Abstract
[Objective] Aiming at the problems of low accuracy and poor robustness in the previous classification methods based on artificial features. [Methods] A strong generalization automatic classification method of potato shape and size was proposed in this study. First, two potato ViT models were built based on Transformer model to complete potato shape grading and size grading tasks in parallel. Secondly, a robust model was trained by using migration strategy and data augmentation method. Finally, the effectiveness of this method in potato grading was verified by quantitative analysis of test sets. [Results] The experimental results show that the potato ViT model achieves 96.36% and 94.75% for potato shape classification, and 89.66% and 85.16% for size grading in terms of accuracy and μF1 index. The classification accuracy was better than VGG16, ResNet50 and MobileNetV3 network models. [Conclusion] The results shows that it is feasible to apply the proposed method for the real-time and accurate detection of potato shape and size. The results of this study can provide theoretical and technical support for potato intelligent grading.
Publication Date
9-11-2024
First Page
111
Last Page
116
DOI
10.13652/j.spjx.1003.5788.2023.81032
Recommended Citation
Hongpeng, FAN; Pengfei, YU; and Sen, YANG
(2024)
"Automatic grading of potato shape and size based on visual Transformer,"
Food and Machinery: Vol. 40:
Iss.
7, Article 17.
DOI: 10.13652/j.spjx.1003.5788.2023.81032
Available at:
https://www.ifoodmm.cn/journal/vol40/iss7/17
References
[1] 肖伟中, 高迎春, 陈海需, 等. 小型马铃薯捡拾分级机的设计与试验[J]. 农机化研究, 2019, 41（12）: 130-134.
XIAO W Z, GAO Y C, CHEN H X, et al. Design and test of a small potato pickup and grading machine[J]. Journal of Agricultural Mechanization Research, 2019, 41（12）: 130-134.
[2] 向静, 何志良, 汤林越, 等. 结合计算机视觉的马铃薯外部品质检测技术[J]. 计算机工程与应用, 2018, 54（5）: 165-169.
XIANG J, HE Z L, TANG L Y, et al. Research of potato quality detection technology based on computer vision[J]. Comp Engin Appl, 2018, 54（5）: 165-169.
[3] 孔彦龙, 高晓阳, 李红玲, 等. 基于机器视觉的马铃薯质量和形状分选方法[J]. 农业工程学报, 2012, 28（17）: 143-148.
KONG Y L, GAO X Y, LI H L, et al. Potato grading method of mass and shapes based on machine vision[J]. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28（17）: 143-148.
[4] SU Q H, KONDO N S, LI M Z, et al. Potato quality grading based on machine vision and 3D shape analysis[J]. Computers and Electronics in Agriculture, 2018, 152: 261-268.
[5] 王红军, 熊俊涛, 黎邹邹, 等. 基于机器视觉图像特征参数的马铃薯质量和形状分级方法[J]. 农业工程学报, 2016, 32（8）: 272-277.
WANG H J, XIONG J T, LI Z Z, et al. Potato grading method of weight and shape based on imaging characteristics parameters in machine vision system[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32（8）: 272-277.
[6] 邓立苗, 杜宏伟, 徐艳, 等. 基于机器视觉的马铃薯智能分选方法与实现[J]. 中国农机化学报, 2015, 36（5）: 145-150.
DENG L M, DU H W, XU Y, et al. Implementation of intelligent potato grading method based on vision[J]. Journal of Chinese Agricultural Mechanization, 2015, 36（5）: 145-150.
[7] SHI R, LI T X, YAMAGUCHI Y S. An attribution-based pruning method for real-time mango detection with YOLO network[J]. Computers and Electronics in Agriculture, 2020, 169: 105214.
[8] WU L, MA J, ZHAO Y H, et al. Apple detection in complex scene using the improved YOLOv4 model[J]. Agronomy, 2021, 11（3）: 476.
[9] 曲福恒, 李金状, 杨勇, 等. 基于改进DeepLabv3+的轻量化作物杂草识别方法[J]. 石河子大学学报（自然科学版）, 2024, 42（1）: 117-125.
QU F H, LI J Q, YANG Y, et al. Lightweight crop and weed recognition method based onimporved DeepLabv3+[J]. Journal of Shihezi University （Natural Science）, 2024, 42（1）: 117-125.
[10] WU D H, LU S C, JIANG M, et al. Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments[J]. Computers and Electronics in Agriculture, 2020, 178: 105742.
[11] XIONG J T, LIU Z, CHEN S M, et al. Visual detection of green mangoes by an unmanned aerial vehicle in orchards based on a deep learning method[J].Biosystems Engineering, 2020, 194: 261-272.
[12] 杨森, 冯全, 张建华, 等. 基于轻量卷积网络的马铃薯外部缺陷无损分级[J]. 食品科学, 2021, 42（10）: 284-289.
YANG S, FENG Q, ZHANG J H, et al. Non-destructive classification of potato external defects based on lightweight convolutional network[J]. Food Science, 2021, 42（10）: 284-289.
[13] 汪成龙, 黄余凤, 庄学敏, 等. 基于深度学习的马铃薯畸形检测方法研究[J]. 惠州学院学报, 2018, 38（3）: 61-66.
WANG C L, HUANG Y F, ZHUANG X M, et al. Research on-method methodmethod potato on deep potato[J]. Journal of Huizhou University, 2018, 38（3）: 61-66.
[14] 张兆国, 张振东, 李加念, 等. 采用改进YoloV4模型检测复杂环境下马铃薯[J]. 农业工程学报, 2021, 37（22）: 170-178.
ZHANG Z G, ZHANG Z D, LI J N, et al. Potato detection in complex environment based on improved YoloV4 model[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37（22）: 170-178.
[15] 史方青, 王虎林, 黄华. 基于卷积神经网络的马铃薯芽眼检测识别研究[J]. 中国农机化学报, 2022, 43（6）: 159-165.
SHI F Q, WANG H L, HUANG H. Research on potato buds detection and recognition based on convolutional neural network[J]. Journal of Chinese Agricultural Mechanization, 2022, 43（6）: 159-165.
[16] 贾伟宽, 孟虎, 马晓慧, 等. 基于优化Transformer网络的绿色目标果实高效检测模型[J]. 农业工程学报, 2021, 37（14）: 163-170.
JIA W K, MENG H, MA X H, et al. Efficient detection model of green target fruit based on optimized Transformer network[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37（14）: 163-170.
[17] 徐艳蕾, 孔朔琳, 陈清源, 等. 基于Transformer的强泛化苹果叶片病害识别模型[J]. 农业工程学报, 2022, 38（16）: 198-206.
XU Y L, KONG S L, CHEN Q Y, et al. Model for identifying strong generalization apple leaf disease using Transformer[J]. Transactions of The Chinese Society of Agricultural Engineering, 2022, 38（16）: 198-206.
[18] 周丽娟, 毛嘉宁. 视觉Transformer识别任务研究综述[J]. 中国图象图形学报, 2023, 28（10）: 2 969-3 003.
ZHOU L J, MAO J N. Vision Transformer-based recognition tasks: a critical review[J]. Journal of Image and Graphics, 2023, 28（10）: 2 969-3 003.
[19] BAZI Y, BASHMAL L, RAHHAL MM A, et al. Vision transformers for remote sensing image classification[J]. Remote Sensing, 2021, 13（3）: 516.
[20] CAI G, ZHU Y, WU Y, et al. A multimodal transformer to fuse images and metadata for skin disease classification[J]. The Visual Computer, 2023, 39（7）: 2 781-2 793.
[21] AFONSO M, FONTEIJN H, POLDER G, et al. Tomato fruit detection and counting in greenhouses using deep learning[J]. Frontiers in Plant Science, 2020, 11: 571299.
[22] REEDHA R, DERICQUEBOURG E, CANALS R, et al. Transformer neural network for weed and crop classification of high resolution UAV images[J]. Remote Sensing, 2022, 14（3）: 592.