A Vision Based Recognition of Indian Sign Language Alphabets and Numerals Using B-Spline Approximation

Journal Title: International Journal on Computer Science and Engineering - Year 2012, Vol 4, Issue 3

Abstract

Sign language is the most natural way of expression for the deaf community. The urge to support the integration of deaf people into the hearing society made the automatic sign language recognition, an area of interest for the researchers. Indian Sign Language (ISL) is a visual-spatial language which provides linguistic information using hands, arms, facial expressions, and head/body postures. In this paper we propose a novel vision-based recognition of Indian Sign Language Alphabets and Numerals using B-Spline Approximation. Gestures of ISL alphabets are complex since it involves the gestures of both the hands together. Our algorithm approximates the boundary extracted from the Region of Interest, to a B-Spline curve by taking the Maximum Curvature Points (MCPs) as the Control points. Then the B-Spline curve is subjected to iterations for smoothening resulting in the extraction of Key Maximum Curvature points (KMCPs), which are the key contributors of the gesture shape. Hence a translation & scale invariant feature vector is obtained from the spatial locations of the KMCPs in the 8 Octant Regions of the 2D Space which is given for classification.

Authors and Affiliations

Geetha M , Manjusha U C

Keywords

Related Articles

Text Summarization and Discovery of Frames and Relationship from Natural Language Text - A R&D Methodology

The paper deals with the concept of data mining whereby the data resources can be fetched and accessed accordingly with reduced time complexity. Resource sharing is an important aspect in the field of information science...

On the Timing Analysis of Cluster based Communication Devices for Large Scale Computing Systems

Many parallel computing environments utilize cluster based architecture for large scale computing owing to the ease of their availability. As the cluster based approach may be used extensively, the interconnection mechan...

REMOTE SENSING IMAGE COMPRESSION USING 3D-SPIHT ALGORITHM AND 3D-OWT

Remote Sensing is the gathering of information about a place from a distance. Such information can occur by sensors or satellite, without making any direct contact with that object. We present a new technique for the com...

Effect of Optical Pulse Shape on the Performance of OCDMA in Presence of GVD and Pulse Linear Chirp

In this paper, the effect of optical pulse shape on the performance of direct sequence optical code division multiple access in presence of fiber group velocity dispersion (GVD) and pulse linear chirp is analyzed. In our...

Power Saving Scheme (PSS) in Clusters of Heterogeneous ireless Sensor Networks

In this paper, we proposed a Power Saving Scheme (PSS) multi-hop sensor network using partition clusters. It avoids collision and idle listening time of sensor nodes for better overall network life time. The basic sensor...

Download PDF file
  • EP ID EP129957
  • DOI -
  • Views 156
  • Downloads 0

How To Cite

Geetha M, Manjusha U C (2012). A Vision Based Recognition of Indian Sign Language Alphabets and Numerals Using B-Spline Approximation. International Journal on Computer Science and Engineering, 4(3), 406-415. https://europub.co.uk/articles/-A-129957