Saw-Mark Defect Detection in Heterogeneous Solar Wafer Images using GAN-based Training Samples Generation and CNN Classification

Du-Ming Tsai, Morris S. K. Fan, Yi-Quan Huang, Wei-Yao Chiu

2019

Abstract

This paper presents a machine vision-based scheme to automatically detect saw-mark defects in solar wafer surfaces. A saw-mark defect is a severe flaw when cutting a silicon ingot into wafers. A multicrystalline solar wafer surface presents random shapes, sizes and orientations of crystal grains in the surface and, thus, results in a heterogeneous texture. It makes the automatic visual inspection task extremely difficult. The deep learning technique is an ideal choice to tackle the problem, but it requires a huge amount of positive (defect-free) and negative (defective) samples for the training. The negative samples are generally not sufficient enough in a manufacturing process. We thus apply a GAN-based model to generate the defective samples for training, and then use the true defect-free samples and the synthesized defective samples to train a CNN model. It solves the imbalanced data arising in manufacturing inspection. The preliminary experiment has shown promising results of the proposed method for detecting various saw-mark defects including black line, white line, and impurity in multicrystalline solar wafers.

Download


Paper Citation


in Harvard Style

Tsai D., Fan M., Huang Y. and Chiu W. (2019). Saw-Mark Defect Detection in Heterogeneous Solar Wafer Images using GAN-based Training Samples Generation and CNN Classification. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 234-240. DOI: 10.5220/0007306602340240


in Bibtex Style

@conference{visapp19,
author={Du-Ming Tsai and Morris S. K. Fan and Yi-Quan Huang and Wei-Yao Chiu},
title={Saw-Mark Defect Detection in Heterogeneous Solar Wafer Images using GAN-based Training Samples Generation and CNN Classification},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={234-240},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007306602340240},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Saw-Mark Defect Detection in Heterogeneous Solar Wafer Images using GAN-based Training Samples Generation and CNN Classification
SN - 978-989-758-354-4
AU - Tsai D.
AU - Fan M.
AU - Huang Y.
AU - Chiu W.
PY - 2019
SP - 234
EP - 240
DO - 10.5220/0007306602340240
PB - SciTePress