Potato Surface Defect Detection Based on Deep Transfer Learning

Wang, Chenglong; Xiao, Zhifeng

doi:10.3390/agriculture11090863

Cited by 23 publications

(18 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to our study, their developed VGG model achieved lower recall, precision, and F1-score of 78, 93 and 85% for crack detection in green plums under controlled imaging conditions. However, in another study [13], their developed R-FCN ResNet101 model for scratch detection in potato had a higher precision (98.1%), recall (99%) and F1-score (98.6%) compared with our proposed networks. This could be due to the different conditions used in two studies, e.g., imaging situations, the type of damage and samples, as well as the controlled conditions of trial in the study [13].…”

Section: Resultsmentioning

confidence: 62%

“…Furthermore, [31] reported that YOLO v4 was able to detect apple fruit in a complex environment with recall and an average precision of around 93 and 88%, respectively, compared to Faster R-CNN with 90 and 83%, respectively. The use of R-FCN as a detector and ResNet101 as a feature extractor showed also high values of precision and recall of more than 98% in a study by [13] for potato surface defect detection. However, compared to our study, the images of the fruit were captured in a control situation.…”

Section: Resultsmentioning

confidence: 96%

“…Their developed models allowed users to classify and detect mechanical damage of up to 100 tubers in one second. In a similar study, the deep learning-based detection of potato damage and defects was investigated by [13]. In that study, transfer learning through various deep-CNNs, i.e., single shot multibox detector (SSD) inception v2, faster regions with convolutional neural network (Faster R-CNN) ResNet101, and region-based fully convolutional network (R-FCN) ResNet101 were developed.…”

Section: Introductionmentioning

confidence: 99%

“…In that study, transfer learning through various deep-CNNs, i.e., single shot multibox detector (SSD) inception v2, faster regions with convolutional neural network (Faster R-CNN) ResNet101, and region-based fully convolutional network (R-FCN) ResNet101 were developed. Their results showed that the R-FCN ResNet101 had the best overall performance in detection speed and accuracy [13]. Likewise, a CNN and a computer vision method to classify defects and damages of green plums was adopted [14].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Sugar Beet Damage Detection during Harvesting Using Different Convolutional Neural Network Models

2021

View full text Add to dashboard Cite

Mechanical damages of sugar beet during harvesting affects the quality of the final products and sugar yield. The mechanical damage of sugar beet is assessed randomly by operators of harvesters and can depend on the subjective opinion and experience of the operator due to the complexity of the harvester machines. Thus, the main aim of this study was to determine whether a digital two-dimensional imaging system coupled with convolutional neural network (CNN) techniques could be utilized to detect visible mechanical damage in sugar beet during harvesting in a harvester machine. In this research, various detector models based on the CNN, including You Only Look Once (YOLO) v4, region-based fully convolutional network (R-FCN) and faster regions with convolutional neural network features (Faster R-CNN) were developed. Sugar beet image data during harvesting from a harvester in different farming conditions were used for training and validation of the proposed models. The experimental results showed that the YOLO v4 CSPDarknet53 method was able to detect damage in sugar beet with better performance (recall, precision and F1-score of about 92, 94 and 93%, respectively) and higher speed (around 29 frames per second) compared to the other developed CNNs. By means of a CNN-based vision system, it was possible to automatically detect sugar beet damage within the sugar beet harvester machine.

show abstract

Section: Resultsmentioning

confidence: 62%

Section: Resultsmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sugar Beet Damage Detection during Harvesting Using Different Convolutional Neural Network Models

2021

View full text Add to dashboard Cite

show abstract

“…Machine vision inspection has the advantages of economy, objectivity, and high index, which overcome the disadvantages of high labor costs, low efficiency, vague grading standards, and subjectivity of manual expert inspection. It has become a hot research topic in crop shape inspection [ 33 ]. However, existing methods use high-dimensional feature parameters to accurately detect the complex variable shapes of irregular potatoes.…”

Section: Introductionmentioning

confidence: 99%

Identifying Irregular Potatoes Using Hausdorff Distance and Intersection over Union

Jiang

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

Further processing and the added value of potatoes are limited by irregular potatoes. An ellipse-fitting-based Hausdorff distance and intersection over union (IoU) method for identifying irregular potatoes is proposed to solve the problem. First, the acquired potato image is resized, translated, segmented, and filtered to obtain the potato contour information. Secondly, a least-squares fitting method fits the extracted contour to an ellipse. Then, the similarity between the irregular potato contour and the fitted ellipse is characterized using the perimeter ratio, area ratio, Hausdorff distance, and IoU. Next, the characterization ability of the four features is analyzed, and an identification standard of irregular potatoes is established. Finally, we discuss the algorithm’s shortcomings in this paper and draw the advantages of the algorithm by comparison. The experimental results showed that the characterization ability of perimeter ratio and area ratio was inferior to that of Hausdorff distance and IoU, and using Hausdorff distance and IoU as feature parameters can effectively identify irregular potatoes. Using Hausdorff distance separately as a feature parameter, the algorithm achieved excellent performance, with precision, recall, and F1 scores reaching 0.9423, 0.98, and 0.9608, respectively. Using IoU separately as a feature parameter, the algorithm achieved a higher overall recognition rate, with precision, recall, and F1 scores of 1, 0.96, and 0.9796, respectively. Compared with existing studies, the proposed algorithm identifies irregular potatoes using only one feature, avoiding the complexity of high-dimensional features and significantly reducing the computing effort. Moreover, simple threshold segmentation does not require data training and saves algorithm execution time.

show abstract

A scalable, low‐cost phenotyping strategy to assess tuber size, shape, and the colorimetric features of tuber skin and flesh in potato breeding populations

Feldman,

Park,

Miller

et al. 2024

The Plant Phenome Journal

View full text Add to dashboard Cite

Tuber size, shape, colorimetric characteristics, and defect susceptibility are all factors that influence the acceptance of new potato cultivars. Despite the importance of these characteristics, our understanding of their inheritance is substantially limited by our inability to precisely measure these features quantitatively on the scale needed to evaluate breeding populations. To alleviate this bottleneck, we developed a low‐cost, semiautomated workflow to capture data and measure each of these characteristics using machine vision. This workflow was applied to assess the phenotypic variation present within 189 F1 progeny of the A08241 breeding population. Machine vision was applied to estimate linear and volumetric tuber size, assess tuber shape characteristics using aspect ratio and biomass profiles, and quantify tuber skin and flesh color; additionally, a deep learning mode was developed to classify the presence of hollow‐heart defect. Our results provide an example of quantitative measurements acquired using machine vision methods that are reliable, heritable, and capable of being used to understand and select multiple traits simultaneously in structured potato breeding populations.

show abstract

Potato Surface Defect Detection Based on Deep Transfer Learning

Cited by 23 publications

References 50 publications

Sugar Beet Damage Detection during Harvesting Using Different Convolutional Neural Network Models

Sugar Beet Damage Detection during Harvesting Using Different Convolutional Neural Network Models

Identifying Irregular Potatoes Using Hausdorff Distance and Intersection over Union

A scalable, low‐cost phenotyping strategy to assess tuber size, shape, and the colorimetric features of tuber skin and flesh in potato breeding populations

Contact Info

Product

Resources

About