Scribd Logo
Upload

Welcome to Scribd!

  • 8 views

    Demo File

    Uploaded by

    pdhruvil6969
    This document discusses a research project that aims to develop a desktop application using computer vision and convolutional neural networks to recognize American Sign Language (ASL) gestures in real-time and translate them to text. The researchers used ASL datasets to train a CNN model to classify hand gestures as letters of the alphabet. Their initial results showed the model achieving around 96% accuracy on classifying the 26 letters. The goal of the project is to help facilitate communication between deaf or hard of hearing individuals and others who don't understand sign language.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    Demo File

    Uploaded by

    pdhruvil6969
    8 views7 pages
    This document discusses a research project that aims to develop a desktop application using computer vision and convolutional neural networks to recognize American Sign Language (ASL) gestures in real-time and translate them to text. The researchers used ASL datasets to train a CNN model to classify hand gestures as letters of the alphabet. Their initial results showed the model achieving around 96% accuracy on classifying the 26 letters. The goal of the project is to help facilitate communication between deaf or hard of hearing individuals and others who don't understand sign language.

    Original Description:

    Gjd

    Original Title

    DemoFile

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses a research project that aims to develop a desktop application using computer vision and convolutional neural networks to recognize American Sign Language (ASL) gestures in real-time and translate them to text. The researchers used ASL datasets to train a CNN model to classify hand gestures as letters of the alphabet. Their initial results showed the model achieving around 96% accuracy on classifying the 26 letters. The goal of the project is to help facilitate communication between deaf or hard of hearing individuals and others who don't understand sign language.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    8 views7 pages

    Demo File

    Uploaded by

    pdhruvil6969
    This document discusses a research project that aims to develop a desktop application using computer vision and convolutional neural networks to recognize American Sign Language (ASL) gestures in real-time and translate them to text. The researchers used ASL datasets to train a CNN model to classify hand gestures as letters of the alphabet. Their initial results showed the model achieving around 96% accuracy on classifying the 26 letters. The goal of the project is to help facilitate communication between deaf or hard of hearing individuals and others who don't understand sign language.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 7

    Sign to Text Language Translation in Real

    Time Using Convolution Neural Network

    Fenil Panseriya Harshil Patel Dhruvil Patel

    Dept. of IT,DDU Dept. of IT,DDU Dept. of IT,DDU

    Nadiad,India. Nadiad,India. Nadiad,India.

    Abstract:-
    Sign language is one of the most reliable ways of communicating with special
    needs people, as it can be done anywhere. However, The most people do not
    understand sign language. Therefore, we have devised an idea to make a
    desktop application that can recognize sign language and convert it to text in
    real time.Therefore, we have devised an idea to make a desktop application that
    can recognize sign language and convert it to text in real time. In This research
    uses American Sign Language (ASL) datasets and the Convolutional Neural
    Networks (CNN) classification system.A CNN is highly efficient in tackling
    computer vision problems and is capable of detecting desired features with high
    degree of accuracy upon sufficient training. In the classification, the hand image
    is first passed through a filter and after the filter is applied, the hand is passed
    through a classifier which predicts the class of the hand gestures. This research
    Focus on the accuracy of recognition.Application Resulted in almost 96%
    accuracy for the 26 Latters of the alphabet.

    Keywords:- CNN, ASL, training ,Sign Language Recognition.

    1
    1. Introduction
    AI or artificial intelligence capable of solving problems. Computer vision is a
    subcategory of Artificial Intelligence (AI). The goal of computer vision is to
    extract useful information from images. However, it is challenging to
    implement. Computer vision has been used to manufacture robots and photo
    scans and is also used in the automotive, medical, mathematical and industrial
    fields [1, 2].. American Sign Language (ASL) is natural syntax that has the same
    etymological homes as being speaking languages, having completely different
    grammar, ASL can be express with destiny of actions of the body. In native
    America, people who are deaf or can’t see, it’s a reliable source of absurdity.
    There is not any formal or familiar form of sign language. Different signal
    languages are speculating in particular areas. For a case, British Sign Language
    (BSL) is an entirely different language from an ASL, and USA people who
    familiarise with ASL would not easily understand BSL. Some nations adopt
    capabilities of ASL of their sign languages. Sign language is a way of verbal
    exchange via human beings diminished by speech and listening to loss. Around
    360 million human beings globally be afflicted via unable to hearing loss out of
    which 328000000 are adults and 32000000 children. hearing impairment extra
    than 40 decibels in the better listening to ear is referred as disabling listening
    to loss. Thus, with growing range of people with deafness, there is moreover
    rise in demand for translators. Minimizing the verbal exchange gap among
    listening to impaired and regular humans turns into a want to make certain
    effective conversation among all. Sign language translation is one of the
    amongst most growing line of research nowadays and its miles the maximum
    natural manner of communication for the humans with hearing impairments.

    A hand gesture recognition gadget can offer an opportunity for deaf people to
    talk with vocal humans without the need of an interpreter. The system is built
    for the automated conversion of ASL into textual content and speech.. As such,
    this research aims to recognize hand gestures or ASL, which the system will
    change into text that can be read in real-time, making communication with
    people with special needs easier. Hand gesture recognition is also in Human-
    Computer Interaction (HCI) because it interacts with the user directly. Human-
    Computer Interaction (HCI) is the study, planning, or design of interaction
    between users and computers. One of the functional interactions for a hand

    2
    gesture recognition system is displaying text composed of alphabets read by
    the system [5, 6]. In this research, we will utilize Computer Vision and Pattern
    Recognition technology to create a desktop application that can detect hand
    movements in real-time using a webcam/live camera. Afterward, we will use
    American Sign Language (ASL) datasets and the Convolutional Neural Networks
    (CNN) classification system. This research focuseson the accuracy of
    recognizing letters of the alphabet and provides the results in a text in real-
    time.

    3
    2. Litrature Surwey

    4
    3. Methodology
    3.1)Dataset

    3.2)Implementing Algorithm

    3.3)Evaluate

    5
    4) Result and Discussion

    6
    5) Conclusion

    You might also like