5,707 Hits in 4.1 sec

Automatic fingersign-to-speech translation system

Marek Hrúz, Pavel Campr, Erinç Dikici, Ahmet Alp Kındıroğlu, Zdeněk Krňoul, Alexander Ronzhin, Haşim Sak, Daniel Schorno, Hülya Yalçın, Lale Akarun, Oya Aran, Alexey Karpov (+2 others)
2011 Journal on Multimodal User Interfaces  
Different spoken languages and sign languages such as English, Russian, Turkish and Czech are considered.  ...  Fingerspelling is a subset of sign language, and uses finger signs to spell letters of the spoken or written language. We aim to convert finger spelled words to speech and vice versa.  ...  The animation model allows expressing both manual and non-manual components of sign languages. The manual component is fully expressed by rotations of the body segments.  ... 
doi:10.1007/s12193-011-0059-3 fatcat:dexq3o2auzeupivz76sn6yn4bi


Muhammed Süzgün, Hilal Özdemir, Necati Camgöz, Ahmet Kındıroğlu, Doğaç Başaran, Cengiz Togay, Lale Akarun
2015 Journal of Naval Science and Engineering  
HospiSign recognizes isolated signs in a structured activity diagram using Dynamic Time Warping based classifiers.  ...  The objective of this paper is to review sign language based Human-Computer Interaction applications and to introduce HospiSign in this context.  ...  In the finger spelling synthesis model, a 3D animated avatar is used to express both manual and non manual features of a given sign.  ... 
doaj:fc2888286a074d17b648b168c64ce764 fatcat:ksecv5a64jennd54ufwh74upqe

Recognition of Sign Language Letters Using Image Processing and Deep Learning Methods

Ali ÖZTÜRK, Melih KARATEKİN, İ̇̇sa Alperen SAYLAR, Nazım Bahadır BARDAKCI
2021 Zeki sistemler teori ve uygulamaları dergisi  
In this study, it was achieved t o dynamically recognize the movements of the sign language finger alphabet via image processing using deep learning methods and to translate it into writing.  ...  Accordingly, it is aimed to facilitate communication between people who do not know the sign language in daily life and people with hearing loss.  ...  Acknowledgment The dataset used for training in this study is available at  ... 
doi:10.38016/jista.808458 fatcat:tyewgcxarrgrdho4hyfypyq36i

Towards Computer Assisted International Sign Language Recognition System: A Systematic Survey

Mikhaylyna Melnyk, Vira Shadrova, Borys Karwatsky
2014 International Journal of Computer Applications  
In this paper, we focus on the advancements in computer assisted sign language recognition systems.  ...  There is a number of automated sign language recognition systems proposed in the computer vision literature.  ...  They use a single non-manual signal, head movement, to evaluate the proposed framework when recognizing non-manual signals.  ... 
doi:10.5120/15727-4698 fatcat:2ni6daxrybenrpjzebogt4pcge

Sign Language Tutoring Tool

Oya Aran, Cem Keskin, Lale Akarun
2005 Zenodo  
Publication in the conference proceedings of EUSIPCO, Antalya, Turkey, 2005  ...  In the current version of the demonstrator, we used 7 different dynamic signs from Turkish Sign Language. Table 1 shows the properties of each sign.  ...  The current version of the demonstrator has some requirements and restrictions: • The signs currently in the application library are 7 signs form Turkish Sign Language • These 7 signs are dynamic signs  ... 
doi:10.5281/zenodo.39435 fatcat:qvykdph7gzftlf7wou62uzvaga

Sequential Belief-Based Fusion of Manual and Non-manual Information for Recognizing Isolated Signs [chapter]

Oya Aran, Thomas Burger, Alice Caplier, Lale Akarun
2009 Lecture Notes in Computer Science  
This work aims to recognize signs which have both manual and nonmanual components by providing a sequential belief-based fusion mechanism.  ...  We propose a methodology based on belief functions for fusing extracted manual and non-manual features in a sequential two-step approach.  ...  American Sign Language (ASL), British Sign Language, Turkish Sign Language, French Sign Language are different sign languages used by corresponding communities of hearing impaired people.  ... 
doi:10.1007/978-3-540-92865-2_14 fatcat:pp2irxi4v5ekbhxzm3ih7t63t4

Automatic recognition fingerspelling gestures in multiple languages for a communication interface for the disabled

A. Alp Kindiroglu, H. Yalcin, O. Aran, M. Hrúz, P. Campr, L. Akarun, A. Karpov
2012 Pattern Recognition and Image Analysis  
The system converts fingerspelled words to speech and vice versa using fingerspelling recognition, fingerspelling synthesis, speech recognition and speech synthesis in Czech, Russian and Turkish Languages  ...  We describe an adaptive skin color based fingersign recognition system with a close to real time performance and present recognition results on 88 different letters signed by five different signers, using  ...  Although most sign languages are quite rich in terms of the number of signs in the lan guage, there can be some foreign words, private names, or uncommon words, for which no sign is defined.  ... 
doi:10.1134/s1054661812040086 fatcat:llrl4ncd2jagtpg7ynmhzzps3m

BosphorusSign22k Sign Language Recognition Dataset [article]

Oğulcan Özdemir, Ahmet Alp Kındıroğlu, Necati Cihan Camgöz, Lale Akarun
2020 arXiv   pre-print
The primary objective of this dataset is to serve as a new benchmark in Turkish Sign Language Recognition for its vast lexicon, the high number of repetitions by native signers, high recording quality,  ...  In this paper, we introduce the BosphorusSign22k, a publicly available large scale sign language dataset aimed at computer vision, video recognition and deep learning research communities.  ...  and production systems, where distinguishing between instances of similar sign classes with similar manual and non-manual features is essential.  ... 
arXiv:2004.01283v2 fatcat:rcoim462wvdvllyvh6xfe4d7nm

Towards Hybrid Multimodal Manual and Non-Manual Arabic Sign Language Recognition: mArSL Database and Pilot Study

Hamzah Luqman, El-Sayed M. El-Alfy
2021 Electronics  
In addition, we evaluated the fusion of spatial and temporal features of different modalities, manual and non-manual, for sign language recognition using the state-of-the-art deep learning techniques.  ...  However, most of the existing and available works on sign language recognition systems focus on manual gestures, ignoring other non-manual information needed for other language signals such as facial expressions  ...  In addition, a few signs in sign language depend on the non-manual gestures without manual gestures.  ... 
doi:10.3390/electronics10141739 fatcat:ga37vyeimjbrpasutw4spqw5ta

SignTutor: An Interactive System for Sign Language Tutoring

Oya Aran, Ismail Ari, Lale Akarun, Bülent Sankur, Alexandre Benoit, Alice Caplier, Pavel Campr, Ana Huerta Carrillo, Fran¸ois-Xavier Fanard
2009 IEEE Multimedia  
Sign Language, the natural communication medium for a deaf person, is difficult to learn for the general population.  ...  Since language learning can only advance with continuous practice and corrective feedback, we have developed an interactive system, called SignTutor, which automatically evaluates users' signing and gives  ...  It should exploit both the manual and non-manual signs and the grammar and syntax of the sign language.  ... 
doi:10.1109/mmul.2009.17 fatcat:xg4hq72jhngdhlurek6w4epuki

A Corpus-Based Typology of Negation Strategies in Turkish Sign Language

2021 Dilbilim Araştırmaları Dergisi  
This paper investigates the distribution of negation strategies in Turkish Sign Language (TİD) in the light of frequency-based data from a naturalistic TİD Corpus.  ...  not lexically specified for NOT in contrast to Gökgöz ( 2011 ), (iii) on the other hand, in line with Pfau (2016), we show that TİD can easily be categorized as a Non-Strict NC language.  ...  Negation Strategies in Turkish Sign Language As stated above, NMMs, such as brow raising and backward head tilt, play a crucial role in the TİD grammar.  ... 
doi:10.18492/dad.853176 fatcat:4pepysnqcbbr3dvzktq2lgd254

Design and Development of a Humanoid Robot for Sign Language Interpretation

Ragib Amin Nihal, Nawara Mahmood Broti, Shamim Ahmed Deowan, Sejuti Rahman
2021 SN Computer Science  
It can imitate 16 BdSL alphabets in sign language, can capture a video or image input in real-time from the user, and recognize 10 medical signs and 38 alphabets of BdSL.  ...  Image-based Bangla sign language recognition achieved an overall test accuracy of 98.19% in our dataset and 93.8% in another available dataset.  ...  sign language of American sign language dictionary Number of signs recognized 15 signs of Turkish sign language 9 signs of Turkish Sign language Cannot recognize signs 38 signs of Bangla sign  ... 
doi:10.1007/s42979-021-00627-3 fatcat:i5qqglt5gja3ph2rx5iib37g4a


Rudranarayan Mohapatra, AnadiCharan Gan.
2017 International Journal of Advanced Research  
Sign languages are made up of both manuals components and non-manual components such as gaze, facial expressions and emotions.  ...  Japanese Sign Language (Nihon Shuwa, JSL), British Sign Language (BSL) and Turkish Sign Language (Türk İşaret Dili, TID) are out of them.  ... 
doi:10.21474/ijar01/3841 fatcat:bkh7qyueg5eplbwtlhy4oidyyu

Aspects of Türk Isaret Dili (Turkish Sign Language)

Ulrike Zeshan
2003 Sign Language and Linguistics  
This article provides a first overview of some striking grammatical structures in Türk İş aret Dili (Turkish Sign Language, TID), the sign language used by the Deaf community in Turkey.  ...  The data are described with a typological perspective in mind, focusing on aspects of TID grammar that are typologically unusual across sign languages.  ...  My research on sign language typology is funded by the German Science Foundation (DFG) under the Emmy-Noether post-doctoral research scheme.  ... 
doi:10.1075/sll.6.1.04zes fatcat:acy3oeclz5ge3mn5iewqf7bqme

A belief-based sequential fusion approach for fusing manual signs and non-manual signals

Oya Aran, Thomas Burger, Alice Caplier, Lale Akarun
2009 Pattern Recognition  
of the research on sign language recognition concentrates on recognizing only manual signs (hand gestures and shapes), discarding a very important component: the non-manual signs (facial expressions and  ...  We address the recognition of signs with both manual and non-manual components using a sequential belief-based fusion technique.  ...  American Sign Language, British Sign Language, Turkish Sign Language, and French Sign Language are different sign languages used by corresponding communities of hearing-impaired people.  ... 
doi:10.1016/j.patcog.2008.09.010 fatcat:apaw7wqwc5fbjgjpk7wmgiu44i
« Previous Showing results 1 — 15 out of 5,707 results