Integrating evolutionary optimization and graph attention variational autoencoding for wood surface defect recognition
Published online on February 26, 2026
Abstract
Measurement and Control, Ahead of Print.
This study introduces a novel hybrid deep learning framework, CNN–LPMPSO–GATVAE, designed to address the inherent challenges of wood surface defect classification, where high visual variability and complex texture patterns often hinder traditional ...
This study introduces a novel hybrid deep learning framework, CNN–LPMPSO–GATVAE, designed to address the inherent challenges of wood surface defect classification, where high visual variability and complex texture patterns often hinder traditional ...