Image Pattern Classification Using MFCC and HMM

Zahra Shah; Minsu Kim; Gil Jin Jang

doi:10.1109/ICCE-ASIA.2018.8552112

Image Pattern Classification Using MFCC and HMM

Zahra Shah, Minsu Kim, Gil Jin Jang

School of Electronics Engineering

Kyungpook National University

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

Abstract

We propose a novel method for recognizing temporally or spatially varying patterns using MFCC (mel-frequency ceptral coefficient) and HMM (hidden Markov model). MFCC and HMM have been adopted as de factostandard for speech recognition. It is very useful in modeling time-domain signals with temporally varying characteristics. Most images have characteristical patterns, so HMM is expected to model them very efficiently. We suggest efficient pattern classification algorithm with MFCC and HMM, and showed its improved performance in MNISTand fashionMNIST databases.

Original language	English
Title of host publication	2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538658079
DOIs	https://doi.org/10.1109/ICCE-ASIA.2018.8552112
State	Published - 28 Nov 2018
Event	2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018 - JeJu, Korea, Republic of Duration: 24 Jun 2018 → 26 Jun 2018

Publication series

Name	2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018

Conference

Conference	2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018
Country/Territory	Korea, Republic of
City	JeJu
Period	24/06/18 → 26/06/18

Keywords

Discrete Cosine Transform (DCT)
Hidden Markov Models (HMMs)
Mel-Frequency Cepstral Coefficients (MFCC)
Mixed National Institute of Standards and Technology (MNIST)

Access to Document

10.1109/ICCE-ASIA.2018.8552112

Cite this

Shah, Z., Kim, M., & Jang, G. J. (2018). Image Pattern Classification Using MFCC and HMM. In 2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018 Article 8552112 (2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-ASIA.2018.8552112

@inproceedings{7e0cf8d7ce674616a6b7c1d0ba6ef5ab,

title = "Image Pattern Classification Using MFCC and HMM",

abstract = "We propose a novel method for recognizing temporally or spatially varying patterns using MFCC (mel-frequency ceptral coefficient) and HMM (hidden Markov model). MFCC and HMM have been adopted as de factostandard for speech recognition. It is very useful in modeling time-domain signals with temporally varying characteristics. Most images have characteristical patterns, so HMM is expected to model them very efficiently. We suggest efficient pattern classification algorithm with MFCC and HMM, and showed its improved performance in MNISTand fashionMNIST databases.",

keywords = "Discrete Cosine Transform (DCT), Hidden Markov Models (HMMs), Mel-Frequency Cepstral Coefficients (MFCC), Mixed National Institute of Standards and Technology (MNIST)",

author = "Zahra Shah and Minsu Kim and Jang, {Gil Jin}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018 ; Conference date: 24-06-2018 Through 26-06-2018",

year = "2018",

month = nov,

day = "28",

doi = "10.1109/ICCE-ASIA.2018.8552112",

language = "English",

series = "2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018",

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

booktitle = "2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018",

address = "United States",

}

Shah, Z, Kim, M & Jang, GJ 2018, Image Pattern Classification Using MFCC and HMM. in 2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018., 8552112, 2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018, Institute of Electrical and Electronics Engineers Inc., 2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018, JeJu, Korea, Republic of, 24/06/18. https://doi.org/10.1109/ICCE-ASIA.2018.8552112

Image Pattern Classification Using MFCC and HMM. / Shah, Zahra; Kim, Minsu; Jang, Gil Jin.
2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 8552112 (2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018).

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

TY - GEN

T1 - Image Pattern Classification Using MFCC and HMM

AU - Shah, Zahra

AU - Kim, Minsu

AU - Jang, Gil Jin

PY - 2018/11/28

Y1 - 2018/11/28

N2 - We propose a novel method for recognizing temporally or spatially varying patterns using MFCC (mel-frequency ceptral coefficient) and HMM (hidden Markov model). MFCC and HMM have been adopted as de factostandard for speech recognition. It is very useful in modeling time-domain signals with temporally varying characteristics. Most images have characteristical patterns, so HMM is expected to model them very efficiently. We suggest efficient pattern classification algorithm with MFCC and HMM, and showed its improved performance in MNISTand fashionMNIST databases.

AB - We propose a novel method for recognizing temporally or spatially varying patterns using MFCC (mel-frequency ceptral coefficient) and HMM (hidden Markov model). MFCC and HMM have been adopted as de factostandard for speech recognition. It is very useful in modeling time-domain signals with temporally varying characteristics. Most images have characteristical patterns, so HMM is expected to model them very efficiently. We suggest efficient pattern classification algorithm with MFCC and HMM, and showed its improved performance in MNISTand fashionMNIST databases.

KW - Discrete Cosine Transform (DCT)

KW - Hidden Markov Models (HMMs)

KW - Mel-Frequency Cepstral Coefficients (MFCC)

KW - Mixed National Institute of Standards and Technology (MNIST)

UR - http://www.scopus.com/inward/record.url?scp=85060016910&partnerID=8YFLogxK

U2 - 10.1109/ICCE-ASIA.2018.8552112

DO - 10.1109/ICCE-ASIA.2018.8552112

M3 - Conference contribution

AN - SCOPUS:85060016910

T3 - 2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018

BT - 2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE International Conference on Consumer Electronics - Asia, ICCE-Asia 2018

Y2 - 24 June 2018 through 26 June 2018

ER -

Image Pattern Classification Using MFCC and HMM

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this