Abstract
Objective: In order to classify the pecan materials after the shell is broken, and to improve the deep processing level of pecans. Methods: 5 types of pecan samples were obtained through the image acquisition system, including relatively intact shell kernels, undivided kernels, unbroken intact pecans, incomplete shell kernels undivided, and shells. Using the data augmentation way, a sample containing 15 000 images created data sets were obtained. Build a model based on the VGG16 network, which was trained and verified on a data set containing 5 types of pecan material images according to the ratio of 9∶1. Results: The results showed that the accuracy of model training and validation accuracy reached 97.3% and 99.7%, respectively. Through classification and recognition of 1 713 hickory processed material images, the accuracy reached 99.5%. Conclusion: The model can be achieved after a break of pecan shell material classification accuracy requirements.
Publication Date
9-28-2021
First Page
133
Last Page
138,185
DOI
10.13652/j.issn.1003-5788.2021.09.022
Recommended Citation
Wen-bao, LI; Cheng-mao, CAO; Jin-yan, ZHANG; and Mei-le, PENG
(2021)
"Classification and recognition of broken hickory shell materials based on deep learning,"
Food and Machinery: Vol. 37:
Iss.
9, Article 22.
DOI: 10.13652/j.issn.1003-5788.2021.09.022
Available at:
https://www.ifoodmm.cn/journal/vol37/iss9/22
References
[1] 李夕勃, 赵书岗, 王红霞, 等. 核桃坚果硬壳结构与木质素和纤维素相关性研究[J]. 湖北农业科学, 2012, 51（22）: 5 076-5 079.
[2] 刘明政, 李长河, 曹成茂, 等. 核桃分级破壳取仁及壳仁分离关键技术与装置研究进展[J]. 农业工程学报, 2020, 36（20）: 294-310.
[3] 曹成茂, 李正, 罗坤, 等. 山核桃二次破壳取仁机设计与试验[J]. 农业机械学报, 2019, 50（3）: 128-135.
[4] KAMILARIS A, PRENAFETA-BOLDU F X. Deep learning in agriculture: A survey[J]. Computers and Electronics in Agriculture, 2018, 147: 70-90.
[5] MOMENY M, JAHANBAKHSHI A, JAFARNEZHAD K, et al. Accurate classification of cherry fruit using deep CNN based on hybrid pooling approach[J]. Postharvest Biology and Technology, 2020, 166: 111204.
[6] KOZOWSKI M, GRECKI P, SZCZYPINSKI P M. Varietal classification of barley by convolutional neural networks[J]. Biosystems Engineering, 2019, 184: 155-165.
[7] NASIRI A, TAHERI-GARAVAND A, ZHANG Yu-dong. Image-based deep learning automated sorting of date fruit[J]. Postharvest Biology and Technology, 2019, 153: 133-141.
[8] 龚中良, 杨张鹏, 梁力. 基于机器视觉的柑橘表面缺陷检测[J]. 江苏农业科学, 2019, 47（7）: 236-239.
[9] 王鑫, 赵莹, 杨简. 基于视觉技术的苹果分拣系统设计[J]. 中国农机化学报, 2014, 35（5）: 169-172.
[10] 孙宝霞, 汤林越, 何志良, 等. 基于机器视觉的采后荔枝表皮微损伤实时检测[J]. 农业机械学报, 2016, 47（7）: 35-41.
[11] 任锐, 张淑娟, 赵华民. 基于机器视觉的辣椒外部品质检测[J]. 食品与机械, 2021, 37（1）: 165-168.
[12] 刘鸿飞, 黄敏敏, 赵旭东, 等. 基于机器视觉的温室番茄裂果检测[J]. 农业工程学报, 2018, 34（16）: 170-176.
[13] 高震宇, 王安, 刘勇, 等. 基于卷积神经网络的鲜茶叶智能分选系统研究[J]. 农业机械学报, 2017, 48（7）: 53-58.
[14] 汪天宇, 曹成茂, 谢承健, 等. 基于模糊聚类算法的山核桃壳仁分选系统设计[J]. 食品与机械, 2018, 34（6）: 110-114, 157.
[15] 杨明欣, 张耀光, 刘涛. 基于卷积神经网络的玉米病害小样本识别研究[J]. 中国生态农业学报, 2020, 28（12）: 1 924-1 931.
[16] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521（7 553）: 436.
[17] GHAZI M M, YANIKOGLU B, APTOULA E. Plant identification using deep neural networks via optimization of transfer learning parameters[J]. Neurocomputing, 2017, 235: 228-235.
[18] INKYU S, ZONGYUAN G, FERAS D, et al. Deep fruits: A fruit detection system using deep neural networks[J]. Sensors, 2016, 16（8）: 1 222.
[19] DYRMANN M, KARSTOFT H, MIDTIBY H S. Plant species classification using deep convolutional neural network[J]. Biosystems Engineering, 2016, 151: 72-80.
[20] IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]// International Conference on Machine Learning. [S.l.]: PMLR, 2015: 448-456.