eCite Digital Repository

Generating training images with different angles by GAN for improving grocery product image recognition

Citation

Wei, Y and Xu, S and Kang, B and Hoque, S, Generating training images with different angles by GAN for improving grocery product image recognition, Neurocomputing, 488, (1) pp. 694-705. ISSN 0925-2312 (2021) [Refereed Article]

Copyright Statement

2021 Elsevier B.V. All rights reserved.

DOI: doi:10.1016/j.neucom.2021.11.080

Abstract

Image recognition based on deep learning methods has gained remarkable achievements by feeding with abundant training data. Unfortunately, collecting a tremendous amount of annotated images is time-consuming and expensive, especially in grocery product recognition tasks. It is challenging to recognise grocery products accurately when the deep learning model is trained with insufficient data. This paper proposes multi-angle Generative Adversarial Networks (MAGAN), which can generate realistic training images with different angles for data augmentation. Mutual information is employed in the novel GAN to achieve the learning of angles in an unsupervised manner. This paper aims to create training images containing grocery products from different angles, thus improving grocery product recognition accuracy. We first enlarge the fruit dataset by using MAGAN and the state-of-the-art GAN variants. Then, we compare the top-1 accuracy results from CNN classifiers trained with different data augmentation methods. Finally, our experiments demonstrate that the MAGAN exceeds the existing GANs for grocery product recognition tasks, obtaining a significant increase in the accuracy.

Item Details

Item Type:Refereed Article
Keywords:grocery product recognition, data augmentation, generative adversarial network (GAN), convolutional neural network (CNN)
Research Division:Information and Computing Sciences
Research Group:Artificial intelligence
Research Field:Artificial intelligence not elsewhere classified
Objective Division:Information and Communication Services
Objective Group:Information systems, technologies and services
Objective Field:Artificial intelligence
UTAS Author:Wei, Y (Dr Yuchen Wei)
UTAS Author:Xu, S (Dr Shuxiang Xu)
UTAS Author:Kang, B (Professor Byeong Kang)
UTAS Author:Hoque, S (Mrs Sabera Hoque)
ID Code:150826
Year Published:2021
Deposited By:Information and Communication Technology
Deposited On:2022-07-01
Last Modified:2022-09-07
Downloads:0

Repository Staff Only: item control page