Using multiple sensors for mobile sign language recognition

Brashear, Helene; Starner﻿﻿, Thad; Lukowicz, Paul; Junker, Holger

doi:10.1109/iswc.2003.1241392

Cited by 116 publications

(85 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…From the literature survey, we understand that the models proposed for sign language recognition address the problem either at finger spelling level [20,24,26,27] or at word level [3,9,23,30,32]. Since signs used by hearing impaired people are very abstract, the sign language recognition based on fingerspelling or word seems to be cumbersome and not effective.…”

Section: Related Workmentioning

confidence: 99%

Spatial Relationship Based Features for Indian Sign Language Recognition

2016

IJCCIE

View full text Add to dashboard Cite

Abstract-In this paper, the task of recognizing signs made by hearing impaired people at sentence level has been addressed. A novel method of extracting spatial features to capture hand movements of a signer has been proposed. Frames of a given video of a sign are preprocessed to extract face and hand components of a signer. The local centroids of the extracted components along with the global centroid are exploited to extract spatial features. The concept of interval valued type symbolic data has been explored to capture variations in the same sign made by the different signers at different instances of time. A suitable symbolic similarity measure is studied to establish matching between test and reference signs and a simple nearest neighbour classifier is used to recognize an unknown sign as one among the known signs by specifying a desired level of threshold. An extensive experimentation is conducted on a considerably large database of signs created by us during the course of research work in order to evaluate the performance of the proposed system. Index Terms-Hearing impaired, Key-frame, Sign language and Symbolic data.

show abstract

Section: Related Workmentioning

confidence: 99%

Spatial Relationship Based Features for Indian Sign Language Recognition

2016

IJCCIE

View full text Add to dashboard Cite

show abstract

“…Another novel approach to sign language data acquisition was taken by Brashear et al [18] where features from both a hat mounted camera and accelerometer data were used to classifying signs Figure 2.8. While wearable computing approaches to data acquisition can extract accurate features representing the signs being performed, some of these approaches require that the signer wears cumbersome devices which can hinder the ease and naturalness of signing.…”

Section: Fig26: Sensing Glove With Six Accelerometers and A Basic Smentioning

confidence: 99%

Review of Literature for the Development of Indian Sign Language Recognition System

Dour¹,

Sharma²

2015

IJCA

View full text Add to dashboard Cite

“…As we incorporate these findings into our ASL generation software, we will conduct additional evaluation studies with native ASL signers to evaluate the 3D animations that result and guide the development of our technology. Earlier researchers have collected video-based sign language corpora [2] [5] [6] [7] [16] or collected samples of sign language using motion-capture [1] [4] [20]. For this project, we are collecting a corpus of ASL using a motion-capture suit and gloves, and we are recording multisentence passages in which signers associate entities with locations in space.…”

Section: Broader Research Objectives and Progressmentioning

confidence: 99%

Improving Spatial Reference in American Sign Language Animation through Data Collection from Native ASL Signers

Huenerfauth

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Many deaf adults in the U.S. have difficulty reading written English text; computer animations of American Sign Language (ASL) can improve these individuals' access to information, communication, and services. Current ASL animation technology cannot automatically generate expressions in which the signer associates locations in space with entities under discussion, nor can it generate many ASL signs whose movements are modified based on these locations. To determine how important such phenomena are to user-satisfaction and the comprehension of animations by deaf individuals, we conducted a study in which native ASL signers evaluated ASL animations with and without entity-representing spatial phenomena. We found that the inclusion of these expressions in the repertoire of ASL animation systems led to a significant improvement in user comprehension of the animations, thereby motivating future research on automatically generating such ASL spatial expressions.

show abstract

Using multiple sensors for mobile sign language recognition

Cited by 116 publications

References 13 publications

Spatial Relationship Based Features for Indian Sign Language Recognition

Spatial Relationship Based Features for Indian Sign Language Recognition

Review of Literature for the Development of Indian Sign Language Recognition System

Improving Spatial Reference in American Sign Language Animation through Data Collection from Native ASL Signers

Contact Info

Product

Resources

About