Matching before and after Surgery Faces

Anchit Bansal, Nisha P. Shetty

Research output: Contribution to journalConference article

Abstract

Cosmetic surgery is a voluntary procedure usually performed with the motive of improving a person's appearance, removing aging signs and correcting impairments caused due to accidents such as burns or abnormalities. It also serves as a means for frauds and criminals to evade identification. One of the major challenges faced by face recognition algorithms is the effective identification of such altered faces. This paper aims to verify faces before and after facial surgery that will help to seal various security and biometric loopholes also for in general face verification for official records and similar purposes. The paper takes two pictures of a person preferably before and after surgery as input and further on the software removes noise (using interpolation) from the pictures for better quality and then finds fisher vector encodings of the different features (nose, mouth, eye pair) extracted from both the images. The extracted fisher vector encodings are the further passed to a trained classifier which outputs positive or negative indicating matched or unmatched respectively.

Original languageEnglish
Pages (from-to)141-148
Number of pages8
JournalProcedia Computer Science
Volume132
DOIs
Publication statusPublished - 01-01-2018
Externally publishedYes
Event2018 International Conference on Computational Intelligence and Data Science, ICCIDS 2018 - Gurugram, India
Duration: 07-04-201808-04-2018

Fingerprint

Surgery
Biometrics
Face recognition
Seals
Interpolation
Accidents
Classifiers
Aging of materials

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Bansal, Anchit ; Shetty, Nisha P. / Matching before and after Surgery Faces. In: Procedia Computer Science. 2018 ; Vol. 132. pp. 141-148.
@article{4be13155bca4486e926e336afd72536c,
title = "Matching before and after Surgery Faces",
abstract = "Cosmetic surgery is a voluntary procedure usually performed with the motive of improving a person's appearance, removing aging signs and correcting impairments caused due to accidents such as burns or abnormalities. It also serves as a means for frauds and criminals to evade identification. One of the major challenges faced by face recognition algorithms is the effective identification of such altered faces. This paper aims to verify faces before and after facial surgery that will help to seal various security and biometric loopholes also for in general face verification for official records and similar purposes. The paper takes two pictures of a person preferably before and after surgery as input and further on the software removes noise (using interpolation) from the pictures for better quality and then finds fisher vector encodings of the different features (nose, mouth, eye pair) extracted from both the images. The extracted fisher vector encodings are the further passed to a trained classifier which outputs positive or negative indicating matched or unmatched respectively.",
author = "Anchit Bansal and Shetty, {Nisha P.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.procs.2018.05.175",
language = "English",
volume = "132",
pages = "141--148",
journal = "Procedia Computer Science",
issn = "1877-0509",
publisher = "Elsevier BV",

}

Matching before and after Surgery Faces. / Bansal, Anchit; Shetty, Nisha P.

In: Procedia Computer Science, Vol. 132, 01.01.2018, p. 141-148.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Matching before and after Surgery Faces

AU - Bansal, Anchit

AU - Shetty, Nisha P.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Cosmetic surgery is a voluntary procedure usually performed with the motive of improving a person's appearance, removing aging signs and correcting impairments caused due to accidents such as burns or abnormalities. It also serves as a means for frauds and criminals to evade identification. One of the major challenges faced by face recognition algorithms is the effective identification of such altered faces. This paper aims to verify faces before and after facial surgery that will help to seal various security and biometric loopholes also for in general face verification for official records and similar purposes. The paper takes two pictures of a person preferably before and after surgery as input and further on the software removes noise (using interpolation) from the pictures for better quality and then finds fisher vector encodings of the different features (nose, mouth, eye pair) extracted from both the images. The extracted fisher vector encodings are the further passed to a trained classifier which outputs positive or negative indicating matched or unmatched respectively.

AB - Cosmetic surgery is a voluntary procedure usually performed with the motive of improving a person's appearance, removing aging signs and correcting impairments caused due to accidents such as burns or abnormalities. It also serves as a means for frauds and criminals to evade identification. One of the major challenges faced by face recognition algorithms is the effective identification of such altered faces. This paper aims to verify faces before and after facial surgery that will help to seal various security and biometric loopholes also for in general face verification for official records and similar purposes. The paper takes two pictures of a person preferably before and after surgery as input and further on the software removes noise (using interpolation) from the pictures for better quality and then finds fisher vector encodings of the different features (nose, mouth, eye pair) extracted from both the images. The extracted fisher vector encodings are the further passed to a trained classifier which outputs positive or negative indicating matched or unmatched respectively.

UR - http://www.scopus.com/inward/record.url?scp=85049060729&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049060729&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2018.05.175

DO - 10.1016/j.procs.2018.05.175

M3 - Conference article

VL - 132

SP - 141

EP - 148

JO - Procedia Computer Science

JF - Procedia Computer Science

SN - 1877-0509

ER -