Detection and counting of root-knot nematodes using YOLO models with mosaic augmentation

Pun, Top Bahadur; Neupane, Arjun; Koech, Richard; Walsh, Kerry

doi:10.1016/j.biosx.2023.100407

Cited by 7 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All three single-stage models exhibited numerous precision, accuracy, or recall values greater than 99% when assessing five or two classes. Such metrics can suggest potential overfitting risks; however, these results are in line with previous studies that also prevented overfitting when using YOLOv4 [64,65], YOLOv5 [66][67][68], or YOLOv8 [69]. Overfitting is a fundamental issue in supervised machine learning, which prevents generalizing the models to fit observed data on training data, as well as unseen data on testing sets [70].…”

Section: Deep Learning Modelssupporting

confidence: 85%

An Assessment of Human Inspection and Deep Learning for Defect Identification in Floral Wreaths

Caballero-Ramirez,

Baez-Lopez,

Limon-Romero

et al. 2023

Horticulturae

View full text Add to dashboard Cite

Quality assurance through visual inspection plays a pivotal role in agriculture. In recent years, deep learning techniques (DL) have demonstrated promising results in object recognition. Despite this progress, few studies have focused on assessing human visual inspection and DL for defect identification. This study aims to evaluate visual human inspection and the suitability of using DL for defect identification in products of the floriculture industry. We used a sample of defective and correct decorative wreaths to conduct an attribute agreement analysis between inspectors and quality standards. Additionally, we computed the precision, accuracy, and Kappa statistics. For the DL approach, a dataset of wreath images was curated for training and testing the performance of YOLOv4-tiny, YOLOv5, YOLOv8, and ResNet50 models for defect identification. When assessing five classes, inspectors showed an overall precision of 92.4% and an accuracy of 97%, just below the precision of 93.8% obtained using YOLOv8 and YOLOv5 with accuracies of 99.9% and 99.8%, respectively. With a Kappa value of 0.941, our findings reveal an adequate agreement between inspectors and the standard. The results evidence that the models presented a similar performance to humans in terms of precision and accuracy, highlighting the suitability of DL in assisting humans with defect identification in artisanal-made products from floriculture. Therefore, by assisting humans with digital technologies, organizations can embrace the full potential of Industry 4.0, making the inspection process more intelligent and reliable.

show abstract

Section: Deep Learning Modelssupporting

confidence: 85%

An Assessment of Human Inspection and Deep Learning for Defect Identification in Floral Wreaths

Caballero-Ramirez,

Baez-Lopez,

Limon-Romero

et al. 2023

Horticulturae

View full text Add to dashboard Cite

show abstract

“…Convolutional Neural Networks [14], [15] (CNNs) are ideal for insect classification because they process image data. CNN applies convolutional layers to insect imagery to simulate human vision and understand intricate features.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Comparison Efficacy of VGG16 and VGG19 Insect Classification Models

Hindarto,

Afarini,

Esthi H

2023

jiko

View full text Add to dashboard Cite

This study compares two popular deep-learning models, VGG16 and VGG19, for insect classification. This study aims to evaluate insect detection architectures to automate insect identification. We use a large, heterogeneous dataset of insect species, including common pests and beneficial insects, and their images to achieve this goal. The dataset was used to re-adjust the VGG16 and VGG19 models and analyze their classification performance. With an average improvement of 1,8%, VGG19 outperforms VGG16 in insect classification accuracy. VGG19 is more robust because it can handle complex traits and subtle insect morphology differences. Each architecture's model training duration and computational resources are examined for their practicality in real-world scenarios. This study emphasizes deep learning models in insect classification and shows VGG19's higher accuracy and robustness than VGG16. These findings matter to entomologists, agricultural researchers, and pest control experts. They can improve insect identification accuracy and effectiveness using VGG19-based models, which can help solve insect-related problems in various fields.96.28 percent accuracy was achieved with the implementation of VGG16, according to the experimental findings; 97.07 percent accuracy was obtained with the implementation of VGG19.

show abstract

“…In addition, YOLOv8 (Pun et al, 2023) can do segmentation tasks, enabling the model to distinguish objects from the background within an image effectively. Accurate object identification and background isolation are particularly crucial in applications that require exact delineation of objects, such as recognizing handwritten characters in text processing.…”

Section: Ultralyticsmentioning

confidence: 99%

Exploring YOLOv8 Pretrain for Real-Time Detection of Indonesian Native Fish Species

Hindarto

2023

SinkrOn

View full text Add to dashboard Cite

The main objective of this research is to determine the efficacy of the YOLO model in detecting native fish species found in Indonesia. Indonesia has a variety of maritime natural resources and shows significant diversity. This research utilizes the YOLO architecture, previously trained on several datasets, for fish detection in the environment in Indonesian waters. This dataset consists of various fish species native to Indonesia and was used to retrain the YOLO Pretrain model. The model was evaluated using test data that accurately represents Indonesian water conditions. Empirical findings show that the modified YOLO Pretrain model can accurately recognize these fish in real-time. After utilizing YOLO and Pre-Train with Ultralytics YOLO Version 8.0.196, the results show an accuracy of 92.3% for head detection, 86.9% for tail detection, and an overall detection accuracy of 89.6%. The fish image dataset, consisting of a total of 401 images, is categorized into three subsets: the training dataset, which consists of 255 images; the validation dataset, which includes 66 images; and the testing dataset, which contains 80 images. This research has great potential for application in fisheries monitoring, marine biology research, and marine environmental monitoring. A real-time fish detection system for the Identification and tracking of fish species is carried out by researchers and field workers. The findings of this research provide a valuable contribution to ongoing efforts aimed at conserving marine biodiversity and implementing more sustainable management practices in Indonesia.

show abstract

Detection and counting of root-knot nematodes using YOLO models with mosaic augmentation

Cited by 7 publications

References 25 publications

An Assessment of Human Inspection and Deep Learning for Defect Identification in Floral Wreaths

An Assessment of Human Inspection and Deep Learning for Defect Identification in Floral Wreaths

Comparison Efficacy of VGG16 and VGG19 Insect Classification Models

Exploring YOLOv8 Pretrain for Real-Time Detection of Indonesian Native Fish Species

Contact Info

Product

Resources

About