TY - GEN
T1 - Food Detection and Recognition with Deep Learning: A Comparative Study
AU - Tan, Siao Wah
AU - Lee, Chin Poo
AU - Lim, Kian Ming
AU - Lim, Jit Yan
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Food detection and recognition involves the use of computer vision and machine learning techniques to identify and classify food items in images or videos. It has numerous applications, such as dietary tracking, nutrition analysis, and inventory management. This research paper presents a comparative study of six deep learning models (SSD (VGG-16), Faster-RCNN (Resnet-50), Faster-RCNN (Mobilenet-V3), Faster-RCNN (Mobilenet-V3-320), RetinaNet (Resnet-50), and YOLOv5) for food detection and recognition. The models' performance is evaluated using three publicly available datasets: School Lunch Dataset, UEC FOOD 100, and UEC FOOD 256. Notably, Faster R-CNN (Mobilenet-V3) achieved mAP of 0.931 in the School Lunch Dataset, while YOLOv5 achieved 0.774 and 0.701 mAP in the UEC FOOD 100 and UEC FOOD 256 Datasets, respectively. YOLOv5 demonstrates comparable results to Faster R-CNN but with a smaller input image size and a larger batch size in food detection.
AB - Food detection and recognition involves the use of computer vision and machine learning techniques to identify and classify food items in images or videos. It has numerous applications, such as dietary tracking, nutrition analysis, and inventory management. This research paper presents a comparative study of six deep learning models (SSD (VGG-16), Faster-RCNN (Resnet-50), Faster-RCNN (Mobilenet-V3), Faster-RCNN (Mobilenet-V3-320), RetinaNet (Resnet-50), and YOLOv5) for food detection and recognition. The models' performance is evaluated using three publicly available datasets: School Lunch Dataset, UEC FOOD 100, and UEC FOOD 256. Notably, Faster R-CNN (Mobilenet-V3) achieved mAP of 0.931 in the School Lunch Dataset, while YOLOv5 achieved 0.774 and 0.701 mAP in the UEC FOOD 100 and UEC FOOD 256 Datasets, respectively. YOLOv5 demonstrates comparable results to Faster R-CNN but with a smaller input image size and a larger batch size in food detection.
KW - Faster Region-Based Convolutional Neural Networks (Faster R-CNN)
KW - Food detection
KW - Object detection
KW - YOLOv5
UR - http://www.scopus.com/inward/record.url?scp=85174394864&partnerID=8YFLogxK
U2 - 10.1109/ICoICT58202.2023.10262523
DO - 10.1109/ICoICT58202.2023.10262523
M3 - Conference Proceeding
AN - SCOPUS:85174394864
T3 - 2023 11th International Conference on Information and Communication Technology, ICoICT 2023
SP - 283
EP - 288
BT - 2023 11th International Conference on Information and Communication Technology, ICoICT 2023
T2 - 11th International Conference on Information and Communication Technology, ICoICT 2023
Y2 - 23 August 2023 through 24 August 2023
ER -