An efficient deep learning approach for 3D face detection using multiple angular 2D images
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.
| Main Authors: | , , , |
|---|---|
| מחברים אחרים: | |
| פורמט: | Thesis |
| שפה: | English |
| יצא לאור: |
Brac University
2023
|
| נושאים: | |
| גישה מקוונת: | http://hdl.handle.net/10361/21771 |
| id |
10361-21771 |
|---|---|
| record_format |
dspace |
| spelling |
10361-217712023-10-11T21:04:30Z An efficient deep learning approach for 3D face detection using multiple angular 2D images Rafsan, Nayeem Nayeem, Hasibul Hoque Dad, Hamed Efaz Md. Elahi Yen, Afzal Hossain Alam, Md. Ashraful Department of Computer Science and Engineering, Brac University 3D point cloud Face detection & recognition CNN Next Face Haar cascade This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. Cataloged from PDF version of thesis. Includes bibliographical references (pages 38-39). 3D face reconstruction is a useful computer vision technique for facial recognition. Accuracy decreases drastically while extracting features from 2D and moving images. To overcome this problem, we are proposing reconstruction of 3D models generated by multiple 2D angular images. Our primary approach consists of the following steps: rebuilding 3D mesh from 2D image, feature extraction, deep learning algorithm for recognition. We will be taking images of 0°, +10°, +20°, +30°, +40°,+50°, +60°, +70°, +80°, +90°, -10°, -20°,-30°, -40°, -50°,-60°, -70°,-80°, -90° angular deviations. We have compared the results from 2D architectures and 3D architectures and showed that 3D deep learning models perform better on angular images and in motion. The proposed method is time efficient and robust in nature, and it overcomes the previous limitations. 2023-10-11T04:25:27Z 2023-10-11T04:25:27Z 2022 2022-09-25 Thesis ID 19101133 ID 19101433 ID 19101304 ID 18201131 http://hdl.handle.net/10361/21771 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 39 pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
English |
| topic |
3D point cloud Face detection & recognition CNN Next Face Haar cascade |
| spellingShingle |
3D point cloud Face detection & recognition CNN Next Face Haar cascade Rafsan, Nayeem Nayeem, Hasibul Hoque Dad, Hamed Efaz Md. Elahi Yen, Afzal Hossain An efficient deep learning approach for 3D face detection using multiple angular 2D images |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022. |
| author2 |
Alam, Md. Ashraful |
| author_facet |
Alam, Md. Ashraful Rafsan, Nayeem Nayeem, Hasibul Hoque Dad, Hamed Efaz Md. Elahi Yen, Afzal Hossain |
| format |
Thesis |
| author |
Rafsan, Nayeem Nayeem, Hasibul Hoque Dad, Hamed Efaz Md. Elahi Yen, Afzal Hossain |
| author_sort |
Rafsan, Nayeem |
| title |
An efficient deep learning approach for 3D face detection using multiple angular 2D images |
| title_short |
An efficient deep learning approach for 3D face detection using multiple angular 2D images |
| title_full |
An efficient deep learning approach for 3D face detection using multiple angular 2D images |
| title_fullStr |
An efficient deep learning approach for 3D face detection using multiple angular 2D images |
| title_full_unstemmed |
An efficient deep learning approach for 3D face detection using multiple angular 2D images |
| title_sort |
efficient deep learning approach for 3d face detection using multiple angular 2d images |
| publisher |
Brac University |
| publishDate |
2023 |
| url |
http://hdl.handle.net/10361/21771 |
| work_keys_str_mv |
AT rafsannayeem anefficientdeeplearningapproachfor3dfacedetectionusingmultipleangular2dimages AT nayeemhasibulhoque anefficientdeeplearningapproachfor3dfacedetectionusingmultipleangular2dimages AT dadhamedefazmdelahi anefficientdeeplearningapproachfor3dfacedetectionusingmultipleangular2dimages AT yenafzalhossain anefficientdeeplearningapproachfor3dfacedetectionusingmultipleangular2dimages AT rafsannayeem efficientdeeplearningapproachfor3dfacedetectionusingmultipleangular2dimages AT nayeemhasibulhoque efficientdeeplearningapproachfor3dfacedetectionusingmultipleangular2dimages AT dadhamedefazmdelahi efficientdeeplearningapproachfor3dfacedetectionusingmultipleangular2dimages AT yenafzalhossain efficientdeeplearningapproachfor3dfacedetectionusingmultipleangular2dimages |
| _version_ |
1814309381075894272 |