Multi-task deep learning for automated tobacco leaf grading in a controlled environment

Simple item page
creativework.keywordsair-cured Burley tobacco, image preprocessing, multi-task deep learning, tobacco leaf grading
dc.contributor.authorMarzan, Charlie S.
dc.contributor.authorRuiz, Conrado Jr.
dc.contributor.authorAran, Oya
dc.date.accessioned2026-07-20T06:08:05Z
dc.date.available2026-07-20T06:08:05Z
dc.date.issued2026
dc.description.abstractGrading tobacco leaves is crucial for ensuring fair pricing and quality control, however, the process is still largely carried out manually, resulting in a slow, subjective, and often inconsistent outcome. In this work, we present a multi-task deep learning approach designed to automate the grading of air-cured Burley tobacco leaves in controlled settings. The model is constructed with shared convolutional layers and separate task-specific branches, allowing it to predict stalk group, quality, and color at the same time, in line with the hierarchical grading system. To improve consistency, images were preprocessed using coin-based size normalization, rotation alignment, and segmentation. In our experiments, the multi-task model with EfficientNetB0 achieved an accuracy of 94.82% and significantly outperformed the multi-class and single-task baselines, while reducing both training time and inference delay. These findings suggest that multi-task learning can be a valuable and robust method for automated tobacco grading, showing gains in accuracy, speed, and scalability compared to other algorithms.
dc.identifier.citationMarzan, C. S., Ruiz, C. Jr., & Aran, O. (2026). Multi-task deep learning for automated tobacco leaf grading in a controlled environment. International Journal of Computer Theory and Engineering, 18(2), 99-109. DOI: 10.7763/IJCTE.2026.V18.1392
dc.identifier.issn1793-8201
dc.identifier.issne2972-4511
dc.identifier.urihttps://lakasa.dmmmsu.edu.ph/handle/123456789/2229
dc.language.isoen_US
dc.publisherInternational Journal of Computer Theory and Engineering
dc.relation.urihttps://www.ijcte.org/show-153-1721-1.html
dc.rights.licenseCC BY 4.0
dc.sdgSDG 2
dc.sdgSDG 9
dc.subjectTobacco leaf grading
dc.subjectDeep learning
dc.subjectMulti-task learning
dc.subjectComputer vision
dc.subjectImage processing
dc.subjectImage processing
dc.subjectAgricultural automation
dc.subjectMachine learning in agriculture
dc.subjectBurley tobacco
dc.subjectArtificial intelligence
dc.subjectCrop quality assessment
dc.subject.ddcComputer vision
dc.subject.ddcArtificial intelligence
dc.subject.ddcMachine learning
dc.subject.lcshTobacco industry--Quality control
dc.subject.lcshTobacco leaves--Classification
dc.subject.lcshComputer vision
dc.subject.lcshDeep learning (Artificial intelligence)
dc.subject.lcshImage processing--Digital techniques
dc.subject.lcshPrecision agriculture
dc.subject.lcshArtificial intelligence
dc.titleMulti-task deep learning for automated tobacco leaf grading in a controlled environment
dc.typeArticle
local.subject.scientificnameNicotiana tabacum L. (Burley tobacco)
oaire.citation.endPage109
oaire.citation.issue2
oaire.citation.startPage99
oaire.citation.volume18
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
PUB-JAPE-2026-MarzanCS-FT
Size:
13.31 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Journal articles published externally