Convolutional Neural Network for Object Detection in Garlic Root Cutting Equipment

Traditional manual garlic root cutting is inefficient and can cause food safety problems. To develop food processing equipment, a novel and accurate object detection method for garlic using deep learning—a convolutional neural network—is proposed in this study. The you-only-look-once (YOLO) algorith...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Foods Ročník 11; číslo 15; s. 2197
Hlavní autoři: Yang, Ke, Peng, Baoliang, Gu, Fengwei, Zhang, Yanhua, Wang, Shenying, Yu, Zhaoyang, Hu, Zhichao
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 24.07.2022
MDPI
Témata:
Accuracy
Algorithms
Artificial neural networks
bulbs
Computer vision
convolutional neural network
Cutting equipment
Deep learning
Efficiency
Food processing
food research
Food safety
food safety control
Food science
Garlic
garlic root cutting
Harvest
Machine learning
Neural networks
object detection
Object recognition
Physiological aspects
Sensors
standard deviation
Transfer learning
YOLO
United Kingdom
ISSN:2304-8158, 2304-8158
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Traditional manual garlic root cutting is inefficient and can cause food safety problems. To develop food processing equipment, a novel and accurate object detection method for garlic using deep learning—a convolutional neural network—is proposed in this study. The you-only-look-once (YOLO) algorithm, which is based on lightweight and transfer learning, is the most advanced computer vision method for single large object detection. To detect the bulb, the YOLOv2 model was modified using an inverted residual module and residual structure. The modified model was trained based on images of bulbs with varied brightness, surface attachment, and shape, which enabled sufficient learning of the detector. The optimum minibatches and epochs were obtained by comparing the test results of different training parameters. Research shows that IRM-YOLOv2 is superior to the SqueezeNet, ShuffleNet, and YOLOv2 models of classical neural networks, as well as the YOLOv3 and YOLOv4 algorithm models. The confidence score, average accuracy, deviation, standard deviation, detection time, and storage space of IRM-YOLOv2 were 0.98228, 99.2%, 2.819 pixels, 4.153, 0.0356 s, and 24.2 MB, respectively. In addition, this study provides an important reference for the application of the YOLO algorithm in food research.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2304-8158
2304-8158
DOI:10.3390/foods11152197