Font creation using class discriminative deep convolutional generative adversarial networks
2018 (English)In: Proceedings - 4th Asian Conference on Pattern Recognition, ACPR 2017, Institute of Electrical and Electronics Engineers Inc. , 2018, p. 238-243Conference paper, Published paper (Refereed)
Abstract [en]
In this research, we attempt to generate fonts automatically using a modification of a Deep Convolutional Generative Adversarial Network (DCGAN) by introducing class consideration. DCGANs are the application of generative adversarial networks (GAN) which make use of convolutional and deconvolutional layers to generate data through adversarial detection. The conventional GAN is comprised of two neural networks that work in series. Specifically, it approaches an unsupervised method of data generation with the use of a generative network whose output is fed into a second discriminative network. While DCGANs have been successful on natural images, we show its limited ability on font generation due to the high variation of fonts combined with the need of rigid structures of characters. We propose a class discriminative DCGAN which uses a classification network to work alongside the discriminative network to refine the generative network. This results of our experiment shows a dramatic improvement over the conventional DCGAN.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2018. p. 238-243
Keywords [en]
Classification, DCGAN, Font Generation, Generative Adversarial Network, Generative Model, Text Generation, Classification (of information), Convolution, Text processing, Adversarial networks, Text generations, Pattern recognition
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:kth:diva-246994DOI: 10.1109/ACPR.2017.99ISI: 000455581900040Scopus ID: 2-s2.0-85060513937OAI: oai:DiVA.org:kth-246994DiVA, id: diva2:1330768
Conference
4th Asian Conference on Pattern Recognition, ACPR 2017, 26 November 2017 through 29 November 2017
Note
Part of proceedings: ISBN 978-1-5386-3354-0
QC 20190626
2019-06-262019-06-262022-12-20Bibliographically approved