Project AURIONAI Use-Cases Research & Innovation
vision

TF-ResNet50 Ganoderma detector

Research model for Ganoderma basal stem rot detection in oil palm (TENCON 2025): 84% accuracy, 74% sensitivity for early infection, 86% specificity.

Multimedia UniversityMultimedia UniversityMalaysiaFGV R&D Sdn BhdMalaysia
Multimedia University
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
ReleasedOct 2025
Opennessunknown
Runs onnot in the notes
Statusnot in the notes

Lineage

finetune
ResNet50 (ImageNet) to TF-ResNet50 Ganoderma detector: finetune, high confidenceResNet50 (ImageNet)ResNet50 (ImageNet)TF-ResNet50 Ganoderma detectorTF-ResNet50 Ganoderma dete…Multimedia University, Oct 2025
ResNet50 (ImageNet) is the parent (finetune)high confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.

Industry Use Cases

Agriculture
Ganoderma (basal stem rot) detection

R&D Topics

Plantation, crop and wildlife monitoring visionexemplar

Identity

Developer
Multimedia University, FGV R&D Sdn Bhd
Family
not in the notes
Released
Oct 2025 sourcesnotes
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
CNN Fine-tuned ResNet50 after PCA on UAV hyperspectral imagery; SVM baseline
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
ResNet50 about 25M params (unverified)
Context length
not in the notes
Input
image
Output
not in the notes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
research only
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Sources

  1. Ganoderma Detection in Oil Palm Plantations Using UAV Hyperspectral Imaging and AI - MMU Institutional Repository shdl.mmu.edu.my https://shdl.mmu.edu.my/15767/

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "TF-ResNet50 Ganoderma Detector", https://aurion.semai.id/models/multimedia-university-tf-resnet50-ganoderma/, records of October 2026.