Benchmarking human face similarity using identical twins
Abstract The problem of distinguishing identical twins and non‐twin look‐alikes in automated facial recognition (FR) applications has become increasingly important with the widespread adoption of facial biometrics. Due to the high facial similarity of both identical twins and look‐alikes, these face...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-09-01
|
| Series: | IET Biometrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/bme2.12090 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832559607261691904 |
|---|---|
| author | Shoaib Meraj Sami John McCauley Sobhan Soleymani Nasser Nasrabadi Jeremy Dawson |
| author_facet | Shoaib Meraj Sami John McCauley Sobhan Soleymani Nasser Nasrabadi Jeremy Dawson |
| author_sort | Shoaib Meraj Sami |
| collection | DOAJ |
| description | Abstract The problem of distinguishing identical twins and non‐twin look‐alikes in automated facial recognition (FR) applications has become increasingly important with the widespread adoption of facial biometrics. Due to the high facial similarity of both identical twins and look‐alikes, these face pairs represent the hardest cases presented to facial recognition tools. This work presents an application of one of the largest twin data sets compiled to date to address two FR challenges: (1) determining a baseline measure of facial similarity between identical twins and (2) applying this similarity measure to determine the impact of doppelgangers, or look‐alikes, on FR performance for large face data sets. The facial similarity measure is determined via a deep convolutional neural network. This network is trained on a tailored verification task designed to encourage the network to group together highly similar face pairs in the embedding space and achieves a test AUC of 0.9799. The proposed network provides a quantitative similarity score for any two given faces and has been applied to large‐scale face data sets to identify similar face pairs. An additional analysis that correlates the comparison score returned by a facial recognition tool and the similarity score returned by the proposed network has also been performed. |
| format | Article |
| id | doaj-art-1910a4e7bc11414eab0ae761191d1537 |
| institution | Kabale University |
| issn | 2047-4938 2047-4946 |
| language | English |
| publishDate | 2022-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-1910a4e7bc11414eab0ae761191d15372025-02-03T01:29:39ZengWileyIET Biometrics2047-49382047-49462022-09-0111545948410.1049/bme2.12090Benchmarking human face similarity using identical twinsShoaib Meraj Sami0John McCauley1Sobhan Soleymani2Nasser Nasrabadi3Jeremy Dawson4Lane Department of Computer Science and Electrical Engineering West Virginia University Morgantown West Virginia USALane Department of Computer Science and Electrical Engineering West Virginia University Morgantown West Virginia USALane Department of Computer Science and Electrical Engineering West Virginia University Morgantown West Virginia USALane Department of Computer Science and Electrical Engineering West Virginia University Morgantown West Virginia USALane Department of Computer Science and Electrical Engineering West Virginia University Morgantown West Virginia USAAbstract The problem of distinguishing identical twins and non‐twin look‐alikes in automated facial recognition (FR) applications has become increasingly important with the widespread adoption of facial biometrics. Due to the high facial similarity of both identical twins and look‐alikes, these face pairs represent the hardest cases presented to facial recognition tools. This work presents an application of one of the largest twin data sets compiled to date to address two FR challenges: (1) determining a baseline measure of facial similarity between identical twins and (2) applying this similarity measure to determine the impact of doppelgangers, or look‐alikes, on FR performance for large face data sets. The facial similarity measure is determined via a deep convolutional neural network. This network is trained on a tailored verification task designed to encourage the network to group together highly similar face pairs in the embedding space and achieves a test AUC of 0.9799. The proposed network provides a quantitative similarity score for any two given faces and has been applied to large‐scale face data sets to identify similar face pairs. An additional analysis that correlates the comparison score returned by a facial recognition tool and the similarity score returned by the proposed network has also been performed.https://doi.org/10.1049/bme2.12090facial similarityfacial recognitionidentical twinslook‐alikes |
| spellingShingle | Shoaib Meraj Sami John McCauley Sobhan Soleymani Nasser Nasrabadi Jeremy Dawson Benchmarking human face similarity using identical twins IET Biometrics facial similarity facial recognition identical twins look‐alikes |
| title | Benchmarking human face similarity using identical twins |
| title_full | Benchmarking human face similarity using identical twins |
| title_fullStr | Benchmarking human face similarity using identical twins |
| title_full_unstemmed | Benchmarking human face similarity using identical twins |
| title_short | Benchmarking human face similarity using identical twins |
| title_sort | benchmarking human face similarity using identical twins |
| topic | facial similarity facial recognition identical twins look‐alikes |
| url | https://doi.org/10.1049/bme2.12090 |
| work_keys_str_mv | AT shoaibmerajsami benchmarkinghumanfacesimilarityusingidenticaltwins AT johnmccauley benchmarkinghumanfacesimilarityusingidenticaltwins AT sobhansoleymani benchmarkinghumanfacesimilarityusingidenticaltwins AT nassernasrabadi benchmarkinghumanfacesimilarityusingidenticaltwins AT jeremydawson benchmarkinghumanfacesimilarityusingidenticaltwins |