Systematic Literature Survey on Sign Language Recognition Systems

Systematic Literature Survey on Sign Language Recognition Systems

Ashok Kumar L., Karthika Renuka D., Raajkumar G.
DOI: 10.4018/978-1-6684-6001-6.ch012
OnDemand:
(Individual Chapters)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Recently, communication via signing acknowledgment has received a lot of attention in personal computer vision. Sign language is a method of conveying messages by using the hand, arm, body, and face to convey considerations and implications. Communication through gestures, like communication in languages, arises and develops naturally within hearing-impaired networks. All the same, gesture-based communication is uncommon. There is no universally perceived and accepted gesture-based communication for all deaf and hard-of-hearing people. Each nation has its own communication via gestures with a significant level of syntactic variety, just as it does when communicating in language. The gesture-based communication utilized is usually known as sign language.
Chapter Preview
Top

Literature Survey

Acquisition Using Wearable Computing

Wearable registration approaches to gesture-based communication information security provide a precise method for separating data about the underwriters' hand developments and hand shape. Each detecting innovation differs in a few ways, including precision, goal and range of movement, client comfort, and cost.

(Berman, 2011) proposed a reasonable visual movement information glove with high acknowledgment precision. In place of the more widely used development separating fibres or multi-channel accounting, the glove device employed a single - carrier video, with a repeating estimate to make up for the deficiencies of single-channel accounts. The growth of the hand was captured using a monocular camera, and after that, a visual analyser estimation identified the optical markings and reconstructed the 3D locations of the joints and fingers. In MATLAB, three different circumstances (left/right snaps, numerals, and the OK symbol) were dealt with and made into 3D graphics.

(Madeo, 2013) used the KHU-l information glove to create a 3D hand movement following and motion recognition framework. A Bluetooth device was used to connect the information glove to a PC. It was capable of performing hand movements such as clench hand grasping, hand extending, and bowing. For 50 preliminary trials, three signals (scissor, rock, and paper) were tried with 100% precision. Although 3D recognition and remote transmission were significant advancements, they resulted in time lag.

(Witt, 2007) devised a method for integrating glove-based devices into various applications using a setting system. The hand glove synchronised with electronic device may be used in three different ways, as demonstrated: to move, zoom, and choose parts of an assistant; to study a regulator in display; and to control a toy robot's left and right movements. Backwards/advances One issue was that, while this device could detect movement in the X and Y hatchets, it couldn't detect movement in the Z centre, such as the claimed “yaw.” Furthermore. The precision of acknowledgment was sacrificed in order to achieve wear capacity, light weight, and a cool appearance.

Complete Chapter List

Search this Book:
Reset