Smoothed Disparity Maps for Continuous American Sign Language Recognition

Dreuw, Philippe; Steingrube, Pascal; Deselaers, Thomas; Ney, Hermann

doi:10.1007/978-3-642-02172-5_5

Cited by 10 publications

(5 citation statements)

References 11 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…x x x Signum DGS [Dreuw et al, 2007] 2007 103 3 x x x x ASL [Mohandes et al, 2007] 2007 300 1 x x x x ArSL [Infantino et al, 2007] 2007 40 x x x x x LIS [Infantino et al, 2007] 2007 40 x x x x x LIS [Shanableh et al, 2007] 2007 23 3 x x x ArSL [Cooper and Bowden, 2007b] 2007 5 9 x x x BSL [Wang et al, 2007] 2007 100 1 x x x x CSL [Cooper and Bowden, 2007a] 2007 164 1 x x x x x BSL [Yang et al, 2007] 2007 39 x x x ASL [von Agris et al, 2008b] 2008 152 x x x x x x x DGS [von Agris et al, 2008b] 2008 229 4 x x x x x x x BSL [Forster, 2008] 2008 103 3 x x x BU-104 ASL [von Agris et al, 2008a] 2008 450 25 x x x x x x x Signum DGS [Maebatake et al, 2008] 2008 183 4 x x x x JSL [Paulraj et al, 2008] 2008 Trmal et al, 2008] 2008 25 20 x x x x CzSL [Lichtenauer et al, 2008] 2008 120 75 x x x NGT [Derpanis et al, 2008] 2008 148 3 x x x ASL 2008 102 3 x x x x x ASL [Athitsos et al, 2008] 2008 108 2 x x x ASL [Dreuw and Ney, 2008] 2008 104 3 x x x x ASL [Dreuw, 2008] 2008 [Lichtenauer et al, 2009] 2009 120 75 x x x x NGT [Hrúz et al, 2009] 2009 50 1 x x x x x CzSL [Ding and Martinez, 2009] 2009 38 10 x x x x x ASL [Dreuw et al, 2009] 2009 103 3 x x x x x ASL [Dias et al, 2009] 2009 15 4 x x x Libras [Buehler et al, 2009] 2009 210 3 x x x x x BSL [Liwicki and Everingham, 2009] 2009 100…”

Section: Supplemental Materialsmentioning

confidence: 99%

Quantitative Survey of the State of the Art in Sign Language Recognition

Koller¹

2020

Preprint

View full text Add to dashboard Cite

This work presents a meta study covering around 300 published sign language recognition papers with over 400 experimental results. It includes most papers between the start of the field in 1983 and 2020. Additionally, it covers a fine-grained analysis on over 25 studies that have compared their recognition approaches on RWTH-PHOENIX-Weather 2014, the standard benchmark task of the field. Research in the domain of sign language recognition has progressed significantly in the last decade, reaching a point where the task attracts much more attention than ever before. This study compiles the state of the art in a concise way to help advance the field and reveal open questions. Moreover, all of this meta study's source data is made public, easing future work with it and further expansion. The analyzed papers have been manually labeled with a set of categories. The data reveals many insights, such as, among others, shifts in the field from intrusive to non-intrusive capturing, from local to global features and the lack of non-manual parameters included in medium and larger vocabulary recognition systems. Surprisingly, RWTH-PHOENIX-Weather with a vocabulary of 1080 signs represents the only resource for large vocabulary continuous sign language recognition benchmarking world wide.

show abstract

Section: Supplemental Materialsmentioning

confidence: 99%

Quantitative Survey of the State of the Art in Sign Language Recognition

Koller¹

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…It is worth mentioning that some RGB-D cameras, based on the time-of-flight principle, operate even in a dark room [40]. Solutions using stereovision and multi-camera systems have been known in the literature for a long time, e.g., [41][42][43]. Currently, most methods use RGB-D cameras, e.g., [44][45][46][47].…”

Section: Recent Workmentioning

confidence: 99%

Recognition of Signed Expressions in an Experimental System Supporting Deaf Clients in the City Office

Kapuściński

Wysocki

2020

Sensors

View full text Add to dashboard Cite

The paper addresses the recognition of dynamic Polish Sign Language expressions in an experimental system supporting deaf people in an office when applying for an ID card. A method of processing a continuous stream of RGB-D data and a feature vector are proposed. The classification is carried out using the k-nearest neighbors algorithm with dynamic time warping, hidden Markov models, and bidirectional long short-term memory. The leave-one-subject-out protocol is used for the dataset containing 121 Polish Sign Language sentences performed five times by four deaf people. A data augmentation method is also proposed and tested. Preliminary observations and conclusions from the use of the system in a laboratory, as well as in real conditions with an experimental installation in the Office of Civil Affairs are given.

show abstract

“…The reason for attaching prime importance to feature selection and extraction is its vital role in the performance and accuracy of the complete SLR system. Samir et al [22] and Philippe Dreuw et al [25] have used multiple cameras to recognize sign language. Samir et al have generated image features with pulse-coupled neural network (PCNN) from two different viewing angles for recognizing Arabic Sign Language [22].…”

Section: Related Workmentioning

confidence: 99%

“…A lot of work has been done for different languages of the world . Especially researchers have got a good focus on Australian Sign Language [1][2][3][4][5][6], American Sign Language [9][10][11][12], Chinese Sign Language [13][14][15], and Arabic Sign Language [16][17][18][19]. Unfortunately very limited work has been done for the recognition of Pakistani Sign Language (PSL).…”

Section: Introductionmentioning

confidence: 99%

Vision-based Classification of Pakistani Sign Language

Kausar¹,

Javed²,

Tehsin³

et al. 2016

IJIGSP

View full text Add to dashboard Cite

Automated sign language recognition is one of the important areas of computer vision today, because of its applicability in vast fields of life. This paper presents automated recognition of signs taken from Pakistani Sign Language (PSL). The paper presents empirical analysis of two statistical and one transformation based shape descriptors for the recognition of PSL. A purely vision based, efficient, signer independent, multi-aspect invariant method is proposed for the recognition of 44 signs of PSL. The method has proved its worth by utilizing a very small shape descriptor and giving promising results for a reasonable size of sign dictionary. The proposed methodology achieved an accuracy of 92%.

show abstract

Smoothed Disparity Maps for Continuous American Sign Language Recognition

Cited by 10 publications

References 11 publications

Quantitative Survey of the State of the Art in Sign Language Recognition

Quantitative Survey of the State of the Art in Sign Language Recognition

Recognition of Signed Expressions in an Experimental System Supporting Deaf Clients in the City Office

Vision-based Classification of Pakistani Sign Language

Contact Info

Product

Resources

About