แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Nathaphon Boonnam. Comparative analysis of deep learning models for nutrition table detection in food product images. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2025.
Comparative analysis of deep learning models for nutrition table detection in food product images
Name: Mintira Sae-Eia
Organization :
Prince of Songkla University. Faculty of Science and Industrial Technology
Email :
mintira.eia@gmail.com
Name: Nathaphon Boonnam
Organization :
Prince of Songkla University. Faculty of Science and Industrial Technology
Email :
nathaphon.b@psu.ac.th
keyword:
Object detection
LCSH:
Nutrition
-- Information services
LCSH:
Image processing
Abstract:
Nutrition tables on food product packaging are vital for consumers, nutritionists, and health researchers, but extracting this information from images poses challenges due to varying formats, orientations, and backgrounds. This research evaluates the effectiveness of deep learning architectures for detecting nutrition tables, laying the groundwork for a system to extract nutrient information. Among YOLOv5s, YOLOv8n, and DETR models, YOLOv8n excelled in Recall (1.00) and F1-score (≈ 0.9985), while YOLOv5s achieved the highest Precision of 1.00. However, DETR outperformed the others in bounding box localization accuracy (≈ 0.9587) and successfully detected all three nutrition labels in real-world testing without false detections. All models struggled with ingredient labels that had similar structures. These findings indicate that DETR may offer the most accurate and comprehensive detection across varied real-world images.
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2025
Modified:
2026-01-08
Issued:
2026-01-08
บทความ/Article
application/pdf
BibliograpyCitation :
In IEEE Thailand Section. Antennas and Propagation/Electron Devices/Microwave Theory and Techniques Joint Chapter, Electrical Engineering/Electronics, Computer, Telecommunications, and Information Technology Association, and King Mongkut's University of Technology North Bangkok. The 5th Research, Invention and Innovation Congress (RI2C 2025) (pp.260-267). Bangkok : IEEE Thailand Section
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
-0.966634 วินาที
Mintira Sae-Eia
| Title | Contributor | Type |
|---|---|---|
| Comparative analysis of deep learning models for nutrition table detection in food product images
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Mintira Sae-Eia;Nathaphon Boonnam | บทความ/Article |
Nathaphon Boonnam
| Title | Contributor | Type |
|---|---|---|
| Efficiency measurement of energy yield from solar photovoltaic cell with embedded system of alternative clamp meter
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Orachon Lanteng;Nathaphon Boonnam | บทความ/Article | |
| Osteoporosis prognosis through machine learning analysis of x-ray films
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Jiranuwat Massatith;Nathaphon Boonnam;Rattanasak Hama | บทความ/Article | |
| Optimizing machine learning approaches for personalized food recommendation systems in non-communicable disease management
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Surat Lawdi;Nathaphon Boonnam | บทความ/Article | |
| Comparative analysis of deep learning models for nutrition table detection in food product images
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Mintira Sae-Eia;Nathaphon Boonnam | บทความ/Article |