基于卷积神经网络的多尺度葡萄图像识别方法

doi:10.11772/j.issn.1001-9081.2019040594

计算机应用 ›› 2019, Vol. 39 ›› Issue (10): 2930-2936.DOI: 10.11772/j.issn.1001-9081.2019040594

基于卷积神经网络的多尺度葡萄图像识别方法

邱津怡^1,2, 罗俊^1,2, 李秀³, 贾伟¹, 倪福川^1,2, 冯慧¹

1. 华中农业大学信息学院, 武汉 430070;
2. 湖北省农业大数据工程技术研究中心, 武汉 430070;
3. 华中农业大学工学院, 武汉 430070

收稿日期:2019-04-10 修回日期:2019-06-22 出版日期:2019-10-10 发布日期:2019-08-21
通讯作者: 罗俊
作者简介:邱津怡(1995-),女,天津人,硕士研究生,CCF会员,主要研究方向:计算机视觉、图像处理;罗俊(1981-),男,湖北武汉人,副教授,博士,CCF会员,主要研究方向:机器学习、大数据;李秀(1995-),女,山东济南人,硕士研究生,CCF会员,主要研究方向:计算机视觉、图像处理;贾伟(1994-),男,四川德阳人,硕士研究生,主要研究方向:计算机视觉、深度学习;倪福川(1974-),男,湖北黄冈人,讲师,博士,主要研究方向:机器学习、大数据;冯慧(1987-),女,湖北浠水人,讲师,博士,主要研究方向:计算机视觉、植物表型检测。
基金资助:
国家自然科学基金资助项目（21800305）；国家重点研发计划项目（2018YFC1604000）；中央高校基本科研业务费专项资金资助项目（2662017PY059）。

Multi-scale grape image recognition method based on convolutional neural network

QIU Jinyi^1,2, LUO Jun^1,2, LI Xiu³, JIA Wei¹, NI Fuchuan^1,2, FENG Hui¹

1. College of Informatics, Huazhong Agricultural University, Wuhan Hubei 430070, China;
2. Hubei Engineering Technology Research Center of Agricultural Big Data, Wuhan Hubei 430070;
3. College of Engineering, Huazhong Agricultural University, Wuhan Hubei 430070, China

Received:2019-04-10 Revised:2019-06-22 Online:2019-10-10 Published:2019-08-21
Supported by:
This work is partially supported by the National Natural Science Foundation of China (21800305), the National Key R&D Program of China (2018YFC1604000), the Fundamental Research Funds for the Central Universities (2662017PY059).

摘要/Abstract

摘要： 葡萄品种质量检测需要识别多类别的葡萄，而葡萄图片中存在多种景深变化、多串等多种场景，单一预处理方法存在局限导致葡萄识别的效果不佳。实验的研究对象是大棚中采集的15个类别的自然场景葡萄图像，并建立相应图像数据集Vitis-15。针对葡萄图像中同一类别的差异较大而不同类别的差异较小的问题，提出一种基于卷积神经网络（CNN）的多尺度葡萄图像识别方法。首先，对Vitis-15数据集中的数据通过三种方法进行预处理：旋转图像的数据扩增方法、中心裁剪的多尺度图像方法以及前两种方法的数据融合方法；然后，采用迁移学习方法和卷积神经网络方法来进行分类识别，迁移学习选取ImageNet上预训练的Inception V3网络模型，卷积神经网络采用AlexNet、ResNet、Inception V3这三类模型；最后，提出适合Vitis-15的多尺度图像数据融合的分类模型MS-EAlexNet。实验结果表明，在同样的学习率和同样的测试集上，数据融合方法在MS-EAlexNet上的测试准确率达到了99.92%，相较扩增和多尺度图像方法提升了近1个百分点，并且所提方法在分类小样本数据集上具有较高的效率。

关键词: 图像识别, 自然场景, 迁移学习, 卷积神经网络, 多尺度图像, 数据融合

Abstract: Grape quality inspection needs the identification of multiple categories of grapes, and there are many scenes such as depth of field changes and multiple strings in the grape images. Grape recognition is ineffective due to the limitations of single pretreatment method. The research objects were 15 kinds of natural scene grape images collected in the greenhouse, and the corresponding image dataset Vitis-15 was established. Aiming at the large intra-class differences and small inter-class of differences grape images, a multi-scale grape image recognition method based on Convolutional Neural Network (CNN) was proposed. Firstly, the data in Vitis-15 dataset were pre-processed by three methods, including the image rotating based data augmentation method, central cropping based multi-scale image method and data fusion method of the above two. Then, transfer learning method and convolution neural network method were adopted to realiize the classification and recognition. The Inception V3 network model pre-trained on ImageNet was selected for transfer learning, and three types of models-AlexNet, ResNet and Inception V3 were selected for convolution neural network. The multi-scale image data fusion classification model MS-EAlexNet was proposed, which was suitable for Vitis-15. Experimental results show that with the same learning rate on the same test dataset, compared with the augmentation and multi-scale image method, the data fusion method improves nearly 1% testing accuracy on MS-EAlexNet model with 99.92% accuracy, meanwhile the proposed method has higher efficiency in classifying small sample datasets.

Key words: image recognition, natural scene, transfer learning, Convolutional Neural Network (CNN), multi-scale image, data fusion

中图分类号:

TP183

邱津怡, 罗俊, 李秀, 贾伟, 倪福川, 冯慧. 基于卷积神经网络的多尺度葡萄图像识别方法[J]. 计算机应用, 2019, 39(10): 2930-2936.

QIU Jinyi, LUO Jun, LI Xiu, JIA Wei, NI Fuchuan, FENG Hui. Multi-scale grape image recognition method based on convolutional neural network[J]. Journal of Computer Applications, 2019, 39(10): 2930-2936.

参考文献

[1] 晁无疾. 调整提高转型升级促进我国葡萄产业稳步发展[J]. 中国果菜, 2015(9):12-14. (CHAO W J. Adjustment, improvement, transformation and upgrading to promote the steady development of China's grape industry[J]. China Fruit Vegetable, 2015(9):12-14.)
[2] ZHAO B, FENG J, WU X, et al. A Survey on deep learning-based fine-grained object classification and semantic segmentation[J]. International Journal of Automation and Computing, 2017, 14(2):119-135.
[3] LUO L, TANG Y, ZOU X, et al. Vision-based extraction of spatial information in grape clusters for harvesting robots[J]. Biosystems Engineering, 2016, 151:90-104.
[4] FAN J, GAO Y, LUO H. Multi-level annotation of natural scenes using dominant image components and semantic concepts[C]//Proceedings of the 12th Annual ACM International Conference on Multimedia. New York:ACM, 2004:540-547.
[5] NIXON M S, AGUADO A S. 特征提取与图像处理[M]. 李实英, 杨高波, 译.北京:电子工业出版社, 2010:147-289. (NIXON M S, AGUADO A S. Feature Extraction and Image Processing[M]. LI S Y, YANG G B, translated. Beijing:Publishing House of Electronics Industry, 2010:147-289.)
[6] HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7):1527-1554.
[7] YU C, WANG J, PENG C, et al. Learning a discriminative feature network for semantic segmentation[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:1857-1866.
[8] SCHUSTER M, PALIWAL K K. Bidirectional recurrent neural networks[J]. IEEE Transactions on Signal Processing, 1997, 45(11):2673-2681.
[9] CARNEIRO G, VASCONCELOS N. Formulating semantic image annotation as a supervised learning problem[C]//Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2005:163-168.
[10] LeCUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[11] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. La Jolla, CA:Neural Information Processing Systems Foundation, 2012:1097-1105.
[12] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2019-02-10]. https://arxiv.org/pdf/1409.1556.pdf.
[13] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Patten Recognition. Piscataway:IEEE, 2015:1-9.
[14] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778.
[15] SZEGEDY C, IOFFE S, van HOUCKE V, et al. Inception-V4, inception-ResNet and the impact of residual connections on learning[C]//Proceedings of the 201631st AAAI Conference on Artificial Intelligence. Pola Alto, CA:AAAI, 2016:4278-4284.
[16] GEHLER P, NOWOZIN S. On feature combination for multiclass object classification[C]//Proceedings of the 12th IEEE International Conference on Computer Vision. Piscataway:IEEE, 2009:221-228.
[17] JARRETT K, KAVUKCUOGLU K, RANZATO M, et al. What is the best multi-stage architecture for object recognition?[C]//Proceedings of the 12th IEEE International Conference on Computer Vision. Piscataway:IEEE, 2009:2146-2153.
[18] CHEN P H, LIN C J, SCHOLKOPF, BERNHARD. A tutorial on ν-support vector machines[J]. Applied Stochastic Models in Business and Industry, 2005, 21(2):111-136.
[19] WEISS K, KHOSHGOFTAAR T M, WANG D D. A survey of transfer learning[J]. Journal of Big Data, 2016, 3:9.
[20] WOLD S. Principal component analysis[J]. Chemometrics & Intelligent Laboratory Systems, 1987, 2(1):37-52.
[21] SZEGEDY C, van HOUCKE V, IOFFE S, et al. Rethinking the Inception architecture for computer vision[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:2818-2826.
[22] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436-444.
[23] IOFFE S, SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[EB/OL].[2019-01-10]. https://arxiv.org/pdf/1502.03167.pdf.

基于卷积神经网络的多尺度葡萄图像识别方法

Multi-scale grape image recognition method based on convolutional 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]	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.
[8]	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.
[9]	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.
[10]	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.
[11]	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.
[12]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[13]	吴则举, 焦翠娟, 陈亮. 基于改进Faster R-CNN的轮胎缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1939-1946.
[14]	杨粟, 欧阳智, 杜逆索. 基于相关度距离的无监督并行哈希图像检索[J]. 计算机应用, 2021, 41(7): 1902-1907.
[15]	武光利, 李雷霆, 郭振洲, 王成祥. 基于改进的双向长短期记忆网络的视频摘要生成模型[J]. 计算机应用, 2021, 41(7): 1908-1914.