Weakly-supervised learning approach for potato defects segmentation

Marino, Sofia; Beauseroy, Pierre; Smolarz, André

doi:10.1016/j.engappai.2019.06.024

Cited by 46 publications

(20 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We proposed using the Viola-Jones algorithm at the first stage of processing the image from a video camera, which, unlike convolutional neural networks, works in a real-time mode [58][59][60][61][62][63]. This method was created for recognizing human faces and did not give good results when used to detect potato tubers; however, by selecting preprocessing filters, we achieved a probability of 97%, which corresponds to the results of a convolutional neural network (from 91 to 95% in works on convolutional networks for the last three years) [25][26][27][28][29][30][31].…”

Section: Discussionmentioning

confidence: 99%

“…The researchers used morphological op- To recognize damaged tubers, we must consider a set of factors related to the conditions in which tubers are selected. Most often, convolutional neural networks (CNNs) are used to solve such problems, which have recently significantly improved their performance [25][26][27][28][29][30][31]. However, as the authors of [32] have shown, convolutional neural networks working with high-resolution images are not intended to be implemented on devices with weak processors.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Development of an Optimal Algorithm for Detecting Damaged and Diseased Potato Tubers Moving along a Conveyor Belt Using Computer Vision Systems

et al. 2021

View full text Add to dashboard Cite

The article discusses the problem of detecting sick or mechanically damaged potatoes using machine learning methods. We proposed an algorithm and developed a system for the rapid detection of damaged tubers. The system can be installed on a conveyor belt in a vegetable store, and it consists of a laptop computer and an action camera, synchronized with a flashlight system. The algorithm consists of two phases. The first phase uses the Viola-Jones algorithm, applied to the filtered action camera image, so it aims to detect separate potato tubers on the conveyor belt. The second phase is the application of a method that we choose based on video capturing conditions. To isolate potatoes infected with certain types of diseases (dry rot, for example), we use the Scale Invariant Feature Transform (SIFT)—Support Vector Machine (SVM) method. In case of inconsistent or weak lighting, the histogram of oriented gradients (HOG)—Bag-of-Visual-Words (BOVW)—neural network (BPNN) method is used. Otherwise, Otsu’s threshold binarization—a convolutional neural network (CNN) method is used. The first phase’s result depends on the conveyor’s speed, the density of tubers on the conveyor, and the accuracy of the video system. With the optimal setting, the result reaches 97%. The second phase’s outcome depends on the method and varies from 80% to 97%. When evaluating the performance of the system, it was found that it allows to detect and classify up to 100 tubers in one second, which significantly exceeds the performance of most similar systems.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Development of an Optimal Algorithm for Detecting Damaged and Diseased Potato Tubers Moving along a Conveyor Belt Using Computer Vision Systems

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Such traditional features are usually customized to fit specific identification problems and lack of generalization. Manual feature engineering is a complex and tedious process that the parameters are needed to change according to the types of prediction problems 36 . In this regard, deep learning techniques such as CNN have made a promising achievement in the area of visual object and machine learning.…”

Section: Background Studymentioning

confidence: 99%

Integrated analysis of machine learning and deep learning in chili pest and disease identification

2020

View full text Add to dashboard Cite

BACKGROUND Chili is one of the most important and high‐value vegetable crops worldwide. However, pest and disease infections are among the main limiting factors in chili cultivation. These diseases cannot be eradicated but can be handled and monitored to mitigate the damage. Hence, the use of an automated identification system based on images will promote quick identification of chili disease. The features extracted from the images are of utmost importance to develop such an accurate identification system. RESULTS In this research, chili pest and disease features extracted using the traditional approach were compared with features extracted using a deep‐learning‐based approach. A total of 974 chili leaf images were collected, which consisted of five types of diseases, two types of pest infestations, and a healthy type. Six traditional feature‐based approaches and six deep‐learning feature‐based approaches were used to extract significant pests and disease features from the chili leaf images. The extracted features were fed into three machine learning classifiers, namely a support vector machine (SVM), a random forest (RF), and an artificial neural network (ANN) for the identification task. The results showed that deep learning feature‐based approaches performed better than the traditional feature‐based approaches. The best accuracy of 92.10% was obtained with the SVM classifier. CONCLUSION A deep‐learning feature‐based approach could capture the details and characteristics between different types of chili pests and diseases even though they possessed similar visual patterns and symptoms. © 2020 Society of Chemical Industry

show abstract

“…Anderson et al [26] compared several orchards in fruits counts and indicated that the DCNNs-based methods gave a better result than transitional methods. In addition, few other specific deep learning-based methods were designed to simplify the model building for better estimation performance [27][28][29].…”

Section: Introductionmentioning

confidence: 99%

Culling Double Counting in Sequence Images for Fruit Yield Estimation

et al. 2022

View full text Add to dashboard Cite

Exact yield estimation of fruits on plants guaranteed fine and timely decisions on harvesting and marketing practices. Automatic yield estimation based on unmanned agriculture offers a viable solution for large orchards. Recent years have witnessed notable progress in computer vision with deep learning for yield estimation. Yet, the current practice of vision-based yield estimation with successive frames may engender fairly great error because of the double counting of repeat fruits in different images. The goal of this study is to provide a wise framework for fruit yield estimation in sequence images. Specifically, the anchor-free detection architecture (CenterNet) is utilized to detect fruits in sequence images from videos collected in the apple orchard and orange orchard. In order to avoid double counts of a single fruit between different images in an image sequence, the patch matching model is designed with the Kuhn–Munkres algorithm to optimize the paring process of repeat fruits in a one-to-one assignment manner for the sound performance of fruit yield estimation. Experimental results show that the CenterNet model can successfully detect fruits, including apples and oranges, in sequence images and achieved a mean Average Precision (mAP) of 0.939 under an IoU of 0.5. The designed patch matching model obtained an F1-Score of 0.816 and 0.864 for both apples and oranges with good accuracy, precision, and recall, which outperforms the performance of the reference method. The proposed pipeline for the fruit yield estimation in the test image sequences agreed well with the ground truth, resulting in a squared correlation coefficient of R2apple = 0.9737 and R2orange = 0.9562, with a low Root Mean Square Error (RMSE) for these two varieties of fruit.

show abstract

Weakly-supervised learning approach for potato defects segmentation

Cited by 46 publications

References 17 publications

Development of an Optimal Algorithm for Detecting Damaged and Diseased Potato Tubers Moving along a Conveyor Belt Using Computer Vision Systems

Development of an Optimal Algorithm for Detecting Damaged and Diseased Potato Tubers Moving along a Conveyor Belt Using Computer Vision Systems

Integrated analysis of machine learning and deep learning in chili pest and disease identification

Culling Double Counting in Sequence Images for Fruit Yield Estimation

Contact Info

Product

Resources

About