基于改进InceptionV3算法的小麦杂质识别研究

doi:10.13733/j.jcam.issn.2095-5553.2024.04.016

摘要/Abstract

摘要： 为解决传统人工识别小麦效率低、主观性高的问题，提出一种基于改进的CBAMInceptionV3小麦杂质识别方法。搭建机器视觉在线检测平台采集动态图像数据，采用数据集增强、图像预处理和KS分类方法对小麦杂质图像进行处理；选用GoogLeNet、ResNet34、InceptionV3三种模型对图像数据集进行分类训练。以InceptionV3模型为基础，引入注意力机制CBAM，增强模型对信息的敏感度，提升模型的识别准确率。将改进卷积神经网络CBAMInceptionV3模型与加入CA模块的CAInceptionV3、InceptionV3两种模型进行对比试验。结果表明，InceptionV3模型在测试集上准确率为83.5%、F1Score为82.41%，CAInceptionV3模型在测试集上准确率为92.3%、F1Score值为92.29%，CBAMInceptionV3在测试集上准确率为92.9%、F1Score值为92.92%。CBAMInceptionV3模型对测试集的平均预测时间为0.045张/s，明显优于其他两种模型。

关键词: 小麦杂质, 卷积神经网络, 分类识别, CBAMInceptionV3, 可视化

Abstract: In order to solve the problem of low efficiency and high subjectivity of traditional wheat identification, an improved CBAMInceptionV3 wheat impurity identification method was proposed. Firstly, a machine vision online detection platform was built to collect dynamic image data, and the wheat impurity image was processed by data set enhancement, image preprocessing and KS classification. Then, GoogLeNet, ResNet34 and InceptionV3 models were used to classify and train the image data set. Secondly, based on InceptionV3 model, CBAM was introduced to enhance the sensitivity of the model to information and improve the recognition accuracy of the model. The improved convolutional neural network CBAMInceptionV3 model is compared with CAInceptionV3 and InceptionV3 models added in CA module. The results show that the accuracy of InceptionV3 model on test set is 83.5% and F1Score is 82.41%, and the accuracy of CAInceptionV3 model on test set is 92.3% and F1Score is 92.29%. CBAMInceptionV3 has 92.9% accuracy and 92.92% F1Score on the test set. The average prediction time of CBAMInceptionV3 model for the test set is 0.045 pieces/s, which is significantly better than the other two models.

Key words: wheat impurity, convolutional neural network, classification and recognition, CBAMInceptionV3, visualization

中图分类号:

林燕翔, 沈印, 李光林. 基于改进InceptionV3算法的小麦杂质识别研究[J]. 中国农机化学报, 2024, 45(4): 108-116.

Lin Yanxiang, Shen Yin, Li Guanglin. Research on wheat impurity identification based on improved InceptionV3 algorithm[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(4): 108-116.

参考文献

［1］　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.
［2］　苏忆楠. 基于机器视觉和高光谱图像技术的粮食水分检测及杂质与不完善粒识别方法研究［D］. 杭州: 浙江大学, 2011.
Su Yinan. Research on grain water content detection and impurities recognition method based on machine vision and hyperspectral imaging technique ［D］. Hangzhou: Zhejiang University, 2011.
［3］　Singh C B, Jayas D S, Paliwal J, et al. Identification of insectdamaged wheat kernels using shortwave nearinfrared hyperspectral and digital colour imaging ［J］. Computers and Electronics in Agriculture, 2010, 73(2): 118-125.
［4］　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 Huan, Wang Yaqian, Wang Xiaoming, et al. Study on detection method of wheat unsound kernel based on nearinfrared hyperspectral imaging technology ［J］. Spectroscopy and Spectral Analysis, 2019, 39(1): 223-229.
［5］　樊超, 夏旭, 石小凤, 等. 基于图像处理的小麦品种分类研究［J］. 河南工业大学学报(自然科学版), 2011, 32(5): 74-78.
Fan Chao, Xia Xu, Shi Xiaofeng, et al. Wheat variety classification based on image processing ［J］. Journal of Henan University of Technology (Natural Science Edition), 2011, 32(5): 74-78.
［6］　何红霞. 基于机器视觉的小麦种子品种分类模型研究［D］. 合肥: 安徽农业大学, 2018.
He Hongxia. Study on classification model of wheat seed varieties based on machine vision ［J］. Hefei: Anhui Agricultural University, 2018.
［7］　孟惜. 基于图像处理的小麦籽粒饱满度检测及品种识别［D］. 保定: 河北农业大学, 2017.
Meng Xi. Detection of wheat grain saturation and identification of varieties based on image processing ［D］. Baoding: Heibei Agricultural University, 2017.
［8］　刘光宗. 小麦含水率、容重、杂余数字化检测方法研究［D］. 合肥: 安徽农业大学, 2020.
Liu Guangzong. Study on digital detection method of wheat moisture content, test weight and miscellaneous ［D］. Hefei: Anhui Agricultural University, 2020.
［9］　陈进, 韩梦娜, 练毅, 等. 基于UNet模型的含杂水稻籽粒图像分割［J］. 农业工程学报, 2020, 36(10): 174-180.
Chen Jin, Han Mengna, Lian Yi, et al. Segmentation of impurity rice grain images based on UNet model ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(10): 174-180.
［10］　马志艳, 张徐康, 杨光友. 基于改进Mask RCNN的水稻茎秆杂质分割方法研究［J］. 中国农机化学报, 2021, 42(6): 145-150.
Ma Zhiyan, Zhang Xukang, Yang Guangyou. Research on segmentation method of rice stem impurities based on improved Mask RCNN ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(6): 145-150.
［11］　Sa I, Ge Z, Dayoub F, et al. Deepfruits: A fruit detection system using deep neural networks ［J］. Sensors, 2016, 16(8): 1222.
［12］　陈进, 张帅, 李耀明, 等. 联合收获机水稻破碎籽粒及杂质在线识别方法［J］. 中国农机化学报, 2021, 42(6): 137-144.
Chen Jin, Zhang Shuai, Li Yaoming, et al. Research on online identification system of rice broken impurities in combine harvester ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(6): 137-144.
［13］　张思雨, 张秋菊, 李可. 采用机器视觉与自适应卷积神经网络检测花生仁品质［J］. 农业工程学报, 2020, 36(4): 269-277.
Zhang Siyu, Zhang Qiuju, Li Ke. Detection of peanut kernel quality based on machine vision and adaptive convolution neural network ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(4): 269-277.
［14］　Rong D, Wang H, Xie L, et al. Impurity detection of juglans using deep learning and machine vision ［J］. Computers and Electronics in Agriculture, 2020, 178: 105764.
［15］　赵德安, 吴任迪, 刘晓洋, 等. 基于YOLO深度卷积神经网络的复杂背景下机器人采摘苹果定位［J］. 农业工程学报, 2019, 35(3): 164-173.
Zhao Dean, Wu Rendi, Liu Xiaoyang, et al. Apple positioning based on YOLO deep convolutional neural network for picking robot in complex background ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(3): 164-173.
［16］　刘小刚, 范诚, 李加念, 等. 基于卷积神经网络的草莓识别方法［J］. 农业机械学报, 2020, 51(2): 237-244.
Liu Xiaogang, Fan Cheng, Li Jianian, et al. Identification method of strawberry based on convolutional neural network ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(2): 237-244.
［17］　傅隆生, 冯亚利, Elkamil Tola, 等. 基于卷积神经网络的田间多簇猕猴桃图像识别方法［J］. 农业工程学报, 2018, 34(2): 205-211.
Fu Longsheng, Feng Yali, Elkamil Tola, et al. Image recognition method of multicluster kiwifruit in field based on convolutional neural networks ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(2): 205-211.
［18］　张博, 张苗辉, 陈运忠. 基于空间金字塔池化和深度卷积神经网络的作物害虫识别［J］. 农业工程学报, 2019, 35(19): 209-215.
Zhang Bo, Zhang Miaohui, Chen Yunzhong. Crop pest identification based on spatial pyramid pooling and deep convolution neural network ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(19): 209-215.
［19］　Zhang Z, Liu H, Meng Z, et al. Deep learningbased automatic recognition network of agricultural machinery images ［J］. Computers and Electronics in Agriculture, 2019, 166: 104978.
［20］　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］. 农业机械学报, 2020, 51(5): 36-42.
Zhu Shiping, Zhuo Jiaxin, Huang Hua, et al. Wheat grain integrity image detection system based on CNN ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(5): 36-42.
［21］　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 Tingcui, He Xiaohai, Dong Deliang, et al. Identification of unsound kernels in wheat based on CNN deep model ［J］. Modern Computer (Professional Edition), 2017(36): 9-14.
［22］　张博. 基于深度学习的小麦外观品质机器视觉检测研究［D］.咸阳: 西北农林科技大学, 2019.
Zhang Bo. Machine vision inseption of wheat apprearance quality based on deep learning ［D］. Xianyang: Northwest A & F University, 2019.
［23］　宋怀波, 王云飞, 段援朝, 等. 基于YOLO v5-MDC的重度粘连小麦籽粒检测方法［J］. 农业机械学报, 2022, 53(4): 245-253.
Song Huaibo, Wang Yunfei, Duan Yuanchao, et al. Detection method of severe adhesive wheat grain based on YOLO v5-MDC model ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(4): 245-253.
［24］　Singh A, Arora M. CNN based detection of healthy and unhealthy wheat crop ［C］. 2020 International Conference on Smart Electronics and Communication (ICOSEC). IEEE, 2020: 121-125.
［25］　武威. 基于机器视觉技术的稻麦籽粒外观品质评测研究［D］. 扬州: 扬州大学, 2021.
Wei Wu. Research on appearance quality evaluation of rice and wheat grains based on machine vision technology ［D］. Yangzhou: Yangzhou University, 2021.
［26］　Zhang X, Qiao Y, Meng F, et al. Identification of maize leaf diseases using improved deep convolutional neural networks ［J］. IEEE Access, 2018, 6: 30370-30377.
［27］　Tsai C M. Adaptive local powerlaw transformation for color image enhancement ［J］. Applied Mathematics & Information Sciences, 2013, 7(5): 2019.
［28］　Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module ［J］. Springer, Cham, 2018.
［29］　Ashiquzzaman A, Tushar A K, Dutta S, et al. An efficient method for improving classification accuracy of handwritten Bangla compound characters using DCNN with dropout and ELU ［C］. 2017 Third International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN). IEEE, 2017: 147-152.
［30］　Hripcsak G, Rothschild A S. Technical brief: agreement, the FMeasure, and reliability in information retrieval ［J］. Hripcsak, Rothschilsd, Agreement in Information Retrieval, 2005, 12(3): 296-298.
［31］　Selvaraju R R, Cogswell M, Das A, et al. Gradcam: Visual explanations from deep networks via gradientbased localization ［C］. Proceedings of the IEEE International Conference on Computer Vision. 2017: 618-626.

[1]	张慧蒙, 何超, 徐嘉雯, 罗鑫, 荣剑, 刘学渊. 基于SCGYOLOv5n的收获期澳洲坚果检测算法[J]. 中国农机化学报, 2024, 45(4): 214-221.
[2]	纪元浩, 许金普, 严蓓蓓, 薛俊龙. 基于改进ResNet50模型的咖啡生豆质量和缺陷检测方法[J]. 中国农机化学报, 2024, 45(4): 237-243.
[3]	刘勤, 曹光乔, 胡良龙, 王祎娜, 司明昊. 江苏农机创新主体创新动态分析[J]. 中国农机化学报, 2024, 45(4): 302-310.
[4]	冯树南, , 谭涛, , 尚静, , 温青纯, 孟庆龙, . 枇杷糖度无损检测及可视化研究[J]. 中国农机化学报, 2024, 45(2): 151-156.
[5]	张建杰, 卢紫冰. 我国家庭农场的研究进展——基于CiteSpace的可视化分析[J]. 中国农机化学报, 2024, 45(2): 303-310.
[6]	仇振升, , 胡肄农, 刘建龙, 段恩泽, 田雨, 柏宗春, . 基于数字孪生技术的奶牛场养殖监控平台设计[J]. 中国农机化学报, 2024, 45(1): 183-192.
[7]	方俊泽, 郭正, 李歌, 邢素霞, 王瑜. 基于改进Swin-Transformer的柑橘病叶分类模型[J]. 中国农机化学报, 2024, 45(1): 252-258.
[8]	董萍, 王明, 彭飞, 时雷, 张娟娟, 司海平. 基于Web of Science的作物病害监测和预警研究进展[J]. 中国农机化学报, 2023, 44(9): 137-145.
[9]	梁万杰, 曹静, 孙传亮, 曹宏鑫, 张文宇, . 基于深度学习的农作物病害识别系统研发[J]. 中国农机化学报, 2023, 44(9): 169-175.
[10]	杨波, 何金平, 张立娜. 基于改进SPP-x的YOLOv5神经网络水稻叶片病害识别检测[J]. 中国农机化学报, 2023, 44(9): 190-197.
[11]	汪健, 梁兴建, 雷刚. 基于深度残差网络与迁移学习的水稻病虫害图像识别[J]. 中国农机化学报, 2023, 44(9): 198-204.
[12]	何琼, 李其晓. 我国农业机械可靠性演化分析[J]. 中国农机化学报, 2023, 44(8): 47-55.
[13]	李宗南, 蒋怡, 王思, 李源洪, 黄平, 魏鹏. 基于YOLOv5模型的飞蓬属入侵植物目标检测[J]. 中国农机化学报, 2023, 44(7): 200-206.
[14]	李平, 马玉琨, 李艳翠, 冯继克, 赵明富. 基于迁移学习的小麦籽粒品种识别研究[J]. 中国农机化学报, 2023, 44(7): 220-228.
[15]	周显沁, 韩震宇, 刘成源. 基于改进卷积神经网络与图像处理的蚕茧识别方法[J]. 中国农机化学报, 2023, 44(5): 100-106.