Synthesizing multilevel abstraction ear sketches for enhanced biometric recognition

Freire-Obregón, David (author), Neves, Joao (author), Emeršič, Žiga (author), Meden, Blaž (author), Castrillón-Santana, Modesto (author), Proença, Hugo (author)

Sketch understanding poses unique challenges for general-purpose vision algorithms due to the sparse and semantically ambiguous nature of sketches. This paper introduces a novel approach to biometric recognition that leverages sketch-based representations of ears, a largely unexplored but promising area in biometric research. Specifically, we address the “sketch-2-image” matching problem by synthesizing ear sketches at multiple abstraction levels, achieved through a triplet-loss function adapted to integrate these levels. The abstraction level is determined by the number of strokes used, with fewer strokes reflecting higher abstraction. Our methodology combines sketch representations across abstraction levels to improve robustness and generalizability in matching. Extensive evaluations were conducted on four ear datasets (AMI, AWE, IITDII, and BIPLab) using various pre-trained neural network backbones, showing consistently superior performance over state-of-the-art methods. These results highlight the potential of ear sketch-based recognition, with cross-dataset tests confirming its adaptability to real-world conditions and suggesting applicability beyond ear biometrics.

• Language: English
• Keywords: ear biometrics, sketch-based identification, triplet-loss function, cross-dataset generalizability
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FRI - Faculty of Computer and Information Science
• Publication status: Published
• Publication version: Version of Record
• Year: 2025
• Number of pages: 10 str.
• Numbering: Vol. 154, art. 105424
• PID: 20.500.12556/RUL-176531
• UDC: 004.93:57.087.1
• ISSN on article: 0262-8856
• DOI: 10.1016/j.imavis.2025.105424
• COBISS.SI-ID: 258163715
• Publication date in RUL: 03.12.2025

Record is a part of a journal

• Title: Image and vision computing
• Shortened title: Image vis. comput.
• Publisher: Butterworth Scientific
• ISSN: 0262-8856
• COBISS.SI-ID: 25590016

Licences

• License: CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
• Link: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Description: The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.

Secondary language

• Language: Slovenian
• Keywords: biometrija uhljev, identifikacija na podlagi skice, trojnoizgubna funkcija, splošna prenosljivost med podatkovnimi nabori

Projects

• Funder: FCT - Fundação para a Ciência e a Tecnologia, I.P.
• Project number: UIDB/50008/2020
• Name: Instituto de Telecomunicações
• Acronym: IT

• Funder: FCT - Fundação para a Ciência e a Tecnologia, I.P.
• Project number: UIDB/04516/2020
• Name: NOVA Laboratory for Computer Science and Informatics
• Acronym: NOVA LINCS