A review on vision based American sign language recognition, its techniques, and outcomes

Shivashankara, S; Srinath, Shreesha

doi:10.1109/csnt.2017.8418554

Cited by 13 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of the real-time system is 98.05%. Paper [5] presents a new approach for the translation of 24 static gestures of the American Sign Language alphabet into a human or machine-readable English manuscript. The gestures are location, background, background colour, illumination, angle, distance, time, and camera resolution invariant.…”

Section: Literature Surveymentioning

confidence: 99%

“…The recognition process involves pre-processing and clear segmentation stages, resulting in an average recognition rate of 98.21%, which is an outstanding accuracy compared to state-of-the-art techniques. Paper [6] is a comparative study of various works done by researchers in recognizing American Sign Language (ASL) using vision-based techniques. The goal of the American Sign Language Recognition (ASLR) system is to automatically understand the gestures of ASL and convert them into equivalent human-readable or machinereadable text.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

American Sign Language Recognition and Converter

2023

IRJMETS

View full text Add to dashboard Cite

This research paper proposes an innovative approach to develop an application that translates American Sign Language (ASL) gestures into text or speech using Convolutional Neural Networks (CNN). The proposed application is intended to overcome the communication barriers by providing real-time recognition and conversion of ASL gestures. The use of deep learning and natural language processing techniques and the accessibility of webcams offer a promising solution to enhance the accessibility of sign language recognition and conversion to a wider audience. In addition to sign recognition, the application will also provide a userfriendly interface.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Section: Literature Surveymentioning

confidence: 99%

American Sign Language Recognition and Converter

2023

IRJMETS

View full text Add to dashboard Cite

show abstract

“…Human Computer Interaction(HCI) has made the user interface to helps in capture the hand gestures in an effective way. This method acquire the data from both data gloves and vision based [8]. In static mode, the feedforward and recurrent neural network architecture also used for recognition.…”

Section: Literature Surveymentioning

confidence: 99%

Generating an Audio and Text for Indian Sign Language

Renjitha.¹,

Rubashree.²,

Priya³

et al. 2020

IJEAT

View full text Add to dashboard Cite

Every normal people have the ability to observe and respond to the environment. Nearby are several unlucky persons who doesn’t encompass this principal blessing. Deaf and Dumb people have to communicate with normal people, it’s a challenging task. Sign Language is designed for deaf and dump people to convey message to the society. Sign Language Recognition is a technology which is used to identify human gestures with the help of Arduino uno. Gesture recognition based on the corresponding gesture symbol produces an audio & text output. The flex sensor is used to recognize the hand gestures. Recognized gesture is transferred to the Arduino uno and the output is generated. By using these techniques we can implement an efficient audio & text output for physically challenged people. Our technology consists of glove which will be worn by dumb people to communicate with normal people. The proposed prototype could also serve as an intermediate between deaf and dump people and normal people in everyday life such as bank or post office. The output will be displayed using LCD and also produces a speech signal.

show abstract

“…The method is exposed to an accuracy problem because of difficulty in differentiating the skin and the marker from the background during image processing. More attention has been given to ASL as found in Shivashankara and Srinath [14] with the review of vision-based ASL recognition. Similar work was done by Nair and Bindu [2].…”

Section: Related Workmentioning

confidence: 99%

Offline Gesture Recognition System for Yorùbá Numeral Counting

Jimoh

Adepoju

Sobowale

et al. 2018

AJRCoS

View full text Add to dashboard Cite

Aims: The study aimed to determine the specific features responsible for the recognition of gestures, to design a computational model for the process and to implement the model and evaluate its performance. Place and Duration of Study: Department of Computer Engineering, Federal Polytechnic, Ede, between August 2017 and February 2018. Methodology: Samples of hand gesture were collected from the deaf school. In total, 40 samples containing 4 gestures for each numeral were collected and processed. The collected samples were pre-processed and rescaled from 340 × 512 pixels to 256 × 256 pixels. The samples were examined for the specific characteristics responsible for the recognition of gestures using edge detection and histogram of the oriented gradient as feature extraction techniques. The model was implemented in MATLAB using Support Vector Machine (SVM) as its classifier. The performance of the system was evaluated using precision, recall and accuracy as metrics. Results: It was observed that the system showed a high classification rate for the considered hand gestures. For numerals 1, 3, 5 and 7, 100% accuracy were recorded, numerals 2 and 9 had 90% accuracy, numeral 4 had 85.67% accuracy, numeral 6 had 93.56%, numeral 8 had 88% while numeral 10 recorded 90.72% accuracy. An average recognition rate of 95% on tested data was recorded over a dataset of 40 hand gestures. Conclusion: The study has successfully classified hand gesture for Yorùbá Sign Language (YSL). Thus, confirming that YSL could be incorporated into the deaf educational system. The developed system will enhance the communication skills between hearing and hearing impaired people.

show abstract

A review on vision based American sign language recognition, its techniques, and outcomes

Cited by 13 publications

References 22 publications

American Sign Language Recognition and Converter

American Sign Language Recognition and Converter

Generating an Audio and Text for Indian Sign Language

Offline Gesture Recognition System for Yorùbá Numeral Counting

Contact Info

Product

Resources

About