2007 9th International Symposium on Signal Processing and Its Applications 2007
DOI: 10.1109/isspa.2007.4555448
|View full text |Cite
|
Sign up to set email alerts
|

Sign language recognition

Abstract: In this paper, an image processing algorithm is presented for the interpretation of the Taiwanese Sign Language, which is one of the sign languages used by the majority of the deaf community. The process involves two layer classifications. At first, coarse classification is done according to detection of hand motion and tracking the hand location and second classification is based on key frame selection and hand shape recognition of key frames. Motion history image and Fourier descriptor are used for motion di… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2009
2009
2021
2021

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(4 citation statements)
references
References 5 publications
0
4
0
Order By: Relevance
“…Hong [3], Modler [17], Vadafar [18], Elmezain [19] Pizzolato [20], Bauer [21], Wang [22], Brasher [23] and Pahlevanzadeh [24] (just to mention a few), tackled the problem of dynamic gesture recognition. Hong proposed a system based on finite-state machines (FSMs).…”
Section: Related Workmentioning
confidence: 99%
“…Hong [3], Modler [17], Vadafar [18], Elmezain [19] Pizzolato [20], Bauer [21], Wang [22], Brasher [23] and Pahlevanzadeh [24] (just to mention a few), tackled the problem of dynamic gesture recognition. Hong proposed a system based on finite-state machines (FSMs).…”
Section: Related Workmentioning
confidence: 99%
“…Coogan and Sutherland [17] used a similar principle when they created a hierarchical decision tree, the leaf nodes of which contained the exemplar of a hand shape class, defined by fuzzy k-means clustering of the Eigenvalues resulting from performing PCA on the artificially constructed training images. Using gloved data to give good segmentation of the hands allowed Pahlevanzadeh et al to use a generic cosine detector to describe basic hand shapes [84] though the system is unlikely to be tractable. Fillbrandt et al used 2D appearance models to infer 3D posture and shape of the hands [31].…”
Section: Hand Shapementioning
confidence: 99%
“…Such approach can be used on the implementation of a recognition technique with satisfactory results [13]. The recognition algorithm has two phases, one dealing with hand configuration and other responsible for hand movement analysis.…”
Section: A) Capturing and Coding Sign Languagementioning
confidence: 99%