A multi-class pattern recognition system for practical finger spelling translation

Hernandez-Rebollar, Jose L.; Lindeman, Robert W.; Kyriakopoulos, N.

doi:10.1109/icmi.2002.1166990

Cited by 53 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Unfortunately, these gloves are both intrusive and expensive. Hernandez-Rebollar et al [7] built their own instrumented glove in an attempt to provide a low-cost option. Other researchers [8][9][10][11] focused on improving visionbased methods to create systems that are relatively inexpensive and require only passive sensing.…”

Section: Related Workmentioning

confidence: 99%

Fingerspelling Recognition through Classification of Letter-to-Letter Transitions

Ricco

Tomasi

2010

Computer Vision – ACCV 2009

View full text Add to dashboard Cite

Abstract. We propose a new principle for recognizing fingerspelling sequences from American Sign Language (ASL). Instead of training a system to recognize the static posture for each letter from an isolated frame, we recognize the dynamic gestures corresponding to transitions between letters. This eliminates the need for an explicit temporal segmentation step, which we show is error-prone at speeds used by native signers. We present results from our system recognizing 82 different words signed by a single signer, using more than an hour of training and test video. We demonstrate that recognizing letter-to-letter transitions without temporal segmentation is feasible and results in improved performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Fingerspelling Recognition through Classification of Letter-to-Letter Transitions

Ricco

Tomasi

2010

Computer Vision – ACCV 2009

View full text Add to dashboard Cite

show abstract

“…Bu sistem; ivmeölçer eldiven (accelerometer glove), mikrokontroller ve beş tane MEMS (Micro Electro Mechanical System) çift-eksen ivmeölçerden oluşmaktadır. Bu çalışma 26 harfin 21'inde % 100, 'U' harfi için % 78'lik bir doğruluk oranı göstermiştir [14]. HernandezRebollar ve arkadaşlarının yaptığı çalışmaya benzer bir çalışma Bui ve Nguye (2005) tarafından yapılmıştır.…”

Section: Introductionunclassified

Lati̇s Tabanli Anlam Çözümlenmesi̇ İle Türkçe İşaret Di̇li̇ Tercüme Si̇stemi̇

Firat¹,

Uğurlu²

2018

Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi

View full text Add to dashboard Cite

ÖZGünlük hayatta insanlar; fikirlerini, düşüncelerini ve yaşadıklarını çevrelerindeki insanlara iletmek için birbirleriyle etkileşirler. İşitme ve konuşma engelli insanlar ise çevreleriyle bu etkileşimi sağlayamazlar. Başkalarıyla iletişim kurmak için işaret dilini kullanırlar. İşaret dili ise, işitme ve konuşma engellilerin kendi aralarında el hareketleri ve yüz mimikleri ile iletişim kurmalarını sağlayan ülkeden ülkeye değişen evrensel olmayan bir dildir. Bu anlamda yapılan çalışmanın amacı, işitme ve konuşma bozukluğu olan kişilerle normal insanlar arasındaki iletişimi sağlayan Türkçe İşaret Dili tercüme sistemini geliştirmektir. Önerilen bu sistemle işaret dilini gösteren el hareketleri, Kinect aygıtı yardımıyla yakalanarak Kontur Analizinde kullanılan algoritmalarla çözümlenmiştir. Çözümlenen görüntülerden elde edilen kelimelerin gerçek anlamları, Biçimsel Kavram Analizi Kuramı çerçevesinde hazırlanan tematik rol latisleriyle bulunmuştur. Gerçek anlamları bulunan bu kelimeler, içinde geçtikleri cümlelerle birlikte bilgisayar ekranında görüntülenmiştir. Böylece bu sistemle, engelli bir kişinin kitlesel bir kalabalıkla iletişim kurabilmesi sağlanmıştır. Ayrıca geliştirilen bu sistemle Türkçe'nin anlamsal çözümlenmesine de katkı sağlanması hedeflenmiştir.Anahtar Kelimeler: Biçimsel kavram analizi, işaret dili tanımlama, kinect, kontur analizi, tematik rol latisleri TURKISH SIGN LANGUAGE TRANSLATION SYSTEM WITH A LATTICE-BASED SEMANTIC ANALYSIS ABSTRACTIn daily life people interact with each other to communicate their ideas, thoughts and experiences to the people around them. On the other hand, people with hearing and speech impairments are not capable of communicating with their environment in the given sense. Thus, they use sign language to communicate with others. Sign language is a non-universal language that changes depending on the country in which it's being used and enables people with hearing and speech impairments to communicate with other people through hand gestures and facial expressions. In this sense, the aim of the study is to develop Turkish Sign Language translation system that enables communication between people with speech and hearing impairments and healthy people. With this proposed system, the hand movements showing sign language are captured with the help of Kinect device and analyzed with the algorithms used in Contour Analysis. Actual meanings of the words obtained from the analyzed images were found thematic role lattices that are prepared in the frame of Formal Concept Analysis theory. The words of which actual meanings were found are displayed with the sentences in which they were used. Therefore, thanks to this system it is ensured that a disabled person can communicate with a mass crowd. The developed system also aims to contribute to the semantic analysis of the Turkish Language.

show abstract

“…While these techniques gave the advantage of accurate positions, they did not allow full natural movement and constricted the mobility of the signer, altering the signs performed. Trials with a modified glove-like device, which was less constricting [43], attempted to address this problem. However, due to the the prohibitive costs of such approaches, the use of vision has become more popular.…”

Section: Data Acquisition and Feature Extractionmentioning

confidence: 99%

Sign Language Recognition

Cooper

Holt

Bowden

2011

Visual Analysis of Humans

171

View full text Add to dashboard Cite

This chapter covers the key aspects of Sign Language Recognition (SLR), starting with a brief introduction to the motivations and requirements, followed by a précis of sign linguistics and their impact on the field. The types of data available and the relative merits are explored allowing examination of the features which can be extracted. Classifying the manual aspects of sign (similar to gestures) is then discussed from a tracking and non-tracking viewpoint before summarising some of the approaches to the non-manual aspects of sign languages. Methods for combining the sign classification results into full SLR are given showing the progression towards speech recognition techniques and the further adaptations required for the sign specific case. Finally the current frontiers are discussed and the recent research presented. This covers the task of continuous sign recognition, the work towards true signer independence, how to effectively combine the different modalities of sign, making use of the current linguistic research and adapting to larger more noisy data sets.

show abstract

A multi-class pattern recognition system for practical finger spelling translation

Cited by 53 publications

References 13 publications

Fingerspelling Recognition through Classification of Letter-to-Letter Transitions

Fingerspelling Recognition through Classification of Letter-to-Letter Transitions

Lati̇s Tabanli Anlam Çözümlenmesi̇ İle Türkçe İşaret Di̇li̇ Tercüme Si̇stemi̇

Sign Language Recognition

Contact Info

Product

Resources

About