SIFT based approach on Bangla sign language recognition

Farhad Yasir; P. W.C. Prasad; Abeer Alsadoon; Amr Elchouemi

doi:10.1109/IWCIA.2015.7449458

SIFT based approach on Bangla sign language recognition

Farhad Yasir
, P. W.C. Prasad
, Abeer Alsadoon
, Amr Elchouemi

Charles Sturt University
Walden University

Research output: Book chapter/Published conference paper › Conference paper › peer-review

61 Citations (Scopus)

Abstract

This paper presents a SIFT-based geometrically computational approach to vigorously recognize Bangla sign language (BdSL). Gaussian distribution and grayscaling techniques are applied for image processing and normalizing the sign image. After this pre-processing, features are extracted from the sign image by implementing scale invariant feature transform. Acquiring all descriptors from the sign image, k-means clustering is executed on all the descriptors which are previously computed by SIFT. Based on the sample training set, each of the cluster denotes as a visual word. Considering the histograms of the clustering descriptors, Bag of words model is introduced on this hybrid approach which develops a set of visual vocabulary. Finally for each of sign word, a binary linear support vector machine (SVM) classifier is trained with a respective training data set. Considering these binary classifiers, we obtained a respective recognition rate on both Bangla signs of expressions and alphabets.

Original language	English
Title of host publication	2015 IEEE 8th international workshop on computational intelligence and applications (IWCIA 2015)
Subtitle of host publication	Proceedings
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	35-39
Number of pages	5
ISBN (Electronic)	9781479998869
ISBN (Print)	9781479988426
DOIs	https://doi.org/10.1109/IWCIA.2015.7449458
Publication status	Published - 11 Apr 2016
Event	8th IEEE International Workshop on Computational Intelligence and Applications: IEEE IWCIA 2015 - Hiroshima City University, Hiroshima, Japan Duration: 06 Nov 2015 → 07 Nov 2015 http://www.smc-hiroshima.info.hiroshima-cu.ac.jp/events/iwcia/2015/ (Conference website)

Conference

Conference	8th IEEE International Workshop on Computational Intelligence and Applications
Country/Territory	Japan
City	Hiroshima
Period	06/11/15 → 07/11/15
Other	The main goal of IWCIA2015 is to provide the scientific researchers and engineers with a vehicle where innovative technologies of computational intelligence could be discussed.
Internet address	http://www.smc-hiroshima.info.hiroshima-cu.ac.jp/events/iwcia/2015/ (Conference website)

Access to Document

10.1109/IWCIA.2015.7449458

Cite this

@inproceedings{e481e05a9b084310b0ac5cd65534d438,

title = "SIFT based approach on Bangla sign language recognition",

abstract = "This paper presents a SIFT-based geometrically computational approach to vigorously recognize Bangla sign language (BdSL). Gaussian distribution and grayscaling techniques are applied for image processing and normalizing the sign image. After this pre-processing, features are extracted from the sign image by implementing scale invariant feature transform. Acquiring all descriptors from the sign image, k-means clustering is executed on all the descriptors which are previously computed by SIFT. Based on the sample training set, each of the cluster denotes as a visual word. Considering the histograms of the clustering descriptors, Bag of words model is introduced on this hybrid approach which develops a set of visual vocabulary. Finally for each of sign word, a binary linear support vector machine (SVM) classifier is trained with a respective training data set. Considering these binary classifiers, we obtained a respective recognition rate on both Bangla signs of expressions and alphabets.",

keywords = "Bag of word, Bangla Sign Language Recognition, Scale invariant feature transform, Support vector machine",

author = "Farhad Yasir and Prasad, \{P. W.C.\} and Abeer Alsadoon and Amr Elchouemi",

note = "Includes bibliographical references.; 8th IEEE International Workshop on Computational Intelligence and Applications : IEEE IWCIA 2015 ; Conference date: 06-11-2015 Through 07-11-2015",

year = "2016",

month = apr,

day = "11",

doi = "10.1109/IWCIA.2015.7449458",

language = "English",

isbn = "9781479988426",

pages = "35--39",

booktitle = "2015 IEEE 8th international workshop on computational intelligence and applications (IWCIA 2015)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

url = "http://www.smc-hiroshima.info.hiroshima-cu.ac.jp/events/iwcia/2015/",

}

Yasir, F, Prasad, PWC, Alsadoon, A & Elchouemi, A 2016, SIFT based approach on Bangla sign language recognition. in 2015 IEEE 8th international workshop on computational intelligence and applications (IWCIA 2015): Proceedings., 7449458, IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 35-39, 8th IEEE International Workshop on Computational Intelligence and Applications, Hiroshima, Japan, 06/11/15. https://doi.org/10.1109/IWCIA.2015.7449458

SIFT based approach on Bangla sign language recognition. / Yasir, Farhad; Prasad, P. W.C.; Alsadoon, Abeer et al.
2015 IEEE 8th international workshop on computational intelligence and applications (IWCIA 2015): Proceedings. United States: IEEE, Institute of Electrical and Electronics Engineers, 2016. p. 35-39 7449458.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - SIFT based approach on Bangla sign language recognition

AU - Yasir, Farhad

AU - Prasad, P. W.C.

AU - Alsadoon, Abeer

AU - Elchouemi, Amr

N1 - Includes bibliographical references.

PY - 2016/4/11

Y1 - 2016/4/11

N2 - This paper presents a SIFT-based geometrically computational approach to vigorously recognize Bangla sign language (BdSL). Gaussian distribution and grayscaling techniques are applied for image processing and normalizing the sign image. After this pre-processing, features are extracted from the sign image by implementing scale invariant feature transform. Acquiring all descriptors from the sign image, k-means clustering is executed on all the descriptors which are previously computed by SIFT. Based on the sample training set, each of the cluster denotes as a visual word. Considering the histograms of the clustering descriptors, Bag of words model is introduced on this hybrid approach which develops a set of visual vocabulary. Finally for each of sign word, a binary linear support vector machine (SVM) classifier is trained with a respective training data set. Considering these binary classifiers, we obtained a respective recognition rate on both Bangla signs of expressions and alphabets.

AB - This paper presents a SIFT-based geometrically computational approach to vigorously recognize Bangla sign language (BdSL). Gaussian distribution and grayscaling techniques are applied for image processing and normalizing the sign image. After this pre-processing, features are extracted from the sign image by implementing scale invariant feature transform. Acquiring all descriptors from the sign image, k-means clustering is executed on all the descriptors which are previously computed by SIFT. Based on the sample training set, each of the cluster denotes as a visual word. Considering the histograms of the clustering descriptors, Bag of words model is introduced on this hybrid approach which develops a set of visual vocabulary. Finally for each of sign word, a binary linear support vector machine (SVM) classifier is trained with a respective training data set. Considering these binary classifiers, we obtained a respective recognition rate on both Bangla signs of expressions and alphabets.

KW - Bag of word

KW - Bangla Sign Language Recognition

KW - Scale invariant feature transform

KW - Support vector machine

UR - https://www.scopus.com/pages/publications/84966507778

UR - https://www.scopus.com/pages/publications/84966507778#tab=citedBy

U2 - 10.1109/IWCIA.2015.7449458

DO - 10.1109/IWCIA.2015.7449458

M3 - Conference paper

AN - SCOPUS:84966507778

SN - 9781479988426

SP - 35

EP - 39

BT - 2015 IEEE 8th international workshop on computational intelligence and applications (IWCIA 2015)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - 8th IEEE International Workshop on Computational Intelligence and Applications

Y2 - 6 November 2015 through 7 November 2015

ER -

SIFT based approach on Bangla sign language recognition

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this