Small but Diverse SEM Image Dataset: Impact of Image Augmentation on the Performance of AlexNet
Small but Diverse SEM Image Dataset: Impact of Image Augmentation on the Performance of AlexNet
Author(s): Khairul Khaizi Mohd Shariff, Noor Ezan Abdullah, Ali Abd Al-Misreb, Aisyah Hartini Jahidin, Megat Syahirul Amin Megat Ali, Ahmad Ihsan Mohd YassinSubject(s): Scientific Life
Published by: UIKTEN - Association for Information Communication Technology Education and Science
Keywords: Scanning electron microscope; small dataset; image augmentation; AlexNet; generalization performance
Summary/Abstract: To this date, scanning electron microscope has produced among the most complex and diverse images at nanoscale resolution. The highly magnified images of backscattered electrons reflected from the surface of samples are non-uniformed, even for the same class of images. The study investigates the impact of having a small but diverse dataset on the performance of AlexNet. A total of 160 samples from EUDAT Collaborative Database Infrastructure is used for the study. Compared to the use of new non-augmented samples to increase the size of dataset, image augmentation has been significantly improved classification performance and generalization ability of the AlexNet.
Journal: TEM Journal
- Issue Year: 12/2023
- Issue No: 2
- Page Range: 883-889
- Page Count: 7
- Language: English
