Unsupervised Screening of Money Plant Leaf Health Anomalies Using a Convolutional Autoencoder
A computer vision study investigating convolutional autoencoders for unsupervised screening of visual health anomalies in money plant leaves.
About the project
This research investigates the use of a convolutional autoencoder for unsupervised screening of health anomalies in money plant leaves. It connects computer vision with plant health assessment, exploring how leaf imagery can support the identification of unusual visual patterns.
The study focuses on an unsupervised approach to anomaly screening. Its research direction examines how learned image representations can help identify variations in leaf appearance that warrant further assessment.
The work brings together image analysis, unsupervised machine learning, and plant health monitoring. It explores a practical application of artificial intelligence in examining visual information from plants.
The paper was submitted to ICEEICT 2027 under Paper ID 35.