Sign gesture recognition system / Ronald S. Apines, Jr., Jonas Andrei C. Ballarta, Aerom Von J. Canimo, Ray John B. Cantonjos.

By:

Apines, Ronald Jr., S

Contributor(s):

Material type: Text

TextManila : Technological University of the Philippines, 2022Description: 100 pages : illustrations ; 28 cm. + 1 CD-ROM (4 3/4 in.)Subject(s):

LOC classification:

BTH QA 76 A65 2022

Dissertation note: College of Science -- Bachelor of Science in Computer Science, Technological University of the Philippines, 2022. Abstract: Speech is the most prevalent means of communication. This communication method, however, is impractical for the deaf community, who interact through sign language. For many years, there has undoubtedly been a communication barrier between signers and non-signers. The necessities of communities and rapidly evolving technologies inspire researchers to devise innovative solutions to meet these demands. Researchers conduct studies, particularly in the field of human-computer interaction (HCI). The Sign Language Recognition System (SLR) is widely valued because it bridges the gap between signers and non-signers. This study applied a deep learning computer vision method to recognize hand gestures by establishing an Artificial Neural Network architecture model (Long short-term memory). The model learns to identify hand gesture photos over an epoch. The Sign Gesture Recognition System was developed using TensorFlow lite, an open-source framework for deep learning with on-device inference. OpenCV for real-time computer vision was utilized to establish the proposed Application successfully. Python, Media Pipe, LSTM, TensorFlow, and Keras for hand gesture recognition., VS Code for an Integrated Development Environment (IDE), a scripting language for application development, and open-source web technologies including HTML, JavaScript, and CSS to design and build the Application. It all starts with data acquisition. Following that is hand gesture recognition; once the model recognizes the gesture, a corresponding word or letter will be displayed on the screen. Using a confusion matrix and ISO 25010, the researchers evaluated all procedures to produce accurate and trustworthy results. The system was assessed as "Moderately Reliable" by ten signers. --Author's Abstract.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Shelving location	Call number	Copy number	Status	Notes	Date due	Barcode
Bachelor's Thesis COS	TUP Manila Library	Thesis Section-2nd floor	BTH QA 76 A65 2022 (Browse shelf(Opens below))	c.1	Not for loan	For Room Use Only		BTH0003440

Thesis (Undergraduate)

College of Science -- Bachelor of Science in Computer Science, Technological University of the Philippines, 2022.

Includes bibliographical references.

Speech is the most prevalent means of communication. This communication method, however, is impractical for the deaf community, who interact through sign language. For many years, there has undoubtedly been a communication barrier between signers and non-signers. The necessities of communities and rapidly evolving technologies inspire researchers to devise innovative solutions to meet these demands. Researchers conduct studies, particularly in the field of human-computer interaction (HCI). The Sign Language Recognition System (SLR) is widely valued because it bridges the gap between signers and non-signers. This study applied a deep learning computer vision method to recognize hand gestures by establishing an Artificial Neural Network architecture model (Long short-term memory). The model learns to identify hand gesture photos over an epoch. The Sign Gesture Recognition System was developed using TensorFlow lite, an open-source framework for deep learning with on-device inference. OpenCV for real-time computer vision was utilized to establish the proposed Application successfully. Python, Media Pipe, LSTM, TensorFlow, and Keras for hand gesture recognition., VS Code for an Integrated Development Environment (IDE), a scripting language for application development, and open-source web technologies including HTML, JavaScript, and CSS to design and build the Application. It all starts with data acquisition. Following that is hand gesture recognition; once the model recognizes the gesture, a corresponding word or letter will be displayed on the screen. Using a confusion matrix and ISO 25010, the researchers evaluated all procedures to produce accurate and trustworthy results. The system was assessed as "Moderately Reliable" by ten signers. --Author's Abstract.

There are no comments on this title.

to post a comment.

Click on an image to view it in the image viewer