Influence of images generated by CGAN on the performance of image classification based on CNN

Yushu Hu

doi:10.1117/12.2669802

28 March 2023 Influence of images generated by CGAN on the performance of image classification based on CNN

Yushu Hu

Proceedings Volume 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022); 1256617 (2023) https://doi.org/10.1117/12.2669802
Event: Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 2022, Chongqing, China

Abstract

Conditional Generative adversarial net (CGAN) can generate data according to the given constraints. Convolutional neural network (CNN) is a neural network that can be used to process images providing learnable parameters for efficient classification. However, there are few researches on whether it is more beneficial for CNN to classify from the images generated by GANs as the training set in the past studies. To solve the issue, this paper compares the training effect of CNN classification of Handwritten-number images using real images, images generated entirely by CGAN that are results through CGAN’s trained from real handwritten-number images, and images mixed with them as training data sets. The dataset used is a famous dataset called MNIST which consists of 10 categories. Based on it, the corresponding experiments are carried out and the final experimental result indicated that the images generated by CGAN can further improve the performance of the CNN.

Citation Download Citation

Yushu Hu "Influence of images generated by CGAN on the performance of image classification based on CNN", Proc. SPIE 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 1256617 (28 March 2023); https://doi.org/10.1117/12.2669802

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available