ARGo: An Architecture for Sign Language Recognition and Interpretation

Braffort, Annelies

doi:10.1007/978-1-4471-0943-3_3

Cited by 30 publications

(15 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Works that interpret sign gestures whose form and manner of movement convey grammatical information mostly focused on spatial variations of the sign's movement. None of the works surveyed gave experimental results for intepretation of the mimetic classifier signs mentioned by Edwards [41] and Bossard et al [15], [19]. It is obvious from the discussion in Section 3.4.2 that this aspect of signing has not received attention.…”

Section: Discussionmentioning

confidence: 99%

“…In contrast, many of the other works are limited in the vocabulary size they can handle due to only using a subset of the information necessary for recognizing a comprehensive vocabulary. For example, it is common for input data to be from one hand only ( [19], [25], [33], [36], [60], [63], [65], [66], [72], [82], [89], [96], [133], [139], [145]). Matsuo et al [93] and Yang et al [158] used input from both hands but only measured position and motion data.…”

Section: Discussionmentioning

confidence: 99%

“…Although the description above has focused on ASL, similar use of NMS and grammatical processes occur in SL(s) of other countries, e.g., Japan [157], Taiwan [127], Britain [130], Australia [71], Italy [29], and France [19].…”

Section: Nonmanual Signals-nmsmentioning

confidence: 99%

“…Six different sentences constructed from two verbs and three different subject-object pairs, which were tested on the same signer that provided the training set, was recognized with an average word accuracy of 93.4 percent. Braffort [19] proposed an architecture where HMMs were employed for classifying lexical signs using all the features of the sign gesture (glove finger flexure values, tracker location and orientation), while verbs which can express person agreement were classified by their movement trajectory alone and classifier signs were classified by their finger flexure values only. Sentences comprising seven signs from the three different categories were successfully recognized with 92-96 percent word accuracy.…”

Section: Grammatical Processes In Sign Gesturesmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Sign Language Analysis: A Survey and the Future beyond Lexical Meaning

Ong

Ranganath²

2005

IEEE Trans. Pattern Anal. Machine Intell.

454

217

View full text Add to dashboard Cite

Abstract-Research in automatic analysis of sign language has largely focused on recognizing the lexical (or citation) form of sign gestures as they appear in continuous signing, and developing algorithms that scale well to large vocabularies. However, successful recognition of lexical signs is not sufficient for a full understanding of sign language communication. Nonmanual signals and grammatical processes which result in systematic variations in sign appearance are integral aspects of this communication but have received comparatively little attention in the literature. In this survey, we examine data acquisition, feature extraction and classification methods employed for the analysis of sign language gestures. These are discussed with respect to issues such as modeling transitions between signs in continuous signing, modeling inflectional processes, signer independence, and adaptation. We further examine works that attempt to analyze nonmanual signals and discuss issues related to integrating these with (hand) sign gestures. We also discuss the overall progress toward a true test of sign recognition systems-dealing with natural signing by native signers. We suggest some future directions for this research and also point to contributions it can make to other fields of research. Web-based supplemental materials (appendicies) which contain several illustrative examples and videos of signing can be found at www.computer.org/publications/dlib.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Nonmanual Signals-nmsmentioning

confidence: 99%

Section: Grammatical Processes In Sign Gesturesmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Sign Language Analysis: A Survey and the Future beyond Lexical Meaning

Ong

Ranganath²

2005

IEEE Trans. Pattern Anal. Machine Intell.

454

217

View full text Add to dashboard Cite

show abstract

“…It attempted to integrate the normally disparate fields of sign language recognition and understanding [2]. Toward this goal, Gibet and colleagues also described a corpus of 3D gestural and sign language movement primitives [8].…”

Section: Related Workmentioning

confidence: 98%

A Framework for Recognizing the Simultaneous Aspects of American Sign Language

Vogler¹,

Metaxas²

2001

Computer Vision and Image Understanding

256

168

View full text Add to dashboard Cite

The major challenge that faces American Sign Language (ASL) recognition now is developing methods that will scale well with increasing vocabulary size. Unlike in spoken languages, phonemes can occur simultaneously in ASL. The number of possible combinations of phonemes is approximately 1.5 × 10 9 , which cannot be tackled by conventional hidden Markov model-based methods. Gesture recognition, which is less constrained than ASL recognition, suffers from the same problem. In this paper we present a novel framework to ASL recognition that aspires to being a solution to the scalability problems. It is based on breaking down the signs into their phonemes and modeling them with parallel hidden Markov models. These model the simultaneous aspects of ASL independently. Thus, they can be trained independently, and do not require consideration of the different combinations at training time. We show in experiments with a 22-sign-vocabulary how to apply this framework in practice. We also show that parallel hidden Markov models outperform conventional hidden Markov models.

show abstract

Appearance-Based Real-Time Understanding of Gestures Using Projected Euler Angles

Chandran¹,

Sawa²

Real-Time Vision for Human-Computer Interaction

View full text Add to dashboard Cite

ARGo: An Architecture for Sign Language Recognition and Interpretation

Cited by 30 publications

References 2 publications

Automatic Sign Language Analysis: A Survey and the Future beyond Lexical Meaning

Automatic Sign Language Analysis: A Survey and the Future beyond Lexical Meaning

A Framework for Recognizing the Simultaneous Aspects of American Sign Language

Appearance-Based Real-Time Understanding of Gestures Using Projected Euler Angles

Contact Info

Product

Resources

About