Work

Unsupervised and few-shot segmentation in photovoltaic electroluminescence images for defect detection via a novel enhanced iterative autoencoder with simple implementation

Year: 2025

Type: article

Abstract: PVEL images are particularly valuable for ML-based automated fault detection. A novel EI-AE incorporates an iterative mechanism into the conventional AE framework, providing simple, effective unsupervised pixel-level defect segmentation.

Source: Energy & Environmental Science

DOI: 10.1039/d5ee05042a

Authors: Ye Lin, Pingyang Sun, Rongcheng Wu, Shu Geng, Man Lung Yiu, Zhidong Li, Fang Chen, Yu Gao, Mingzhe Wang, Kaiwen Sun, Xiaojing Hao

Institutions: University of Technology Sydney, Hong Kong Polytechnic University, Charles Darwin University, UNSW Sydney, Xidian University

Language: English

Topic: Industrial Vision Systems and Defect Detection

Subfield: Industrial and Manufacturing Engineering

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure

Open Access status: hybrid

Funders: Australian Government, National Natural Science Foundation of China, China Postdoctoral Science Foundation, Fundamental Research Funds for the Central Universities

Awards: G2238053653, G6237293519, G6744244746

OpenAlex ID: W7106699566

FWCI: 0.507

Cites: 39

Cited by: 1

Related to: