Arabic Sign Language Recognition System Using Deep Learning

Simple item page
dc.contributor.authorBouakba, Oumaima
dc.contributor.authorKrouma ,Nour El Houda
dc.date.accessioned2024-04-02T07:44:37Z
dc.date.available2024-04-02T07:44:37Z
dc.date.issued2023
dc.description.abstractThe aim of this thesis is to create an AI system that is capable if interpreting the user’s Arabic sign language input gestures to their matching meaning. The proposed system leverages the power of deep learning algorithms, specifically neu- ral networks, for robust and high-performance object detection and recognition. The research includes the collection and preprocessing of a large-scale dataset with diverse data. Experimental evaluations are conducted to assess the performance of the developed AI system, providing insights into the system’s accuracy and detection capabilities across different object categories and varying environmental conditions. The thesis also investi- gates and compares other conventional techniques typically used in the domain of image recognition mainly Convolutional neural networks. The results demonstrate that the developed AI system achieves competitive object de- tection and recognition performance, with high accuracy and real-time processing capa- bilities. The system shows potential for practical deployment in various domains and for other various sign languages. Overall, this thesis contributes to the field of computer vision by presenting an effective AI system for detecting and translating Arabic sign language alphabet. The developed system paves the way for advancements in the field of education.
dc.identifier.urihttp://dspace.univ-skikda.dz:4000/handle/123456789/698
dc.language.isoen
dc.publisherFaculty of sciences
dc.titleArabic Sign Language Recognition System Using Deep Learning
dc.typeMasters degree dipolma
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Arabic Sign Language Recognition System Using Deep Learning.pdf
Size:
3.71 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Informatique