An Autoencoder Based ASCII Art Generator

Masaomi Kimura; Mohammad Iqbal; Imam Mukhlash

doi:10.1145/3591569.3591587

An Autoencoder Based ASCII Art Generator

Masaomi Kimura, Mohammad Iqbal, Imam Mukhlash

Laboratory of Machine Learning and Big Data

Shibaura Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

ASCII art is a way to represent an image with character shapes. It is common to carry ASCII art instead of displaying image files on Internet bulletin boards. Multibyte encodings contain various characters that are useful to shape an image. The essential idea required to get ASCII art is to approximate color distribution at the portion of a target image to a character shape. In this study, we make a machine learning model that learns the shapes of characters in a multibyte encoding to convert a partial image of a target image to a font image.

Original language	English
Title of host publication	ICIIT 2023 - Proceedings of 2023 8th International Conference on Intelligent Information Technology
Publisher	Association for Computing Machinery
Pages	106-111
Number of pages	6
ISBN (Electronic)	9781450399616
DOIs	https://doi.org/10.1145/3591569.3591587
Publication status	Published - 24 Feb 2023
Event	8th International Conference on Intelligent Information Technology, ICIIT 2023 - Hybrid, Da Nang, Viet Nam Duration: 24 Feb 2023 → 26 Feb 2023

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	8th International Conference on Intelligent Information Technology, ICIIT 2023
Country/Territory	Viet Nam
City	Hybrid, Da Nang
Period	24/02/23 → 26/02/23

Keywords

ASCII art synthesis
K-nearest neighborhood
autoencoder
deep learning

Access to Document

10.1145/3591569.3591587

Cite this

@inproceedings{bc1af6b2cd87471da79e2809830fbbf0,

title = "An Autoencoder Based ASCII Art Generator",

abstract = "ASCII art is a way to represent an image with character shapes. It is common to carry ASCII art instead of displaying image files on Internet bulletin boards. Multibyte encodings contain various characters that are useful to shape an image. The essential idea required to get ASCII art is to approximate color distribution at the portion of a target image to a character shape. In this study, we make a machine learning model that learns the shapes of characters in a multibyte encoding to convert a partial image of a target image to a font image.",

keywords = "ASCII art synthesis, K-nearest neighborhood, autoencoder, deep learning",

author = "Masaomi Kimura and Mohammad Iqbal and Imam Mukhlash",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 8th International Conference on Intelligent Information Technology, ICIIT 2023 ; Conference date: 24-02-2023 Through 26-02-2023",

year = "2023",

month = feb,

day = "24",

doi = "10.1145/3591569.3591587",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "106--111",

booktitle = "ICIIT 2023 - Proceedings of 2023 8th International Conference on Intelligent Information Technology",

}

Kimura, M, Iqbal, M & Mukhlash, I 2023, An Autoencoder Based ASCII Art Generator. in ICIIT 2023 - Proceedings of 2023 8th International Conference on Intelligent Information Technology. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 106-111, 8th International Conference on Intelligent Information Technology, ICIIT 2023, Hybrid, Da Nang, Viet Nam, 24/02/23. https://doi.org/10.1145/3591569.3591587

An Autoencoder Based ASCII Art Generator. / Kimura, Masaomi; Iqbal, Mohammad ; Mukhlash, Imam.
ICIIT 2023 - Proceedings of 2023 8th International Conference on Intelligent Information Technology. Association for Computing Machinery, 2023. p. 106-111 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An Autoencoder Based ASCII Art Generator

AU - Kimura, Masaomi

AU - Iqbal, Mohammad

AU - Mukhlash, Imam

PY - 2023/2/24

Y1 - 2023/2/24

N2 - ASCII art is a way to represent an image with character shapes. It is common to carry ASCII art instead of displaying image files on Internet bulletin boards. Multibyte encodings contain various characters that are useful to shape an image. The essential idea required to get ASCII art is to approximate color distribution at the portion of a target image to a character shape. In this study, we make a machine learning model that learns the shapes of characters in a multibyte encoding to convert a partial image of a target image to a font image.

AB - ASCII art is a way to represent an image with character shapes. It is common to carry ASCII art instead of displaying image files on Internet bulletin boards. Multibyte encodings contain various characters that are useful to shape an image. The essential idea required to get ASCII art is to approximate color distribution at the portion of a target image to a character shape. In this study, we make a machine learning model that learns the shapes of characters in a multibyte encoding to convert a partial image of a target image to a font image.

KW - ASCII art synthesis

KW - K-nearest neighborhood

KW - autoencoder

KW - deep learning

UR - http://www.scopus.com/inward/record.url?scp=85167796131&partnerID=8YFLogxK

U2 - 10.1145/3591569.3591587

DO - 10.1145/3591569.3591587

M3 - Conference contribution

AN - SCOPUS:85167796131

T3 - ACM International Conference Proceeding Series

SP - 106

EP - 111

BT - ICIIT 2023 - Proceedings of 2023 8th International Conference on Intelligent Information Technology

PB - Association for Computing Machinery

T2 - 8th International Conference on Intelligent Information Technology, ICIIT 2023

Y2 - 24 February 2023 through 26 February 2023

ER -

An Autoencoder Based ASCII Art Generator

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this