Online defect detection and automatic grading of carrots using computer vision combined with deep learning methods

Abstract The demand for smart automatic system in postharvest technology, particularly in the postharvest of carrot production is high. In this paper, an automatic carrot grading system was developed based on computer vision and deep learning, which can automatically inspect surface quality of carrots and grade washed carrots. Specifically, based on ShuffleNet and transfer learning, a lightweight deep learning model (CDDNet) was constructed to detect surface defects of carrots. Carrot grading methods were also proposed based on minimum bounding rectangle (MBR) fitting and convex polygon approximation. Experimental results showed that the detection accuracy of the proposed CDDNet was 99.82% for binary classification (normal and defective) and 93.01% for multi-class classification (normal, bad spot, abnormity, fibrous root), and demonstrated good performance both in time efficiency and detection accuracy. The grading accuracy of MBR fitting and convex polygon approximation was 92.8% and 95.1% respectively. This research provides a practical method for online defect detection and carrot grading, and has great application potential in commercial packing lines.

[1]  Deng Limiao,et al.  Identifying carrot appearance quality by transfer learning , 2019, Journal of Food Process Engineering.

[2]  Taghi M. Khoshgoftaar,et al.  A survey on Image Data Augmentation for Deep Learning , 2019, Journal of Big Data.

[3]  Piotr Boniecki,et al.  Computer image analysis in the quality in procedure for selected carrot varieties , 2013, Other Conferences.

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Pedro M. A. Miranda,et al.  Piecewise linear fitting and trend changing points of climate parameters , 2004 .

[6]  Y. Vasseghian,et al.  Modeling of mass transfer in vacuum membrane distillation process for radioactive wastewater treatment using artificial neural networks , 2020, Toxin Reviews.

[7]  Bin Zhang,et al.  An Effective Flame Segmentation Method Based on Ohta Color Space , 2012 .

[8]  Peter J. Ramadge,et al.  Descent Methods for Tuning Parameter Refinement , 2010, AISTATS.

[9]  A. Bahadori,et al.  Modeling the Interfacial Tension of Water-Based Binary and Ternary Systems at High Pressures Using a Neuro-Evolutive Technique , 2019, ACS omega.

[10]  Arthur Zanatta Da Costa,et al.  Computer vision based detection of external defects on tomatoes using deep learning , 2020 .

[11]  U. Mn.  Image processing method for detection of carrot green-shoulder, fibrous roots and surface cracks , 2013 .

[12]  Yong He,et al.  Deep Feature Representation with Stacked Sparse Auto-Encoder and Convolutional Neural Network for Hyperspectral Imaging-Based Detection of Cucumber Defects , 2018 .

[13]  Xin He,et al.  On line detection of defective apples using computer vision system combined with deep learning methods , 2020 .

[14]  Mahmoud Omid,et al.  An automatic sorting system for unwashed eggs using deep learning , 2020 .

[15]  Weijun Xie,et al.  Research on Carrot Grading Based on Machine Vision Feature Parameters , 2019, IFAC-PapersOnLine.

[16]  Deng Limiao,et al.  A Carrot Sorting System Using Machine Vision Technique , 2019, Computer Vision-Based Agriculture Engineering.

[17]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Y. Vasseghian,et al.  Ultrasound Assisted Ash and Sulphur Removal from Bitumen Using Column Flotation Technique: Experimental, RSM and ANN Methods in Modelling and Optimization of Process , 2017 .

[19]  Yu Guo Wu.  A New Kind of Optimization Method for Gear Design , 2012 .

[20]  Deyong Yang,et al.  Research on Carrot Surface Defect Detection Methods Based on Machine Vision , 2019, IFAC-PapersOnLine.

[21]  Hongfei Zhu,et al.  Identifying carrot appearance quality by an improved dense CapNet , 2020 .

[22]  Xiangyu Zhang,et al.  ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[24]  Yuzhen Lu,et al.  Detection of early decay in peaches by structured-illumination reflectance imaging , 2019, Postharvest Biology and Technology.