|Table of Contents|

Study on the Optimization of Soybean Seed Selection based on Image Recognition and Convolution Neural Network(PDF)

《大豆科学》[ISSN:1000-9841/CN:23-1227/S]

Issue:
2020年02期
Page:
189-197
Research Field:
Publishing date:

Info

Title:
Study on the Optimization of Soybean Seed Selection based on Image Recognition and Convolution Neural Network
Author(s):
ZHU Rong-sheng1;  YAN Xue-hui2;  CHEN Qing-shan3
(1.College of Science,Northeast Agricultural University,Harbin 150030,China; 2.College of Engineering,Northeast Agricultural University,Harbin 150030,China; 3.College of Agricultural,Northeast Agricultural University,Harbin 150030,China)
Keywords:
Soybean seed;  Quality;  Image processing;  Classification;  Convolution neural network
PACS:
-
DOI:
10.11861/j.issn.1000-9841.2020.02.0189
Abstract:
In order to quickly and accurately detect the quality of soybean seeds by the method of seed images recognition, a method of image screening and recognition based on convolution neural network is proposed, taking the classification of normal and abnormal quality seeds as an example. The data set of soybean seed quality was established, and convolution neural network was designed to extract the image features of soybean seed. In order to improve the classification accuracy and real-time performance, the convolution neural network was optimized from the aspects of design and selection of convolution neural network structure, reduction of over fitting, acceleration of training convergence speed, and enhancement of network robustness. Finally, the 6-layer convolution neural network with 4 convolution layers, 4 pooling layers and 2 fully connected layers were selected, L2 regularization and mini batch training methods were used for the network′s optimization training and test. Comparing the results with the traditional machine learning classification methods, the experimental results show that the accuracy of the optimized convolution neural network is 98.8%, and the average detection time of a single soybean seed image is 2.96 ms, which can provide an important reference for soybean seeds quality classification.

References:

［1］吴冬梅,严菊敏,何会超,等.不同贮藏方式对菜用大豆外观和品质的影响［J］.大豆科学,2012,31(1):155-158. (Wu D M, Yan J M, He H C, et al. Effects of different storage method on appearance and quality of vegetable soybean［J］. Soybean Science, 2012, 31(1): 155-158.［2］徐江, 谭敏, 张春庆. 电晕场与介电分选提高水稻种子活力［J］. 农业工程学报, 2013, 29(23): 233-240. (Xu J, Tan M, Zhang C Q, et al. Improving paddy seed vigor by corona discharge field processing and dielectric separation［J］. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(23): 233-240.)［3］杨冬风. 基于软X-射线造影和机器智能的玉米种子活力检测方法研究［J］. 作物杂志, 2013(3):136-140. (Yang D F. Research on detection method of maize vigor based on soft X-ray and computer intelligence［J］. Crops, 2013(3):136-140. ［4］展慧, 李小昱, 周竹，等. 基于近红外光谱和机器视觉融合技术的板栗缺陷检测［J］. 农业工程学报, 2011, 27(2):345-349. (Zhan H, Li X Y, Zhou Z, et al. Detection of chestnut defect based on data fusion of near-infrared spectroscopy and machine vision［J］. Transactions of the CSAE, 2011, 27(2): 345-349. ) ［5］柴玉华, 毕文佳, 谭克竹, 等. 基于高光谱图像技术的大豆品种无损鉴别［J］. 东北农业大学学报, 2016, 47(3): 86-93. (Chai Y H, Bi W J, Tan K Z, et al. Nondestructive identification of soybean seed varieties based on hyperspectral image technology［J］. Journal of Northeast Agricultural University, 2016, 47(3): 86-93.) ［6］Kotabagi S, Desai B L, Linganagouda K, et al. Classification of soybean seed using color image analysis［C］//Afita: The Fifth International Conference of the Asian Federation for Information Technology in Agriculture, 2006.［7］王润涛, 张长利, 房俊龙, 等. 基于机器视觉的大豆籽粒精选技术［J］. 农业工程学报, 2011, 27(8): 355-359. (Wang R T, Zhang C L, Fang J L, et al. Soybean seeds selection based on computer vision［J］. Transactions of the CSAE, 2011, 27(8): 355-359.) ［8］Liu D,Ning X, Li Z, et al. Discriminating and elimination of damaged soybean seeds based on image characteristics［J］. Journal of Stored Products Research, 2015, 60: 67-74.［9］郝建平, 杨锦忠, 杜天庆, 等. 基于图像处理的玉米品种的种子形态分析及其分类研究［J］. 中国农业科学, 2008, 41(4): 994-102. (Hao J P, Yang J Z, Du T Q, et al. A Study on basic morphologic information and classification of maize cultivars based on seed image process［J］. Scientia Agricultura Sinica, 2008,41(4):994-100.)［10］Vilar W T S, Aranha R M, Medeiros E P, et al. Classification of individual castor seed using digital imaging and, multivariate analysis［J］. Journal of the Brazilian Chemical Society, 2014, 26(1):102-109.［11］Kara M,Sayinci B, Elkoca E, et al. Seed size and shape analysis of registered common bean (Phaseolus vulgaris L.) cultivars in Turkey using digital photography［J］.Tarim Bilimleri Dergisi, 2013,19(3):219-234.［12］Wiesnerová D, Ivo W. Computer image analysis of seed shape and seed color for flax cultivar description［J］. Computers and Electronics in Agriculture, 2008, 61(2):126-135.［13］展慧, 李小昱, 王为, 等. 基于机器视觉的板栗分级检测方法［J］. 农业工程学报, 2010, 26(4):327-331. (Zhan H, Li X Y, Wang W, et al. Determination of chestnuts grading based on machine vision［J］. Transactions of the CSAE, 2010, 26(4): 327-331.)［14］Pourreza A, Pourreza H, Abbaspour-Fard M H, et al. Identification of nine Iranian wheat seed varieties by textural analysis with image processing［J］. Computers and Electronics in Agriculture, 2012, 83:102-108.［15］Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions［J/OL］. Computer Science, 2014:1-12［2020-1-20］. https://arxiv.org/pdf/1409.4842v1.pdf.［16］He K , Zhang X , Ren S , et al. Deep residual learning for image recognition［J］. IEEE Computer Science, 2015:1-47［2020-1-20］.https://www.researchgate.net/publication/307964703_Deep_Residual_Learning.［17］Russakovsky O , Deng J , Su H , et al. ImageNet large scale visual recognition challenge［J］. International Journal of Computer Vision, 2014, 115(3): 211-252.［18］Jeon W S, Rhee S Y, Jeon W S, et al. Plant leaf recognition using a convolution neural network［J］. International Journal of Fuzzy Logic and Intelligent Systems, 2017, 17(1): 26-34.［19］张帅, 淮永建. 基于分层卷积深度学习系统的植物叶片识别研究［J］. 北京林业大学学报, 2016, 38(9):108-115.（Zhang S, Huai Y J. Leaf image recognition based on layered convolutions neural network deep learning［J］.Journal of Beijing Forestry University,2016, 38(9) :108-115.)［20］Mohanty S P, Hughes D P, Salathé M . Using deep learning for image-based plant disease detection［J］. Frontiers in Plant Science,2016,7:1419.［21］孙俊，谭文军，毛罕平，等. 基于改进卷积神经网络的多种植物叶片病害识别［J］. 农业工程学报，2017，33(19):209-215. (Sun J, Tan W J, Mao H P, et al. Recognition of multiple plant leaf diseases based on improved convolutional neural network［J］. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(19): 209-215.) ［22］Zhu L, Li Z B, Li C, et al.High performance vegetable classification from images based on Alex Net deep learning model［J］. International Journal of Agricultural and Biological Engineering, 2018; 11(4): 217-223.［23］赵志衡，宋欢，朱江波，等. 基于卷积神经网络的花生籽粒完整性识别算法及应用［J］. 农业工程学报，2018，34(21):195-201.（Zhao Z H,Song H,Zhu J B,et al. Identification algorithm and application of peanut kernel integrity based on convolution neural network［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(21):195-201.）

Memo

Memo:
-
Last Update: 2020-06-10