Özni̇teli̇k bi̇rleşti̇rmeye dayali çok-di̇lde el alfabesi̇ tanima

Ahmet Alp Kindiroglu; Hülya Yalçin; Lale Akarun

doi:10.1109/SIU.2011.5929626

Özni̇teli̇k bi̇rleşti̇rmeye dayali çok-di̇lde el alfabesi̇ tanima

Translated title of the contribution: Feature fusion based multilingual fingerspelling recognition

Ahmet Alp Kindiroglu^*, Hülya Yalçin, Lale Akarun

^*Corresponding author for this work

Bogazici University

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

Abstract

In this paper, we present a fingerspelling recognition module that has been designed to function in a smart system that is intended to act as a communication medium between people with hearing and visual disabilities. The method described is a computer vision based, close to real-time, automatic skin color based model hand gesture recognition module. We analyze and compare the recognition performance of appearance based hand descriptors on a self collected dataset. The dataset contains isolated videos of 88 different signs of the Czech, Turkish and Russian Sign Alphabets from 5 different signers with a total training and test length of 4 hours. On our test sets, we have achieved signer dependent and signer independent fingerspelling recognition rates of %82 and %42, respectively.

Translated title of the contribution	Feature fusion based multilingual fingerspelling recognition
Original language	Turkish
Title of host publication	2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011
Pages	214-217
Number of pages	4
DOIs	https://doi.org/10.1109/SIU.2011.5929626
Publication status	Published - 2011
Externally published	Yes
Event	2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011 - Antalya, Turkey Duration: 20 Apr 2011 → 22 Apr 2011

Publication series

Name	2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011

Conference

Conference	2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011
Country/Territory	Turkey
City	Antalya
Period	20/04/11 → 22/04/11

Access to Document

10.1109/SIU.2011.5929626

Cite this

Kindiroglu, A. A., Yalçin, H., & Akarun, L. (2011). Özni̇teli̇k bi̇rleşti̇rmeye dayali çok-di̇lde el alfabesi̇ tanima. In 2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011 (pp. 214-217). Article 5929626 (2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011). https://doi.org/10.1109/SIU.2011.5929626

@inproceedings{c11552a8897649f6b019502875990c6e,

title = "{\"O}zn{\.i}tel{\.i}k b{\.i}rle{\c s}t{\.i}rmeye dayali {\c c}ok-d{\.i}lde el alfabes{\.i} tanima",

abstract = "In this paper, we present a fingerspelling recognition module that has been designed to function in a smart system that is intended to act as a communication medium between people with hearing and visual disabilities. The method described is a computer vision based, close to real-time, automatic skin color based model hand gesture recognition module. We analyze and compare the recognition performance of appearance based hand descriptors on a self collected dataset. The dataset contains isolated videos of 88 different signs of the Czech, Turkish and Russian Sign Alphabets from 5 different signers with a total training and test length of 4 hours. On our test sets, we have achieved signer dependent and signer independent fingerspelling recognition rates of %82 and %42, respectively.",

author = "Kindiroglu, {Ahmet Alp} and H{\"u}lya Yal{\c c}in and Lale Akarun",

year = "2011",

doi = "10.1109/SIU.2011.5929626",

language = "T{\"u}rk{\c c}e",

isbn = "9781457704635",

series = "2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011",

pages = "214--217",

booktitle = "2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011",

note = "2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011 ; Conference date: 20-04-2011 Through 22-04-2011",

}

Kindiroglu, AA, Yalçin, H & Akarun, L 2011, Özni̇teli̇k bi̇rleşti̇rmeye dayali çok-di̇lde el alfabesi̇ tanima. in 2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011., 5929626, 2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011, pp. 214-217, 2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011, Antalya, Turkey, 20/04/11. https://doi.org/10.1109/SIU.2011.5929626

Özni̇teli̇k bi̇rleşti̇rmeye dayali çok-di̇lde el alfabesi̇ tanima. / Kindiroglu, Ahmet Alp; Yalçin, Hülya; Akarun, Lale.
2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011. 2011. p. 214-217 5929626 (2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011).

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

TY - GEN

T1 - Özni̇teli̇k bi̇rleşti̇rmeye dayali çok-di̇lde el alfabesi̇ tanima

AU - Kindiroglu, Ahmet Alp

AU - Yalçin, Hülya

AU - Akarun, Lale

PY - 2011

Y1 - 2011

N2 - In this paper, we present a fingerspelling recognition module that has been designed to function in a smart system that is intended to act as a communication medium between people with hearing and visual disabilities. The method described is a computer vision based, close to real-time, automatic skin color based model hand gesture recognition module. We analyze and compare the recognition performance of appearance based hand descriptors on a self collected dataset. The dataset contains isolated videos of 88 different signs of the Czech, Turkish and Russian Sign Alphabets from 5 different signers with a total training and test length of 4 hours. On our test sets, we have achieved signer dependent and signer independent fingerspelling recognition rates of %82 and %42, respectively.

AB - In this paper, we present a fingerspelling recognition module that has been designed to function in a smart system that is intended to act as a communication medium between people with hearing and visual disabilities. The method described is a computer vision based, close to real-time, automatic skin color based model hand gesture recognition module. We analyze and compare the recognition performance of appearance based hand descriptors on a self collected dataset. The dataset contains isolated videos of 88 different signs of the Czech, Turkish and Russian Sign Alphabets from 5 different signers with a total training and test length of 4 hours. On our test sets, we have achieved signer dependent and signer independent fingerspelling recognition rates of %82 and %42, respectively.

UR - http://www.scopus.com/inward/record.url?scp=79960436723&partnerID=8YFLogxK

U2 - 10.1109/SIU.2011.5929626

DO - 10.1109/SIU.2011.5929626

M3 - Konferans katkısı

AN - SCOPUS:79960436723

SN - 9781457704635

T3 - 2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011

SP - 214

EP - 217

BT - 2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011

T2 - 2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011

Y2 - 20 April 2011 through 22 April 2011

ER -

Özni̇teli̇k bi̇rleşti̇rmeye dayali çok-di̇lde el alfabesi̇ tanima

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this