Developing a Non-Destructive Chlorophyll Content Estimation in Mungbean Leaves Using Deep Learning

This study develops a deep learning-based tool for non-destructive chlorophyll content estimation in mungbean leaves, designed to supplement traditional measurement methods. Convolutional Neural Networks extract relevant leaf features from digital images, enhanced by image processing and data augmen...

Full description

Saved in:
Bibliographic Details
Published inProceedings (International Conference on Computer and Automation Engineering. Online) pp. 188 - 191
Main Authors Ebron, Jonalyn G., Alimbuyog, Maryam C., Amoranto, Andro Cecilio A., Libutan, David V., Requintina, Marvin Allen N.
Format Conference Proceeding
LanguageEnglish
Published IEEE 20.03.2025
Subjects
Accuracy
Chlorophyll
Classification
Deep learning
Estimation
Feature extraction
Measurement techniques
Mobile applications
Pipelines
Precision agriculture
Real-time systems
Segmentation
Online AccessGet full text
ISSN2154-4360
DOI10.1109/ICCAE64891.2025.10980582

Cover

More Information
Summary:This study develops a deep learning-based tool for non-destructive chlorophyll content estimation in mungbean leaves, designed to supplement traditional measurement methods. Convolutional Neural Networks extract relevant leaf features from digital images, enhanced by image processing and data augmentation. The model achieved a 92% validation accuracy and a 0.15 mg/cm 2 mean absolute error, demonstrating its potential for precise estimation. A mobile application facilitates real-time, onsite assessment, offering a practical alternative to resourceintensive laboratory techniques. Future research will explore advanced deep learning architectures and refine measurement techniques to improve accuracy and enable widespread adoption in precision agriculture, ultimately providing a complementary approach to traditional chlorophyll analysis
ISSN:2154-4360
DOI:10.1109/ICCAE64891.2025.10980582