Face recognition and classification using deep learning.
| dc.contributor.author | GAMOURA, Abderrazak | |
| dc.contributor.author | KAMMAR, Amar | |
| dc.date.accessioned | 2021-12-06T07:48:30Z | |
| dc.date.available | 2021-12-06T07:48:30Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | We first of all thank Allah "the Almighty, for giving us courage and patience, and for guiding us to where we have arrived. We would like to extend our sincere thanks to the people who have given us their assistance and who have contributed to the development of this brief. We address a big thank you to the person in charge of this memory, Mme. Benabid Sonia for her precious help and for the time she devoted to us as well as for the help she gave us. It is a pleasure for us as much as a duty to thank all the people who have been able to contribute directly or indirectly to the accomplishment of this project. | en_US |
| dc.identifier.issn | MM/626 | |
| dc.identifier.uri | http://10.10.1.6:4000/handle/123456789/1414 | |
| dc.language.iso | en | en_US |
| dc.publisher | UNIVERSITY El-BACHIR EL IBRAHIMI BORDJ BOU ARRERIDJ FACULTY OF MATHEMATICS AND INFORMATIC | en_US |
| dc.title | Face recognition and classification using deep learning. | en_US |
| dc.type | Thesis | en_US |
Files
Original bundle
1 - 1 of 1
- Name:
- Face recognition and classification using Deep learning.pdf
- Size:
- 1.59 MB
- Format:
- Adobe Portable Document Format
- Description:
- We presented in this project all the necessary steps for the development and facilitates the management of attendance via facial recognition technology. Given the amount of potential software (security, social networks, etc.) that can be based on this application, it must meet the requirements of speed and robustness of the results In this sense, the first part consists of locating faces uses CNN layers. The second part of the deals with the recognition of localized faces by applying the CNN method. Convolutional neural networks (CNN) was first proposed in the 1960s, when Hubel and Wiesel discovered its unique network structure, which can effectively reduce the complexity of feedback neural network, while studying the neurons used for local sensitivity and direction selection in the cat cerebral cortex. Indeed, capturing an image of a face, is simple and non-invasive. It is therefore a biometric modality easily tolerated by users, but the performance of facial recognition is still far beyond what one would expect for such applications. This project allowed us to discover more deeply several aspects of the development of complex software. We first had to learn about the algorithmic side of face recognition, and more generally of computer vision. which is a growing field. This research therefore led us to the creation of a “raw” facial recognition engine. We had to solve several algorithmic problems having more or less links with mathematics, an important discipline in image processing in general.
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed to upon submission
- Description: