结合图像增强和卷积神经网络的小麦不完善粒识别

doi:10.11772/j.issn.1001-9081.2020060864

计算机应用 ›› 2021, Vol. 41 ›› Issue (3): 911-916.DOI: 10.11772/j.issn.1001-9081.2020060864

所属专题：前沿与综合应用

• 前沿与综合应用 • 上一篇

结合图像增强和卷积神经网络的小麦不完善粒识别

贺杰安¹, 吴晓红¹, 何小海¹, 胡建蓉², 卿粼波¹

1. 四川大学电子信息学院, 成都 610065;
2. 中储粮成都储藏研究院有限公司, 成都 610091

收稿日期:2020-06-22 修回日期:2020-10-19 出版日期:2021-03-10 发布日期:2021-01-15
通讯作者: 贺杰安
作者简介:贺杰安(1996-),男,四川泸州人,硕士研究生,主要研究方向:图像处理、模式识别、人工智能;吴晓红(1970-),女,四川遂宁人,副教授,博士,主要研究方向:图像处理、模式识别、电子与通信系统;何小海(1964-),四川绵阳人,教授,博士,主要研究方向:图像处理、模式识别、图像通信、机器视觉、智能系统;胡建蓉(1984-),女,四川成都人,实验师,主要研究方向:粮油检测;卿粼波(1982-),男,四川简阳人,副教授,博士,主要研究方向:图像处理、模式识别、视频通信。
基金资助:
四川省科技计划项目（2018HH0143）；四川省教育厅项目（18ZB0355）。

Imperfect wheat kernel recognition combined with image enhancement and conventional neural network

HE Jiean¹, WU Xiaohong¹, HE Xiaohai¹, HU Jianrong², QIN Linbo¹

1. College of Electronics and Information Engineering, Sichuan University, Chengdu Sichuan 610065, China;
2. Sinograin Chengdu Reserves Institute Company Limited, Chengdu Sichuan 610091, China

Received:2020-06-22 Revised:2020-10-19 Online:2021-03-10 Published:2021-01-15
Supported by:
This work is partially supported by the Science and Technology Program of Sichuan Province (2018HH0143), the Sichuan Provincial Department of Education Project (18ZB0355).

摘要/Abstract

摘要： 针对实际应用场景下，小麦籽粒图像背景单一以及小麦不完善粒的不完善特征大多是局部特征而大部分图像特征与正常粒无异的特点，提出一种基于细节的图像增强（IE）的小麦不完善粒识别方法。首先，使用交替最小化算法约束原图在水平方向和竖直方向的L0范数来平滑原图作为基础图层，并用原图减去基础图层得到图像的细节层；然后，突出细节层后将其与基础图层叠加以增强图像；最后，将增强后的图像作为卷积神经网络（CNN）的输入，使用加入了批正则化（BN）层的CNN对图像进行识别。分别以经典分类网络LeNet-5、ResNet-34、VGG-16和在其中添加BN层的这些网络作为分类网络，增强前后的图像作为输入来进行分类实验，并以测试集准确率评估性能。实验结果表明，三个经典分类网络均在添加了BN层后而使用相同输入时的测试集准确率提高了5个百分点，在使用细节增强后的图像作为输入时三个网络的测试集准确率提高了1个百分点，以上二者联合使用时三个网络均获得超过7个百分点的测试集准确率提升。

关键词: 小麦不完善粒识别, 卷积神经网络, L0平滑, 图像增强, 批正则化, 分类

Abstract: In the practical application scenario, the wheat kernel image background is single, and the imperfect characteristics of wheat imperfect grains are mostly local features while most of the image features are not different from normal grains. In order to solve the problems, an imperfect wheat kernel recognition method based on detail Image Enhancement (IE) was proposed. Firstly, the alternate minimization algorithm was used to constrain the L0 norms of the original image in the horizontal and vertical directions to smooth the original image as the base layer, and the original image was subtracted from the base layer to obtain the detail layer of the image. Then, the detail layer was delighted and superimposed with the base layer to enhance the image. Finally, the enhanced image was used as the input of the Convolutional Neural Network (CNN), and the CNN with Batch Normalization (BN) layer was used for recognition of the image. The classic classification networks LeNet-5, ResNet-34, VGG-16 and these networks with the BN layer were used as classification networks, and the images before and after enhancement were used as input to carry out classification experiments, and the accuracy of the test set was used to evaluate the performance. Experimental results show that by adding the BN layer and using the same input, all three classic classification networks have the accuracy of the test set increased by 5 percentage points, and when using the images with enhanced detail as input, the three networks have the accuracy of the test set increased by 1 percentage point, and when the above two are used together, all the three networks obtain the accuracy of the test set improved by more than 7 percentage points.

Key words: imperfect wheat kernel recognition, Conventional Neural Network (CNN), L0 smoothing, image enhancement, Batch Normalization (BN), classification

中图分类号:

TP751

贺杰安, 吴晓红, 何小海, 胡建蓉, 卿粼波. 结合图像增强和卷积神经网络的小麦不完善粒识别[J]. 计算机应用, 2021, 41(3): 911-916.

HE Jiean, WU Xiaohong, HE Xiaohai, HU Jianrong, QIN Linbo. Imperfect wheat kernel recognition combined with image enhancement and conventional neural network[J]. Journal of Computer Applications, 2021, 41(3): 911-916.

参考文献

[1] ZAYAS I, POMERANZ, LAI F S Y. Discrimination between Arthur and Arkan wheats by image-analysis[J]. Cereal Chemistry, 1985,62(6):478-480.
[2] THOMSON W H,POMERANZ Y. Classification of wheat kernels using three-dimensional image-analysis[J]. Cereal Chemistry, 1991,68(4):357-361.
[3] MAJUMDAR S,JAYAS D S. Classification of bulk samples of cereal grains using machine vision[J]. Journal of Agricultural Engineering Research,1999,73(1):35-47.
[4] NEETHIRAJAN S,JAYAS D S,WHITE N D G. Detection of sprouted wheat kernels using soft X-ray image analysis[J]. Journal of Food Engineering,2007,81(3):509-513.
[5] 陈丰农. 基于机器视觉的小麦并肩杂与不完善粒动态实时检测研究[D]. 杭州:浙江大学,2012:51-89.(CHEN F N. Real-time detection of kernel-like impurity and unsound kernel in wheat using machine vision[D]. Hangzhou:Zhejiang University, 2012:51-89.)
[6] 曹婷翠, 何小海, 董德良, 等. 基于CNN深度模型的小麦不完善粒识别[J]. 现代计算机(专业版),2017(36):9-14.(CAO T C, HE X H,DONG D L,et al. Identification of unsound kernels in wheat based on CNN deep model[J]. Modern Computer,2017(36):9-14.)
[7] 陈文根. 基于深度学习的小麦图谱特征技术研究[D]. 郑州:河南工业大学,2018:47-55.(CHEN W G. Wheat map features research based on deep learning[D]. Zhengzhou:Henan University of Technology,2018:47-55.)
[8] 张博. 基于深度学习的小麦外观品质机器视觉检测研究[D]. 杨凌:西北农林科技大学,2019:21-47.(ZHANG B. Machine vision inspection of wheat appearance quality based on deep learning[D]. Yangling:Northwest A&F University,2019:21-47.)
[9] 祝诗平, 卓佳鑫, 黄华, 等. 基于CNN的小麦籽粒完整性图像检测系统[J/OL]. 农业机械学报.[2020-03-07]. http://kns.cnki.net/kcms/detail/11.1964.S.20200304.1947.012.html. (ZHU S P,ZHUO J X,HUANG H,et al. Wheat grain integrity image detection system based on CNN[J/OL]. Transactions of The Chinese Society of Agricultural Machinery.[2020-03-07]. http://kns.cnki.net/kcms/detail/11.1964.S.20200304.1947.012.html.)
[10] XU L,LU C,XU Y,et al. Image smoothing via L₀ gradient minimization[J]. ACM Transactions on Graphics,2011,30(6):No. 174.
[11] WIESLER S, RICHARD A, SCHLÜTER R, et al. Meannormalized stochastic gradient for large-scale deep learning[C]//Proceedings of the 2014 IEEE International Conference on Acoustics,Speech and Signal Processing. Piscataway:IEEE, 2014:180-184.
[12] LOFFE S,SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning. New York:JMLR. org,2015:448-456.
[13] 王迪, 石嵩, 许勇, 等. 深度神经网络的归一化算法探究[C]//中国计算机学会第二十二届计算机工程与工艺年会暨第八届微处理器技术论坛论文集. 长沙:中南大学出版社,2018:170-179.(WANG D,SHI S,XU Y,et al. Research on normalization algorithm of deep neural network[C]//Proceedings of the CCF 22nd Annual Conference of Computer Engineering and Technology/the 8th Microprocessor Technology Forum. Changsha:Central South University Press,2018:170-179.)
[14] 刘爽, 谭鑫, 刘成玉, 等. 高光谱数据处理算法的小麦赤霉病籽粒识别[J]. 光谱学与光谱分析,2019,39(11):3540-3546. (LIU S,TAN X,LIU C Y,et al. Recognition of fusarium head blight wheat grain based on hyperspectral data processing algorithm[J]. Spectroscopy and Spectral Analysis,2019,39(11):3540-3546.)
[15] 刘欢, 王雅倩, 王晓明, 等. 基于近红外高光谱成像技术的小麦不完善粒检测方法研究[J]. 光谱学与光谱分析,2019,39(1):223-229.(LIU H,WANG Y Q,WANG X M,et al. Study on detection method of wheat unsound kernel based on nearinfrared hyperspectral imaging technology[J]. Spectroscopy and Spectral Analysis,2019,39(1):223-229.)
[16] 关二旗, 崔贵金, 卞科, 等. 基于近红外光谱特征的赤霉病小麦籽粒SIMCA识别模型构建研究[J]. 中国粮油学报,2016,31(11):124-129.(GUAN E Q,CUI G J,BIAN K,et al. SIMCA identification model establishment of gibberellic disease wheat grain based on near infrared spectrum characteristics[J]. Journal of the Chinese Cereals and Oils Association,2016,31(11):124-129.)
[17] 于重重, 周兰, 王鑫, 等. 基于CNN神经网络的小麦不完善粒高光谱检测[J]. 食品科学,2017,38(24):283-287.(YU C C, ZHOU L,WANG X,et al. Hyperspectral detection of unsound kernels of wheat based on convolutional neural network[J]. Food Science,2017,38(24):283-287.)
[18] 张红涛, 毛罕平, 剧森, 等. 基于胚部区域特征的麦粒姿态自动识别[J]. 农业工程学报,2014,30(14):163-169.(ZHANG H T,MAO H P,JU S,et al. Automatic posture recognition of wheat kernels based on germ features[J]. Transactions of the Chinese Society of Agricultural Engineering,2014,30(14):163-169.)
[19] 张航, 姚传安, 蒋梦梦, 等. 基于高光谱图像技术的小麦种子分类识别研究[J]. 麦类作物学报,2019,39(1):96-104. (ZHANG H,YAO C A,JIANG M M,et al. Research on wheat seed classification and recognition based on hyperspectral imaging[J]. Journal of Triticeae Crops,2019,39(1):96-104.)
[20] 陈赛赛. 小麦质量指标机器视觉技术研究[D]. 郑州:河南工业大学,2014:44-49.(CHEN S S. The research to discriminate wheat quality indicators using machine vision technology[D]. Zhengzhou:Henan University of Technology,2014:44-49.)
[21] GONZALES R C,WOODS R E. Digital Image Processing[M]. London:Pearson,2009:176-182.
[22] 张静, 金光日. 小波框架中改进的l₀平滑算法的图像复原[J]. 计算机应用,2016,36(S2):149-151, 196.(ZHANG J,JIN G R. Image restoration study based on smoothed l₀ algorithm in wavelet frame[J]. Journal of Computer Applications,2016,36(S2):149-151,196.)
[23] LIU Y,MA X,LI X,et al. Two-stage image smoothing based on edge-patch histogram equalisation and patch decomposition[J]. IET Image Processing,2020,14(6):1132-1140.

结合图像增强和卷积神经网络的小麦不完善粒识别

Imperfect wheat kernel recognition combined with image enhancement and conventional neural network

PDF

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]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[2]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[3]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[4]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[5]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[6]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[7]	毛铭泽, 曹芮浩, 闫春钢. 基于权值多样性的半监督分类算法[J]. 计算机应用, 2021, 41(9): 2473-2480.
[8]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[9]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[10]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[11]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[12]	李蒙蒙, 秦伟, 刘艺, 刁兴春. 结合头脑风暴优化的混合蚁群优化算法[J]. 计算机应用, 2021, 41(8): 2412-2417.
[13]	朱亮, 徐华, 崔鑫. 基于基分类器系数和多样性的改进AdaBoost算法[J]. 计算机应用, 2021, 41(8): 2225-2231.
[14]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[15]	胡天杰, 胡文军, 王士同. 分布熵惩罚的支持向量数据描述[J]. 计算机应用, 2021, 41(8): 2212-2218.