hh.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Mikaelyan, Anna
Publications (10 of 14) Show all publications
Alonso-Fernandez, F., Mikaelyan, A. & Bigun, J. (2017). Compact Multi-scale Periocular Recognition Using SAFE Features. In: : . Paper presented at Swedish Symposium on Image Analysis, SSBA, Linköping, Sweden, March 13-15, 2017.
Open this publication in new window or tab >>Compact Multi-scale Periocular Recognition Using SAFE Features
2017 (English)Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, we present a new approach for periocular recognition based on the Symmetry Assessment by Feature Expansion (SAFE) descriptor, which encodes the presence of various symmetric curve families around image key points. We use the sclera center as single key point for feature extraction, highlighting the object-like identity properties that concentrates to this unique point of the eye. As it is demonstrated, such discriminative properties can be encoded with a reduced set of symmetric curves. Experiments are done with a database of periocular images captured with a digital camera. We test our system against reference periocular features, achieving top performance with a considerably smaller feature vector (given by the use of a single key point). All the systems tested also show a nearly steady correlation between acquisition distance and performance, and they are also able to cope well when enrolment and test images are not captured at the same distance. Fusion experiments among the available systems are also provided.

National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:hh:diva-35644 (URN)
Conference
Swedish Symposium on Image Analysis, SSBA, Linköping, Sweden, March 13-15, 2017
Available from: 2017-12-07 Created: 2017-12-07 Last updated: 2019-09-26Bibliographically approved
Alonso-Fernandez, F., Mikaelyan, A. & Bigun, J. (2016). Compact Multi-scale Periocular Recognition Using SAFE Features. In: Proceedings - International Conference on Pattern Recognition: . Paper presented at 23rd International Conference on Pattern Recognition (ICPR), 4-8 December, 2016, Cancún, Mexico (pp. 1455-1460). Washington: IEEE Communications Society, Article ID 7899842.
Open this publication in new window or tab >>Compact Multi-scale Periocular Recognition Using SAFE Features
2016 (English)In: Proceedings - International Conference on Pattern Recognition, Washington: IEEE Communications Society, 2016, p. 1455-1460, article id 7899842Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, we present a new approach for periocular recognition based on the Symmetry Assessment by Feature Expansion (SAFE) descriptor, which encodes the presence of various symmetric curve families around image key points. We use the sclera center as single key point for feature extraction, highlighting the object-like identity properties that concentrates to this unique point of the eye. As it is demonstrated, such discriminative properties can be encoded with a reduced set of symmetric curves. Experiments are done with a database of periocular images captured with a digital camera. We test our system against reference periocular features, achieving top performance with a considerably smaller feature vector (given by the use of a single key point). All the systems tested also show a nearly steady correlation between acquisition distance and performance, and they are also able to cope well when enrolment and test images are not captured at the same distance. Fusion experiments among the available systems are also provided. © 2016 IEEE

Place, publisher, year, edition, pages
Washington: IEEE Communications Society, 2016
Series
International Conference on Pattern Recognition, ISSN 1051-4651
National Category
Signal Processing
Identifiers
urn:nbn:se:hh:diva-31748 (URN)10.1109/ICPR.2016.7899842 (DOI)000406771301077 ()2-s2.0-85019080000 (Scopus ID)978-1-5090-4847-2 (ISBN)
Conference
23rd International Conference on Pattern Recognition (ICPR), 4-8 December, 2016, Cancún, Mexico
Funder
Swedish Research Council
Available from: 2016-08-11 Created: 2016-08-11 Last updated: 2019-09-24Bibliographically approved
Bigun, J. & Mikaelyan, A. (2016). Frequency map by Structure Tensor in Logarithmic Scale Space and Forensic Fingerprints. In: PROCEEDINGS OF 29TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, (CVPRW 2016): . Paper presented at 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016; Las Vegas; United States; 26 June 2016 through 1 July 2016. (pp. 204-213). Piscataway, NJ: IEEE, Article ID 7789522.
Open this publication in new window or tab >>Frequency map by Structure Tensor in Logarithmic Scale Space and Forensic Fingerprints
2016 (English)In: PROCEEDINGS OF 29TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, (CVPRW 2016), Piscataway, NJ: IEEE, 2016, p. 204-213, article id 7789522Conference paper, Published paper (Refereed)
Abstract [en]

Increasingly, absolute frequency and orientation maps are needed, e.g. for forensics. We introduce a non-linear scale space via the logarithm of trace of the Structure Tensor. Therein, frequency estimation becomes an orientation estimation problem. We show that this offers significant advantages, including construction of efficient isotropic estimations of dense maps of frequency. In fingerprints, both maps are shown to improve each other in an enhancement scheme via Gabor filtering. We suggest a novel continuous ridge counting method, relying only on dense absolute frequency and orientation maps, without ridge detection, thinning, etc. Furthermore, we present new evidence that frequency maps are useful attributes of minutiae. We verify that the suggested method compares favorably with state of the art using forensic fingerprints as test bed, and test images where the ground truth is known. In evaluations, we use public data sets and published methods only.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE, 2016
Series
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, ISSN 2160-7508
Keywords
Absolute frequency, Gabor filtering, Logarithmic scale, Orientation estimation, Orientation maps, Ridge detections, State of the art, Structure tensors
National Category
Signal Processing Probability Theory and Statistics
Identifiers
urn:nbn:se:hh:diva-35669 (URN)10.1109/CVPRW.2016.32 (DOI)000391572100025 ()2-s2.0-85010210669 (Scopus ID)978-1-5090-1437-8 (ISBN)
Conference
29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016; Las Vegas; United States; 26 June 2016 through 1 July 2016.
Available from: 2017-12-01 Created: 2017-12-01 Last updated: 2017-12-01Bibliographically approved
Mikaelyan, A. (2015). Compact orientation and frequency estimation with applications in biometrics: Biometrics on the orientation express. (Doctoral dissertation). Halmstad: Halmstad University Press
Open this publication in new window or tab >>Compact orientation and frequency estimation with applications in biometrics: Biometrics on the orientation express
2015 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Automatic feature extraction still remains a relevant image and signal processing problem even tough both the field and technologies are developing rapidly. Images of low quality, where it is extremely difficult to reliably process image information automatically, are of special interest. To such images we can refer forensic fingerprints, which are left unintentionally on different surfaces andare contaminated by several of the most difficult noise types. For this reason, identification of fingerprints is mainly based on the visual skills of forensic examiners. We address the problem caused by low quality in fingerprints by connecting different sources of information together, yielding dense frequency and orientation maps in an iterative scheme. This scheme comprises smoothing ofthe original, but only along, ideally never across, the ridges. Reliable estimation of dense maps allows to introduce a continuous fingerprint ridge counting technique. In fingerprint scenario the collection of irrefutable tiny details, e.g. bifurcation of ridges, called minutiae, is used to tie the pattern of such points and their tangential directions to the finger producing the pattern. This limited feature set, location and direction of minutiae, is used in current AFIS systems, while fingerprint examiners use the extended set of features, including the image information between the points. With reasonably accurate estimationsof dense frequency and orientation maps at hand, we have been able to propose a novel compact feature descriptor of arbitrary points. We have used these descriptors to show that the image information between minutiae can be extracted automatically and be valuable for identity establishment of forensic images even if the underlying images are noisy. We collect and compress the image information in the neighborhoods of the fine details, such as minutiae, to vectors, one per minutia, and use the vectors to "color" the minutiae. When matching two patterns (of minutiae) even the color of the minutia must match to conclude that they come from the same identity. This feature development has been concentrated and tested on forensic fingerprint images. However, we have also studied an extension of its application area to other biometrics, periocular regions of faces. This allowed us to test the persistence of automatically extracted features across different types of imagesand image qualities, supporting its generalizability.

Place, publisher, year, edition, pages
Halmstad: Halmstad University Press, 2015. p. 69
Series
Halmstad University Dissertations ; 10
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:hh:diva-28205 (URN)978-91-87045-21-9 (ISBN)978-91-87045-20-2 (ISBN)
Public defence
2015-04-17, Wigforssalen, Visionen, Kristian IV:s väg 3, 301 18, Halmstad, 10:15 (English)
Opponent
Supervisors
Available from: 2015-05-11 Created: 2015-05-06 Last updated: 2019-09-26Bibliographically approved
Alonso-Fernandez, F., Mikaelyan, A. & Bigun, J. (2015). Comparison and Fusion of Multiple Iris and Periocular Matchers Using Near-Infrared and Visible Images. In: 3rd International Workshop on Biometrics and Forensics, IWBF 2015: . Paper presented at 3rd International Workshop on Biometrics and Forensics, IWBF 2015, Gjøvik, Norway, 3-4 March, 2015 (pp. Article number: 7110234). Piscataway, NJ: IEEE Press
Open this publication in new window or tab >>Comparison and Fusion of Multiple Iris and Periocular Matchers Using Near-Infrared and Visible Images
2015 (English)In: 3rd International Workshop on Biometrics and Forensics, IWBF 2015, Piscataway, NJ: IEEE Press, 2015, p. Article number: 7110234-Conference paper, Published paper (Refereed)
Abstract [en]

Periocular refers to the facial region in the eye vicinity. It can be easily obtained with existing face and iris setups, and it appears in iris images, so its fusion with the iris texture has a potential to improve the overall recognition. It is also suggested that iris is more suited to near-infrared (NIR) illu- mination, whereas the periocular modality is best for visible (VW) illumination. Here, we evaluate three periocular and three iris matchers based on different features. As experimen- tal data, we use five databases, three acquired with a close-up NIR camera, and two in VW light with a webcam and a dig- ital camera. We observe that the iris matchers perform better than the periocular matchers with NIR data, and the opposite with VW data. However, in both cases, their fusion can pro- vide additional performance improvements. This is specially relevant with VW data, where the iris matchers perform sig- nificantly worse (due to low resolution), but they are still able to complement the periocular modality. © 2015 IEEE.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Press, 2015
Keywords
Iris, periocular, biometrics, near-infrared data, visible data, fusion
National Category
Signal Processing
Identifiers
urn:nbn:se:hh:diva-28021 (URN)10.1109/IWBF.2015.7110234 (DOI)000380429100015 ()2-s2.0-84936077931 (Scopus ID)978-147998105-2 (ISBN)
Conference
3rd International Workshop on Biometrics and Forensics, IWBF 2015, Gjøvik, Norway, 3-4 March, 2015
Funder
Swedish Research Council
Available from: 2015-03-26 Created: 2015-03-26 Last updated: 2018-03-22Bibliographically approved
Gottschlich, C., Mikaelyan, A., Olsen, M. A., Bigun, J. & Busch, C. (2015). Improving Fingerprint Alteration Detection. In: Sven Lončarić, Dick Lerski, Hannu Eskola, Robert Bregović (Ed.), 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA): . Paper presented at 9th International Symposium on Image and Signal Processing and Analysis, Zagreb, Croatia, September 7-9, 2015 (pp. 83-86). Zagreb: University of Zagreb
Open this publication in new window or tab >>Improving Fingerprint Alteration Detection
Show others...
2015 (English)In: 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA) / [ed] Sven Lončarić, Dick Lerski, Hannu Eskola, Robert Bregović, Zagreb: University of Zagreb , 2015, p. 83-86Conference paper, Published paper (Refereed)
Abstract [en]

Fingerprint alteration is a type of presentation attack in which the attacker strives to avoid identification, e.g. at border control or in forensic investigations. As a countermeasure, fingerprint alteration detection aims to automatically discover the occurrence of such attacks by classifying fingerprint images as ’normal’ or ’altered’. In this paper, we propose four new features for improving the performance of fingerprint alteration detection modules. We evaluate the usefulness of these features on a benchmark and compare them to four existing features from the literature. © Copyright 2015 IEEE - All rights reserved.

Place, publisher, year, edition, pages
Zagreb: University of Zagreb, 2015
Series
International Symposium on Image and Signal Processing and Analysis, ISSN 1849-2266 ; 9
Keywords
biometrics, fingerprints
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:hh:diva-29447 (URN)10.1109/ISPA.2015.7306037 (DOI)000378419400015 ()2-s2.0-84978519672 (Scopus ID)978-1-4673-8032-4 (ISBN)978-1-4673-8031-7 (ISBN)
Conference
9th International Symposium on Image and Signal Processing and Analysis, Zagreb, Croatia, September 7-9, 2015
Projects
INGRESS
Funder
EU, FP7, Seventh Framework Programme, SEC-2012-312792
Note

This work is carried out under the funding of the EU-FP7 INGRESS project (Grant No. SEC-2012-312792). C. Gottschlich also acknowledges the support of the Felix-Bernstein-Institute for Mathematical Statistics in the Bio-sciences and the Niedersachsen Vorab of the Volkswagen Foundation.

Available from: 2015-09-13 Created: 2015-09-13 Last updated: 2018-03-22Bibliographically approved
Mikaelyan, A., Alonso-Fernandez, F. & Bigun, J. (2014). Periocular Recognition by Detection of Local Symmetry Patterns. In: Kokou Yetongnon, Albert Dipanda & Richard Chbeir (Ed.), Proceedings: Tenth International Conference on Signal-Image Technology and Internet-Based System: 23–27 November 2014: Marrakech, Morocco. Paper presented at Workshop on Insight on Eye Biometrics (IEB) in conjunction with The 10th International Conference on Signal Image Technology & Internet Based Systems (SITIS), Marrakech, Morocco, 23-27 November, 2014 (pp. 584-591). Los Alamitos, CA: IEEE Computer Society
Open this publication in new window or tab >>Periocular Recognition by Detection of Local Symmetry Patterns
2014 (English)In: Proceedings: Tenth International Conference on Signal-Image Technology and Internet-Based System: 23–27 November 2014: Marrakech, Morocco / [ed] Kokou Yetongnon, Albert Dipanda & Richard Chbeir, Los Alamitos, CA: IEEE Computer Society, 2014, p. 584-591Conference paper, Published paper (Refereed)
Abstract [en]

We present a new system for biometric recognition using periocular images. The feature extraction method employed describes neighborhoods around keypoints by projection onto harmonic functions which estimates the presence of a series of various symmetric curve families around such keypoints. The iso-curves of such functions are highly symmetric w.r.t. the keypoints and the estimated coefficients have well defined geometric interpretations. The descriptors used are referred to as Symmetry Assessment by Feature Expansion (SAFE). Extraction is done across a set of discrete points of the image, uniformly distributed in a rectangular-shaped grid positioned in the eye center. Experiments are done with two databases of iris data, one acquired with a close-up iris camera, and another in visible light with a webcam. The two databases have been annotated manually, meaning that the radius and center of the pupil and sclera circles are available, which are used as input for the experiments. Results show that this new system has a performance comparable with other periocular recognition approaches. We particularly carry out comparative experiments with another periocular system based on Gabor features extracted from the same set of grid points, with the fusion of the two systems resulting in an improved performance. We also evaluate an iris texture matcher, providing fusion results with the periocular systems as well.

Place, publisher, year, edition, pages
Los Alamitos, CA: IEEE Computer Society, 2014
Keywords
biometrics, periocular recognition, eye, symmetry filters, structure tensor
National Category
Signal Processing
Identifiers
urn:nbn:se:hh:diva-26871 (URN)10.1109/SITIS.2014.105 (DOI)000380564200086 ()2-s2.0-84928574243 (Scopus ID)978-1-4799-7978-3 (ISBN)
Conference
Workshop on Insight on Eye Biometrics (IEB) in conjunction with The 10th International Conference on Signal Image Technology & Internet Based Systems (SITIS), Marrakech, Morocco, 23-27 November, 2014
Projects
BBfor2
Funder
Swedish Research Council, 2012-4313EU, FP7, Seventh Framework Programme, 238803Knowledge Foundation
Note

Author A. M. thanks the EU BBfor2 project for funding her doctoral research. Author F. A.-F. thanks the Swedish Research Council and the EU for for funding his postdoctoral research. Authors acknowledge the CAISR program of the Swedish Knowledge Foundation and the EU COST Action IC1106.

Available from: 2014-10-22 Created: 2014-10-22 Last updated: 2018-03-22Bibliographically approved
Mikaelyan, A. & Bigun, J. (2014). SAFE features for matching fingermarks by neighbourhoods of single minutiae. In: 2014 14th International Symposium on Communications and Information Technologies (ISCIT): . Paper presented at 14th International Symposium on Communications and Information Technologies (ISCIT 2014), Incheon, South Korea, September 24-26, 2014 (pp. 181-185). Piscataway, N.J.: IEEE Press, Article ID 7011896.
Open this publication in new window or tab >>SAFE features for matching fingermarks by neighbourhoods of single minutiae
2014 (English)In: 2014 14th International Symposium on Communications and Information Technologies (ISCIT), Piscataway, N.J.: IEEE Press, 2014, p. 181-185, article id 7011896Conference paper, Published paper (Refereed)
Abstract [en]

Symmetry Assessment by Finite Expansion (SAFE) is a novel description of image information by means of Generalized Structure Tensor. It represents orientation data in neighbourhood of key points projected onto the space of harmonic functions creating a geometrically interpretable feature of low dimension. The proposed feature has built in quality metrics reflecting accuracy of the extracted feature and ultimately the quality of the key point. The feature vector is orientation invariant in that it is orientation steerable with low computational cost. We provide experiments on minutia key points of forensic fingerprints to demonstrate its usefulness. Matching is performed based on minutia in regions with high orientation variance, e.g. in proximity of core points. Performance of single matching minutia equals to 20% EER and Rank-20 CMC 69% on the only publicly available annotated forensic fingerprint SD27 database.

Further, we complement SAFE descriptors of orientation maps with SAFE descriptors of frequency features in a similar manner. In case of combined features the performance is improved further to 19% EER and 74% Rank-20 CMC. © 2014 IEEE.

Place, publisher, year, edition, pages
Piscataway, N.J.: IEEE Press, 2014
Keywords
forensic fingerprint, latent, SD27, biometrics, structure tensor, feature extraction, orientation map
National Category
Signal Processing
Identifiers
urn:nbn:se:hh:diva-26585 (URN)10.1109/ISCIT.2014.7011896 (DOI)000380543700040 ()2-s2.0-84922895765 (Scopus ID)978-1-4799-4416-3 (ISBN)
Conference
14th International Symposium on Communications and Information Technologies (ISCIT 2014), Incheon, South Korea, September 24-26, 2014
Available from: 2014-09-25 Created: 2014-09-25 Last updated: 2018-03-22Bibliographically approved
Mikaelyan, A. & Bigun, J. (2014). Symmetry Assessment by Finite Expansion: application to forensic fingerprints. In: Arslan Brömme & Christoph Busch (Ed.), 2014 International Conference of the Biometrics Special Interest Group (BIOSIG): . Paper presented at 13th International Conference of the Biometrics Special Interest Group (BIOSIG), Darmstadt, Germany, 10-12 September, 2014 (pp. 87-98). Bonn: Gesellschaft für Informatik
Open this publication in new window or tab >>Symmetry Assessment by Finite Expansion: application to forensic fingerprints
2014 (English)In: 2014 International Conference of the Biometrics Special Interest Group (BIOSIG) / [ed] Arslan Brömme & Christoph Busch, Bonn: Gesellschaft für Informatik, 2014, p. 87-98Conference paper, Published paper (Refereed)
Abstract [en]

Common image features have too poor information for identification of forensic images of fingerprints, where only a small area of the finger is imaged and hence a small amount of key points are available. Noise, nonlinear deformation, and unknown rotation are additional issues that complicate identification of forensic fingerprints. We propose a feature extraction method which describes image information around key points: Symmetry Assessment by Finite Expansion (SAFE). The feature set has built-in quality estimates as well as a rotation invariance property. The theory is developed for continuous space, allowing compensation for features directly in the feature space when images undergo such rotation without actually rotating them. Experiments supporting that use of these features improves identification of forensic fingerprint images of the public NIST SD27 database are presented. Performance of matching orientation information in a neighborhood of core points has an EER of 24% with these features alone, without using minutiae constellations, in contrast to 36% when using minutiae alone. Rank-20 CMC is 58%, which is lower than 67% when using notably more manually collected minutiae information.

Place, publisher, year, edition, pages
Bonn: Gesellschaft für Informatik, 2014
Series
Lecture Notes in Informatics (LNI) - Proceedings, ISSN 1617-5468 ; P-230
Keywords
forensic fingerprints, NIST SD27, orientation map, feature extraction, latent, structure tensor, biometrics
National Category
Signal Processing
Identifiers
urn:nbn:se:hh:diva-26583 (URN)000412427900007 ()2-s2.0-84919337963 (Scopus ID)978-3-88579-624-4 (ISBN)978-3-88579-624-4 (ISBN)978-1-4799-3798-1 (ISBN)
Conference
13th International Conference of the Biometrics Special Interest Group (BIOSIG), Darmstadt, Germany, 10-12 September, 2014
Available from: 2014-09-25 Created: 2014-09-25 Last updated: 2018-01-16Bibliographically approved
Mikaelyan, A. & Bigun, J. (2013). Frequency and ridge estimation using structure tensor. In: Proceedings of Biometric Technologies in Forensic Science: Nijmegen, 14–15 October 2013. Paper presented at Biometric Technologies in Forensic Science (BTFS 2013), Nijmegen, Netherlands, October 14-15, 2013 (pp. 58-59). Nijmegen: Radboud University Nijmegen
Open this publication in new window or tab >>Frequency and ridge estimation using structure tensor
2013 (English)In: Proceedings of Biometric Technologies in Forensic Science: Nijmegen, 14–15 October 2013, Nijmegen: Radboud University Nijmegen , 2013, p. 58-59Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Nijmegen: Radboud University Nijmegen, 2013
Series
Proceedings of Biometric Technologies in Forensic Science, ISSN 2351-9738
Keywords
structure tensor, forensic fingerprint, latent, SD27, frequency estimation, biometrics
National Category
Signal Processing
Identifiers
urn:nbn:se:hh:diva-26587 (URN)
Conference
Biometric Technologies in Forensic Science (BTFS 2013), Nijmegen, Netherlands, October 14-15, 2013
Available from: 2014-09-25 Created: 2014-09-25 Last updated: 2018-03-22Bibliographically approved
Organisations

Search in DiVA

Show all publications