Technology and Neural Network[J]. Journal of Tea Science, 2017, 37(2): 182-190.

参考文献 15

[1]	唐小林, 李文萃, 范起业. 机采茶鲜叶分类分级技术及相关设备研究进展[J]. 中国茶叶加工, 2015(2): 5-8.
[2]	杨娟, 李中林, 袁林颖, 等. 机采茶鲜叶分级技术初步研究[J]. 中国茶叶加工, 2015(2): 41-45.
[3]	张兰兰, 董迹芬, 唐萌, 等. 名优茶机采鲜叶分级技术研究[J]. 浙江大学学报: 农业与生命科学版, 2012, 38(5): 593-598.
[4]	李明珠, 倪超, 张晓, 等. 基于彩色线阵CCD的茶叶分选识别算法研究[J]. 中国农机化学报, 2015, 36(4): 124-129.
[5]	Zhe T, Yuancheng S, Meng J.A local binary pattern based texture descriptors for classification of tea leaves[J]. Neurocomputing, 2015, 168(30): 1011-1023.
[6]	Shahabi M, Rafiee S, Mohtasebi SS, et al.Image analysis and green tea color change kinetics during thin-layer drying[J]. Food Science and Technology International, 2014, 20(6): 465-476.
[7]	Gagandeep SG, Amod K, Ravinder A.Monitoring and grading of tea by computer vision[J]. Journal of Food Engineering, 2011(106): 13-19.
[8]	Laddi A, Sharma S, Kumar A,et al.Classification of tea grains based upon image texture feature analysis under different illumination conditions[J]. Journal of Food Engineering, 2013, 115(2): 226-231.
[9]	张春燕, 陈笋, 张俊峰. 基于最小风险贝叶斯分类器茶叶茶梗分类[J]. 计算机工程与应用, 2012, 48(28): 187-192.
[10]	常春, 陈怡群, 肖宏儒, 等. 基于神经网络图像分析的智能鲜茶叶分选机[J]. 中国农机化学报, 2013, 34(1): 137-141.
[11]	赵吉文, 高尚, 魏正翠, 等. 基于FPGA的西瓜子机器视觉色选系统[J]. 农业机械学报, 2011, 42(8): 173-177.
[12]	郑华军, 张宪, 乔欣. 蚁群聚类分析算法在茶叶等级分类识别中的应用[J]. 轻工机械, 2011, 25(9): 91-93.
[13]	施健, 何建国, 张冬, 等. 基于计算机视觉的鲜枣大小分级系统研究[J]. 食品与机械, 2013, 29(5): 134-137.
[14]	孔彦龙, 高晓阳, 李红玲, 等. 基于机器视觉的马铃薯质量和形状分选方法[J]. 农业工程学报, 2012, 28(17): 143-148.
[15]	Kurtulmus F, Alibas I, Kavdir I.Classification of pepper seeds using machine vision based on neural network[J]. Int J Agric and Biol Eng, 2016, 9(1): 51-62.