Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/556416
Full metadata record
DC FieldValueLanguage
dc.coverage.spatial
dc.date.accessioned2024-04-02T12:09:08Z-
dc.date.available2024-04-02T12:09:08Z-
dc.identifier.urihttp://hdl.handle.net/10603/556416-
dc.description.abstractAttributed to extensive acceptance and research, lives can and inked fingerprints are successfully used for human recognition. However, applications such as contactless biometrics amidst the pandemic and crime scene identification call for newer covariates of fingerprints. These new unconstrained/semi-constrained covariates consist of contactless fingerprint1, multi-view contactless fingerprints (contactless 3D or finger videos), and latent fingerprints. These fingerprints are prone to acquisition variations, resulting in a non-optimal performance with traditional fingerprint algorithms. These unconstrained fingerprints require dedicated algorithms that can yield state-of-the-art performance under different challenges. Hence, this thesis presents a six-fold contribution of recognition using semi/un-constrained fingerprints (finger photos, finger videos, and latent fingerprints). Structured in two parts, the first part discusses aspects of contactless fingerprints, while the second focuses on latent fingerprints. The thesis provides large-scale databases for different applications of unconstrained fingerprints. Using the databases, dedicated end-to-end recognition algorithms are presented for contactless fingerprints, fingervideos, and latent fingerprints. The recognition algorithm for latent fingerprints is further backed by scientific learning of the process followed by forensic examiners. The details of each of the contributions are listed below. The first three contributions in Part I of the thesis are towards contactless fingerprint recognition. As the first contribution, we create databases to establish large-scale contactless fingerprint recognition under various acquisition challenges and vulnerabilities. Primarily, the proposed IIIT-D Smart Phone Finger-selfie Database v2 (ISPFD-v2) accounts for 19,456 images in total. These databases understand the behavior of finger selfie recognition under various vulnerabilities and challenges.
dc.format.extent238 p.
dc.languageEnglish
dc.relation
dc.rightsuniversity
dc.titleLearning algorithms for multi tasks of unconstrained fingerprint recognition
dc.title.alternative
dc.creator.researcherMalhotra, Aakarsh
dc.subject.keywordComputer Science
dc.subject.keywordComputer Science Information Systems
dc.subject.keywordEngineering and Technology
dc.description.note
dc.contributor.guideVatsa, Mayank and Singh, Richa
dc.publisher.placeDelhi
dc.publisher.universityIndraprastha Institute of Information Technology, Delhi (IIIT-Delhi)
dc.publisher.institutionComputer Science and Engineering
dc.date.registered
dc.date.completed2024
dc.date.awarded2024
dc.format.dimensions29 cm.
dc.format.accompanyingmaterialNone
dc.source.universityUniversity
dc.type.degreePh.D.
Appears in Departments:Department of Computer Science and Engineering

Files in This Item:
File Description SizeFormat 
01-title.pdfAttached File52.79 kBAdobe PDFView/Open
02_prelim pages.pdf643.56 kBAdobe PDFView/Open
03_content.pdf9.54 MBAdobe PDFView/Open
04_abstract.pdf88.29 kBAdobe PDFView/Open
05_chapter 1.pdf602.31 kBAdobe PDFView/Open
06_chapter 2.pdf447.87 kBAdobe PDFView/Open
07_chapter 3.pdf3.36 MBAdobe PDFView/Open
08_chapter 4.pdf398.76 kBAdobe PDFView/Open
09_chapter 5.pdf3.18 MBAdobe PDFView/Open
10_annexures.pdf301.31 kBAdobe PDFView/Open
11_chapter 6.pdf797.88 kBAdobe PDFView/Open
12_chapter 7.pdf667.8 kBAdobe PDFView/Open
80_recommendation.pdf131.38 kBAdobe PDFView/Open


Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

Altmetric Badge: