Compression Techniques for Handwritten Digit Recognition

Hassan Alsobaie; Irfan Ahmad

doi:10.1109/3ICT51146.2020.9312005

Compression Techniques for Handwritten Digit Recognition

Hassan Alsobaie
, Irfan Ahmad

Department of Information and Computer Science

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

2 Scopus citations

Abstract

Compressing images before recognition leads to many benefits including efficient computation, compact models, and optimal memory utilization. Several techniques for compression of handwritten digits have been investigated and implemented. This paper presents three compression techniques used in signal processing for compressing handwritten digit images, which are Discrete Cosine Transform (DCT), Discrete Sine Transform (DST) and Wavelet Transform (WT). These techniques are evaluated for their ability to compress the digit images while retaining useful information needed for classifying them, subsequently. Experiments conducted on the publicly available MINST dataset show the effectiveness of the techniques. With the presented techniques, we were able to compress the original images by 48.98%, 71.30%, and 87.24% while leading to reduction in accuracy by only 1.413%, 3.187%, and 7.238%, respectively, on an independent test set.

Original language	English
Title of host publication	2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728196732
DOIs	https://doi.org/10.1109/3ICT51146.2020.9312005
State	Published - 20 Dec 2020

Publication series

Name	2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

Handwritten digit recognition (HWDR)
accuracy
compressing sensing (CS)
machine learning (ML)

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Information Systems

Access to Document

10.1109/3ICT51146.2020.9312005

Cite this

Alsobaie, H., & Ahmad, I. (2020). Compression Techniques for Handwritten Digit Recognition. In 2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020 Article 9312005 (2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/3ICT51146.2020.9312005

Alsobaie, Hassan ; Ahmad, Irfan. / Compression Techniques for Handwritten Digit Recognition. 2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020. Institute of Electrical and Electronics Engineers Inc., 2020. (2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020).

@inproceedings{46a68a0369704b6f83fe99072fa77795,

title = "Compression Techniques for Handwritten Digit Recognition",

abstract = "Compressing images before recognition leads to many benefits including efficient computation, compact models, and optimal memory utilization. Several techniques for compression of handwritten digits have been investigated and implemented. This paper presents three compression techniques used in signal processing for compressing handwritten digit images, which are Discrete Cosine Transform (DCT), Discrete Sine Transform (DST) and Wavelet Transform (WT). These techniques are evaluated for their ability to compress the digit images while retaining useful information needed for classifying them, subsequently. Experiments conducted on the publicly available MINST dataset show the effectiveness of the techniques. With the presented techniques, we were able to compress the original images by 48.98\%, 71.30\%, and 87.24\% while leading to reduction in accuracy by only 1.413\%, 3.187\%, and 7.238\%, respectively, on an independent test set.",

keywords = "Handwritten digit recognition (HWDR), accuracy, compressing sensing (CS), machine learning (ML)",

author = "Hassan Alsobaie and Irfan Ahmad",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.",

year = "2020",

month = dec,

day = "20",

doi = "10.1109/3ICT51146.2020.9312005",

language = "English",

series = "2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020",

address = "United States",

}

Alsobaie, H & Ahmad, I 2020, Compression Techniques for Handwritten Digit Recognition. in 2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020., 9312005, 2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020, Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/3ICT51146.2020.9312005

Compression Techniques for Handwritten Digit Recognition. / Alsobaie, Hassan; Ahmad, Irfan.
2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9312005 (2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020).

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

TY - GEN

T1 - Compression Techniques for Handwritten Digit Recognition

AU - Alsobaie, Hassan

AU - Ahmad, Irfan

PY - 2020/12/20

Y1 - 2020/12/20

N2 - Compressing images before recognition leads to many benefits including efficient computation, compact models, and optimal memory utilization. Several techniques for compression of handwritten digits have been investigated and implemented. This paper presents three compression techniques used in signal processing for compressing handwritten digit images, which are Discrete Cosine Transform (DCT), Discrete Sine Transform (DST) and Wavelet Transform (WT). These techniques are evaluated for their ability to compress the digit images while retaining useful information needed for classifying them, subsequently. Experiments conducted on the publicly available MINST dataset show the effectiveness of the techniques. With the presented techniques, we were able to compress the original images by 48.98%, 71.30%, and 87.24% while leading to reduction in accuracy by only 1.413%, 3.187%, and 7.238%, respectively, on an independent test set.

AB - Compressing images before recognition leads to many benefits including efficient computation, compact models, and optimal memory utilization. Several techniques for compression of handwritten digits have been investigated and implemented. This paper presents three compression techniques used in signal processing for compressing handwritten digit images, which are Discrete Cosine Transform (DCT), Discrete Sine Transform (DST) and Wavelet Transform (WT). These techniques are evaluated for their ability to compress the digit images while retaining useful information needed for classifying them, subsequently. Experiments conducted on the publicly available MINST dataset show the effectiveness of the techniques. With the presented techniques, we were able to compress the original images by 48.98%, 71.30%, and 87.24% while leading to reduction in accuracy by only 1.413%, 3.187%, and 7.238%, respectively, on an independent test set.

KW - Handwritten digit recognition (HWDR)

KW - accuracy

KW - compressing sensing (CS)

KW - machine learning (ML)

UR - https://www.scopus.com/pages/publications/85100234961

U2 - 10.1109/3ICT51146.2020.9312005

DO - 10.1109/3ICT51146.2020.9312005

M3 - Conference contribution

AN - SCOPUS:85100234961

T3 - 2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020

BT - 2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Alsobaie H, Ahmad I. Compression Techniques for Handwritten Digit Recognition. In 2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9312005. (2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020). doi: 10.1109/3ICT51146.2020.9312005

Compression Techniques for Handwritten Digit Recognition

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this