Simultaneous spotting of signs and fingerspellings based on hierarchical conditional random fields and boostmap embeddings

Yang, Hee-Deok; Lee, Seong–Whan

doi:10.1016/j.patcog.2010.03.007

Cited by 26 publications

(20 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to consider the combination of the three components required for rec ognizing MN s, an hierarchical framework based on thresh old model with CRFs and BoostMap embeddings is ap plied [15,14].…”

Section: Manual Signing Recognitionmentioning

confidence: 99%

“…Sign language is a visual language used by deaf peo ple [7,15,14], which consists of two types of feature; MSs and NMSs. MSs carry an explicit lexical meaning with hand and arm gestures and can be divided into two type of action; sign and fingerspelling [10,15,14].…”

Section: Introductionmentioning

confidence: 99%

“…MSs carry an explicit lexical meaning with hand and arm gestures and can be divided into two type of action; sign and fingerspelling [10,15,14]. Signs are dy -978-1-4577 -0308-9/11/$26.00 ©2011 IEEE 1726 namic gestures discriminated by continuous hand motions and hand configurations, while fingerspellings are a combi nation of continuous hand configurations [10,14]. NMSs provide morphemic information on specific lexical items or indicates the ends of phrases, etc [12].…”

Section: Introductionmentioning

confidence: 99%

“…For dealing with MS, previous vision-based methods have demonstrated some successes using hidden Markov models (HMMs) [11] and CRFs [13,15,14], and so on. In order to distinguish meaningful signs and meaning less (non-sign) patterns, Yang et al have used a threshold model with CRFs [15,14].…”

Section: Introductionmentioning

confidence: 99%

“…In order to distinguish meaningful signs and meaning less (non-sign) patterns, Yang et al have used a threshold model with CRFs [15,14]. Yang and Lee have used hierar chical CRF and BoostMap embedding in order to recognize signs and fingerspellings at the same time [14].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Combination of manual and non-manual features for sign language recognition based on conditional random field and active appearance model

Yang

Lee

2011

2011 International Conference on Machine Learning and Cybernetics

Self Cite

View full text Add to dashboard Cite

Sign language recognition is the task of detection and recognition of manual signals (MSs) and non-manual signals (NMSs) in a signed utterance. In this paper, a novel method for recognizing MS and facial expres sions as a NMS is proposed. This is achieved through a framework consisting of three components: (1) Can didate segments of MSs are discriminated using an hi erarchical conditional random field (CRF) and Boost Map embedding. It can distinguish signs, fingerspellings and non-sign patterns, and is robust to the various sizes, scales and rotations of the signer's hand. (2) Fa cial expressions as a NMS are recognized with sup port vector machine (SVM) and active appearance model (AAM). AAM is used to extract facial feature points. From these facial feature points, several mea surements are computed to distinguish each facial com ponent into defined facial expressions with SVM. (3) Fi nally, the recognition results of MSs and NMSs are fused in order to recognize signed sentences. Experi ments demonstrate that the proposed method can suc cessfully combine MSs and NMSs features for rec ognizing signed sentences from utterance data.

show abstract

Section: Manual Signing Recognitionmentioning

confidence: 99%