Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition

Research output: Chapter in Book/Conference paperConference paper

8 Citations (Scopus)
255 Downloads (Pure)

Abstract

Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as well
as large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the art
face recognition by over 10%. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world face
recognition problem.
Original languageEnglish
Title of host publicationInternational Conference on Computer Vision and Pattern Recognition
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1896-1905
Number of pages9
Publication statusPublished - Jun 2018
EventIEEE Conference on Computer Vision and Pattern Recognition 2018 - Calvin L. Rampton Salt Palace Convention Center, Salt Lake City, United States
Duration: 18 Jun 201822 Jun 2018

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition 2018
Abbreviated titleCVPR 2018
CountryUnited States
CitySalt Lake City
Period18/06/1822/06/18

Fingerprint

Face recognition
Merging
Tuning
Testing

Cite this

Gilani, S., & Mian, A. (2018). Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition. In International Conference on Computer Vision and Pattern Recognition (pp. 1896-1905). United States: IEEE, Institute of Electrical and Electronics Engineers.
Gilani, Syed ; Mian, Ajmal. / Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition. International Conference on Computer Vision and Pattern Recognition. United States : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 1896-1905
@inproceedings{6dfc309b16b54bf38925ab11e7b19a58,
title = "Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition",
abstract = "Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as wellas large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the artface recognition by over 10{\%}. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world facerecognition problem.",
author = "Syed Gilani and Ajmal Mian",
year = "2018",
month = "6",
language = "English",
pages = "1896--1905",
booktitle = "International Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Gilani, S & Mian, A 2018, Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition. in International Conference on Computer Vision and Pattern Recognition. IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 1896-1905, IEEE Conference on Computer Vision and Pattern Recognition 2018, Salt Lake City, United States, 18/06/18.

Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition. / Gilani, Syed; Mian, Ajmal.

International Conference on Computer Vision and Pattern Recognition. United States : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 1896-1905.

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition

AU - Gilani, Syed

AU - Mian, Ajmal

PY - 2018/6

Y1 - 2018/6

N2 - Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as wellas large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the artface recognition by over 10%. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world facerecognition problem.

AB - Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as wellas large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the artface recognition by over 10%. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world facerecognition problem.

UR - http://openaccess.thecvf.com/CVPR2018.py

UR - http://cvpr2018.thecvf.com/organizers

M3 - Conference paper

SP - 1896

EP - 1905

BT - International Conference on Computer Vision and Pattern Recognition

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

ER -

Gilani S, Mian A. Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition. In International Conference on Computer Vision and Pattern Recognition. United States: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 1896-1905