hh.sePublications
1231 of 3
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Ocular Recognition in Unconstrained Sensing Environments
Halmstad University, School of Information Technology.
2024 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

This thesis focuses on the problem of increasing flexibility in the acquisition and application of biometric recognition systems based on the ocular region. While the ocular area is one of the oldest and most widely studied biometric regions thanks to its rich and discriminative elements and characteristics, most modalities such as retina, iris, eye movements, or oculomotor plant have limitations regarding data acquisition. Some require a specific type of illumination like the iris, a limited distance range like eye movements, or specific sensors and user collaboration like the retina. In this context, this thesis focuses on the periocular region, which stands out as the ocular modality with the fewest acquisition constraints. 

The first part focuses on using middle-layers' deep representation of pre-trained CNNs as a one-shot learning method, along with simple distance-based metrics and similarity scores for periocular recognition. This approach tackles the issue of limited data availability and collection for biometric recognition systems by eliminating the need to train the models for the target data. Furthermore, it allows seamless transitions between identification and verification scenarios with a single model, and tackles the problem of the open-world setting and training bias of CNNs. We demonstrate that off-the-shelf features from middle-layers can outperform CNNs trained for the target domain that followed a more extensive training strategy when target data is limited.

The second part of the thesis analyzes traditional methods for biometric systems in the context of periocular recognition. Nowadays, these methods are often overlooked in favor of deep learning solutions. However, we show that they can still outperform heavily trained CNNs in closed-world and open-world settings and can be used in conjunction with CNNs to further improve recognition performance. Moreover, we investigate the use of the complex structure tensor as a handcrafted texture extractor at the input of CNNs. We show that CNNs can benefit from this explicit textural information in terms of performance and convergence, offering the potential for network compression and explainability of the features used. We demonstrate that CNNs may not easily access the orientation information present in the images that are exploited in some more traditional approaches.

The final part of the thesis addresses the analysis of periocular recognition under different light spectra and the cross-spectral scenario. More specifically, we analyze the performance of the proposed methods under different light spectra. We also investigate the cross-spectral scenario for one-shot learning with middle-layers' deep representations and explore the possibility of bridging the domain gap in the cross-spectral scenario by training generative networks. This allows using simpler models and algorithms trained on a single spectrum.

Place, publisher, year, edition, pages
Halmstad: Halmstad University Press, 2024. , p. 49
Series
Halmstad University Dissertations ; 114
Keywords [en]
Biometrics, Computer Vision, Pattern Recognition, Periocular Recognition
National Category
Signal Processing Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:hh:diva-53257Libris ID: 4nf9bljj2m4b3ws0ISBN: 978-91-89587-43-4 (print)ISBN: 978-91-89587-42-7 (electronic)OAI: oai:DiVA.org:hh-53257DiVA, id: diva2:1853957
Public defence
2024-05-28, S3030, Kristian IV:s väg 3, 08:00 (English)
Opponent
Supervisors
Available from: 2024-04-24 Created: 2024-04-24 Last updated: 2024-05-03Bibliographically approved
List of papers
1. Periocular Recognition Using CNN Features Off-the-Shelf
Open this publication in new window or tab >>Periocular Recognition Using CNN Features Off-the-Shelf
2018 (English)In: 2018 International Conference of the Biometrics Special Interest Group (BIOSIG), Piscataway, N.J.: IEEE, 2018Conference paper, Published paper (Refereed)
Abstract [en]

Periocular refers to the region around the eye, including sclera, eyelids, lashes, brows and skin. With a surprisingly high discrimination ability, it is the ocular modality requiring the least constrained acquisition. Here, we apply existing pre-trained architectures, proposed in the context of the ImageNet Large Scale Visual Recognition Challenge, to the task of periocular recognition. These have proven to be very successful for many other computer vision tasks apart from the detection and classification tasks for which they were designed. Experiments are done with a database of periocular images captured with a digital camera. We demonstrate that these offthe-shelf CNN features can effectively recognize individuals based on periocular images, despite being trained to classify generic objects. Compared against reference periocular features, they show an EER reduction of up to ~40%, with the fusion of CNN and traditional features providing additional improvements.

Place, publisher, year, edition, pages
Piscataway, N.J.: IEEE, 2018
Series
2018 International Conference of the Biometrics Special Interest Group (BIOSIG), ISSN 1617-5468 ; 2018
Keywords
Periocular recognition, deep learning, biometrics, Convolutional Neural Network
National Category
Signal Processing
Identifiers
urn:nbn:se:hh:diva-37704 (URN)10.23919/BIOSIG.2018.8553348 (DOI)2-s2.0-85060015047 (Scopus ID)978-3-88579-676-3 (ISBN)
Conference
International Conference of the Biometrics Special Interest Group (BIOSIG), Darmstadt, Germany, Sept. 26-29, 2018
Projects
SIDUS-AIR
Funder
Knowledge Foundation, SIDUS-AIRSwedish Research Council, 2016-03497Vinnova, 2018-00472Knowledge Foundation, CAISR
Available from: 2018-08-14 Created: 2018-08-14 Last updated: 2024-04-24Bibliographically approved
2. Cross Spectral Periocular Matching using ResNet Features
Open this publication in new window or tab >>Cross Spectral Periocular Matching using ResNet Features
2019 (English)In: 2019 International Conference on Biometrics (ICB), Piscataway, N.J.: IEEE, 2019Conference paper, Published paper (Refereed)
Abstract [en]

Periocular recognition has gained attention in the last years thanks to its high discrimination capabilities in less constraint scenarios than other ocular modalities. In this paper we propose a method for periocular verification under different light spectra using CNN features with the particularity that the network has not been trained for this purpose. We use a ResNet-101 pretrained model for the ImageNet Large Scale Visual Recognition Challenge to extract features from the IIITD Multispectral Periocular Database. At each layer the features are compared using χ 2 distance and cosine similitude to carry on verification between images, achieving an improvement in the EER and accuracy at 1% FAR of up to 63.13% and 24.79% in comparison to previous works that employ the same database. In addition to this, we train a neural network to match the best CNN feature layer vector from each spectrum. With this procedure, we achieve improvements of up to 65% (EER) and 87% (accuracy at 1% FAR) in cross-spectral verification with respect to previous studies.

Place, publisher, year, edition, pages
Piscataway, N.J.: IEEE, 2019
Series
Biometrics (ICB), IAPR International Conference on, ISSN 2376-4201
National Category
Signal Processing
Identifiers
urn:nbn:se:hh:diva-40499 (URN)10.1109/ICB45273.2019.8987303 (DOI)2-s2.0-85079777482 (Scopus ID)978-1-7281-3640-0 (ISBN)978-1-7281-3641-7 (ISBN)
Conference
12th IAPR International Conference on Biometrics, Crete, Greece, June 4-7, 2019
Funder
Swedish Research Council, 2016-03497Knowledge Foundation, SIDUS-AIRKnowledge Foundation, CAISR
Available from: 2019-09-04 Created: 2019-09-04 Last updated: 2024-04-24Bibliographically approved
3. Cross-Spectral Periocular Recognition with Conditional Adversarial Networks
Open this publication in new window or tab >>Cross-Spectral Periocular Recognition with Conditional Adversarial Networks
2020 (English)In: IJCB 2020 : IEEE/IAPR International Joint Conference on Biometrics : 28th September-1st October 2020, online, Piscataway: IEEE, 2020Conference paper, Published paper (Refereed)
Abstract [en]

This work addresses the challenge of comparing periocular images captured in different spectra, which is known to produce significant drops in performance in comparison to operating in the same spectrum. We propose the use of ConditionalGenerative Adversarial Networks, trained to convert periocular images between visible and near-infrared spectra, so that biometric verification is carried out in the same spectrum. The proposed setup allows the use of existing feature methods typically optimized to operate in a single spectrum. Recognition experiments are done using a number of off-the-shelf periocular comparators based both on hand-crafted features and CNN descriptors. Using the Hong Kong Polytechnic University Cross-Spectral Iris Images Database (PolyU) as benchmark dataset, our experiments show that cross-spectral performance is substantially improved if both images are converted to the same spectrum, in comparison to matching features extracted from images in different spectra. In addition to this, we fine-tune a CNN based on the ResNet50 architecture, obtaining a cross-spectral periocular performance of EER=l%, and GAR>99% @ FAR=l%, which is comparable to the state-of-the-art with the PolyU database. © 2020 IEEE.

Place, publisher, year, edition, pages
Piscataway: IEEE, 2020
National Category
Signal Processing
Identifiers
urn:nbn:se:hh:diva-43796 (URN)10.1109/IJCB48548.2020.9304899 (DOI)000723870900045 ()2-s2.0-85098614217 (Scopus ID)978-1-7281-9186-7 (ISBN)978-1-7281-9187-4 (ISBN)
Conference
International Joint Conference on Biometrics (IJCB 2020), 28 September - 1 October, 2020, Houston, USA, Online
Funder
Swedish Research Council
Note

s. 1-9

Available from: 2021-02-01 Created: 2021-02-01 Last updated: 2024-04-24Bibliographically approved
4. One-Shot Learning for Periocular Recognition: Exploring the Effect of Domain Adaptation and Data Bias on Deep Representations
Open this publication in new window or tab >>One-Shot Learning for Periocular Recognition: Exploring the Effect of Domain Adaptation and Data Bias on Deep Representations
2023 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 11, p. 100396-100413Article in journal (Refereed) Published
Abstract [en]

One weakness of machine-learning algorithms is the need to train the models for a new task. This presents a specific challenge for biometric recognition due to the dynamic nature of databases and, in some instances, the reliance on subject collaboration for data collection. In this paper, we investigate the behavior of deep representations in widely used CNN models under extreme data scarcity for One-Shot periocular recognition, a biometric recognition task. We analyze the outputs of CNN layers as identity-representing feature vectors. We examine the impact of Domain Adaptation on the network layers’ output for unseen data and evaluate the method’s robustness concerning data normalization and generalization of the best-performing layer. We improved state-of-the-art results that made use of networks trained with biometric datasets with millions of images and fine-tuned for the target periocular dataset by utilizing out-of-the-box CNNs trained for the ImageNet Recognition Challenge and standard computer vision algorithms. For example, for the Cross-Eyed dataset, we could reduce the EER by 67% and 79% (from 1.70%and 3.41% to 0.56% and 0.71%) in the Close-World and Open-World protocols, respectively, for the periocular case. We also demonstrate that traditional algorithms like SIFT can outperform CNNs in situations with limited data or scenarios where the network has not been trained with the test classes like the Open-World mode. SIFT alone was able to reduce the EER by 64% and 71.6% (from 1.7% and 3.41% to 0.6% and 0.97%) for Cross-Eyed in the Close-World and Open-World protocols, respectively, and a reduction of 4.6% (from 3.94% to 3.76%) in the PolyU database for the Open-World and single biometric case.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE, 2023
Keywords
Biometrics, Biometrics (access control), Databases, Deep learning, Deep Representation, Face recognition, Feature extraction, Image recognition, Iris recognition, One-Shot Learning, Periocular, Representation learning, Task analysis, Training, Transfer Learning
National Category
Computer Sciences
Identifiers
urn:nbn:se:hh:diva-51749 (URN)10.1109/ACCESS.2023.3315234 (DOI)2-s2.0-85171525429 (Scopus ID)
Funder
Swedish Research CouncilVinnova
Available from: 2023-10-19 Created: 2023-10-19 Last updated: 2024-04-24Bibliographically approved
5. Understanding and Improving CNNs with Complex Structure Tensor: A Biometrics Study
Open this publication in new window or tab >>Understanding and Improving CNNs with Complex Structure Tensor: A Biometrics Study
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Our study provides evidence that CNNs struggle to effectively extract orientation features. We show that the use of Complex Structure Tensor, which contains compact orientation features with certainties, as input to CNNs consistently improves identification accuracy compared to using grayscale inputs alone. Experiments also demonstrated that our inputs, which were provided by mini complex conv-nets, combined with reduced CNN sizes, outperformed full-fledged, prevailing CNN architectures. This suggests that the upfront use of orientation features in CNNs, a strategy seen in mammalian vision, not only mitigates their limitations but also enhances their explainability and relevance to thin-clients. Experiments were done on publicly available data sets comprising periocular images for biometric identification and verification (Close and Open World) using 6 State of the Art CNN architectures. We reduced SOA Equal Error Rate (EER) on the PolyU dataset by 5-26 % depending on data and scenario.

National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:hh:diva-53249 (URN)
Funder
Vinnova, 2022-00919Swedish Research Council, 2016-03497Swedish Research Council, 2021-05110
Note

Som manuscript i avhandling/As manuscript in thesis

Available from: 2024-04-22 Created: 2024-04-22 Last updated: 2024-04-24

Open Access in DiVA

fulltext(4413 kB)47 downloads
File information
File name FULLTEXT01.pdfFile size 4413 kBChecksum SHA-512
7c9a0391a71db3d48f6fe2fa99e46a78a8c335a2e05282703177c7c46ab1d41e3ca5f4d046c3a3b17f3d09b9f9043301406aee176291969b9566cd63e7c4ed76
Type fulltextMimetype application/pdf

Authority records

Hernandez-Diaz, Kevin

Search in DiVA

By author/editor
Hernandez-Diaz, Kevin
By organisation
School of Information Technology
Signal ProcessingComputer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 47 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 672 hits
1231 of 3
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf