hh.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Teferi Lemma, Dereje
Alternative names
Publications (8 of 8) Show all publications
Teferi Lemma, D. & Bigun, J. (2010). Method and apparatus for encoding and reading optical machine-readable data codes. us 8,757,490 B2.
Open this publication in new window or tab >>Method and apparatus for encoding and reading optical machine-readable data codes
2010 (English)Patent (Other (popular science, discussion, etc.))
Abstract [en]

A method and apparatus for data encoding and optical recognition of encoded data includes generating symbols that represent data using angles (rather than linear dimensions as used for conventional bar codes). One embodiment uses spirals isocurves. Another uses parabolas isocurves. Methods for visually depicting such symbols, including symbols having gray values are disclosed. Methods for machine-based detection and decoding of such symbols regardless of their orientation relative to the machine is also disclosed.

Keywords
spiral codes, bar codes, rotation invariant, scale invariant, autonomous robots, object tracking
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:hh:diva-25867 (URN)
Patent
US 8,757,490 B2 (2014-06-24)
Available from: 2014-06-25 Created: 2014-06-25 Last updated: 2018-03-22Bibliographically approved
Teferi, D. & Bigun, J. (2009). Evaluation Protocol for the DXM2VTS Database and Performance Comparison of Face Detection and Face Tracking on Video. In: Josef Bigun & Antanas Verikas (Ed.), Proceedings SSBA '09: Symposium on Image Analysis, Halmstad University, Halmstad, March 18-20, 2009 (pp. 49-52). Halmstad: Halmstad University
Open this publication in new window or tab >>Evaluation Protocol for the DXM2VTS Database and Performance Comparison of Face Detection and Face Tracking on Video
2009 (English)In: Proceedings SSBA '09: Symposium on Image Analysis, Halmstad University, Halmstad, March 18-20, 2009 / [ed] Josef Bigun & Antanas Verikas, Halmstad: Halmstad University , 2009, p. 49-52Chapter in book (Other academic)
Abstract [en]

Video databases and their corresponding evaluation protocols are used to compare classifiers, such as face detection an tracking. In this paper, a six level evaluation protocol for the Damascened XM2VTS (DXM2VTS) database is presented to measure face detection and tracking performance. Additionally, a novel database containing thousands of videos is created by combining video from the XM2VTS database with a set of newly recorded standardized real-life video used as background and with several realistic degradations, such as motion blur, noise, etc. Moreover, two publicly available and published face detection algorithms, are tested on the six suggested difficulty levels of the protocol. Their performance on video in terms of false acceptance, false rejection, correct detection, and repeatability, are reported and conclusions are drawn.

Place, publisher, year, edition, pages
Halmstad: Halmstad University, 2009
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:hh:diva-25834 (URN)978-91-633-3924-0 (ISBN)
Available from: 2014-06-24 Created: 2014-06-24 Last updated: 2018-03-22Bibliographically approved
Teferi, D. & Bigun, J. (2009). Multi-view and Multi-scale Recognition of Symmetric Patterns. In: Arnt-Børre Salberg, Jon Yngve Hardeberg and Robert Jenssen (Ed.), Image analysis. Paper presented at 16th Scandinavian Conference on Image Analysis, SCIA 2009, Oslo, Norway, June 15-18, 2009 (pp. 657-666). Berlin: Springer
Open this publication in new window or tab >>Multi-view and Multi-scale Recognition of Symmetric Patterns
2009 (English)In: Image analysis / [ed] Arnt-Børre Salberg, Jon Yngve Hardeberg and Robert Jenssen, Berlin: Springer, 2009, p. 657-666Conference paper, Published paper (Refereed)
Abstract [en]

This paper suggests the use of symmetric patterns and their corresponding symmetry filters for pattern recognition in computer vision tasks involving multiple views and scales. Symmetry filters enable efficient computation of certain structure features as represented by the generalized structure tensor (GST). The, properties of the complex moments to changes in scale and multiple views including in-depth rotation of the patterns and the presence of noise is investigated. Images of symmetric patterns captured using a. low resolution low-cost CMOS camera, such as a phone Camera or a web-cam, from as far as three meters are precisely localized and their spatial orientation is determined from the argument of the second order complex moment I-20 without further computation.

Place, publisher, year, edition, pages
Berlin: Springer, 2009
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; Vol. 5575
Keywords
CMOS camera, Complex moments, Efficient computation, Low resolution, Multi-views, Multiple views, Multiscales, Second orders, Spatial orientations, Structure features, Structure tensors, Symmetric patterns, Symmetry filters
National Category
Computer Sciences
Identifiers
urn:nbn:se:hh:diva-14943 (URN)10.1007/978-3-642-02230-2_67 (DOI)000268661000067 ()2-s2.0-70350629799 (Scopus ID)978-3-642-02229-6 (ISBN)
Conference
16th Scandinavian Conference on Image Analysis, SCIA 2009, Oslo, Norway, June 15-18, 2009
Available from: 2011-04-04 Created: 2011-04-04 Last updated: 2018-03-23Bibliographically approved
Teferi Lemma, D. (2007). Audio-video synthesis methods for improving performance of biometric systems. (Licentiate dissertation). Gothenburg: Department of Signals and Systems, Chalmers University of Technology
Open this publication in new window or tab >>Audio-video synthesis methods for improving performance of biometric systems
2007 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

System security is important for any automation. It is even more so in the case of biometric systems due to the sensitive nature of the data it uses for enrollment and authentication - the subjects physical or biological trait. The performance quantification of biometric systems, such as face tracking and recognition, highly depend on the database used for testing the systems. Systems trained and tested on realistic and represenative databases evidently perform better. In fact, the main reason for evaluating any system on test data is that these data sets represent problems that system might face in the real world. However, building biometric databases that represent the real world is an expensive task due to its high demand on the side of the participants. This becomes even more difficult and unrealistic if the data is to be collected in a natural environment such as supermarkets, offices, streets, etc.

This thesis presents a procedure to build a synthetic biometric database by damascening images from a studio recorded database with a realistic scenery. To this end, we developed an image segmenation procedure to spearate the background of a video recorded in studio conditions with the prupose to replace it with an arbitrary complex background. Furthermore, we present how several degradations such as affine transformation, imaging noise, and motion blur can be incorporated into the production of the new database to simulate natural recording environments. The system is applied to the entire XM2VTS database, which already consists of several terabytes of data, to produce the DXM2VTS - Damascened XM2VTS database.

Moreover, the thesis presents a method to segment a video sequence in the time domain based on its audio concept. The video is then reshuffled and used for testing resilience of text-prompted biometric systems against playback attacks. The playback is supported by pyramid based frame interpolation method to reduce discontinuities created at the digit boundaries in time.

Place, publisher, year, edition, pages
Gothenburg: Department of Signals and Systems, Chalmers University of Technology, 2007. p. 31
Series
Technical report R, ISSN 1403-266X ; 2007:6
Keywords
Biometrics, Audio-Video synthesis, Image segmentation, XM2VTS, DXM2VTS
National Category
Computer Sciences
Identifiers
urn:nbn:se:hh:diva-1976 (URN)2082/2371 (Local ID)2082/2371 (Archive number)2082/2371 (OAI)
Presentation
2007-04-24, R1107, Halmstad, 13:15
Supervisors
Available from: 2008-09-29 Created: 2008-09-29 Last updated: 2018-03-23Bibliographically approved
Bigun, J. & Teferi, D. (2007). Damascening video databases for evaluation of face tracking and recognition – The DXM2VTS database. Pattern Recognition Letters, 28(15), 2143-2156
Open this publication in new window or tab >>Damascening video databases for evaluation of face tracking and recognition – The DXM2VTS database
2007 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 28, no 15, p. 2143-2156Article in journal (Refereed) Published
Abstract [en]

Performance quantification of biometric systems, such as face tracking and recognition highly depend on the database used for testing the systems. Systems trained and tested on realistic and representative databases evidently perform better. Actually, the main reason for evaluating any system on test data is that these data sets represent problems that systems might face in the real world. However, building biometric video databases with realistic background for testing is expensive especially due to its high demand of cooperation from the side of the participants. For example, XM2VTS database contain thousands of video recorded in a studio from 295 subjects. Recording these subjects repeatedly in public places such as supermarkets, offices, streets, etc., is not realistic. To this end, we present a procedure to separate the background of a video recorded in studio conditions with the purpose to replace it with an arbitrary complex background, e.g., outdoor scene containing motion, to measure performance, e.g., eye tracking. Furthermore, we present how an affine transformation and synthetic noise can be incorporated into the production of the new database to simulate natural noise, e.g. motion blur due to translation, zooming and rotation. The entire system is applied to the XM2VTS database, which already consists of several terabytes of data, to produce the DXM2VTS–Damascened XM2VTS database essentially without an increase in resource consumption, i.e., storage, bandwidth, and most importantly, the time of clients populating the database, and the time of the operators.

Place, publisher, year, edition, pages
Amsterdam: Elsevier, 2007
Keywords
Biometrics, XM2VTS, Damascened video, Face tracking, Face recognition, Performance quantification
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:hh:diva-1334 (URN)10.1016/j.patrec.2007.06.007 (DOI)000250377600026 ()2-s2.0-34548702005 (Scopus ID)2082/1713 (Local ID)2082/1713 (Archive number)2082/1713 (OAI)
Available from: 2008-04-16 Created: 2008-04-16 Last updated: 2018-03-23Bibliographically approved
Teferi, D. & Bigun, J. (2007). Pyramid Based Interpolation for Face-Video Playback in Audio Visual Recognition. In: Stan Z. Li And Seong-Whan Lee (Ed.), Advances in Biometrics: International Conference, ICB 2007, Seoul, Korea, August 27-29, 2007, Proceedings. Paper presented at International Conference on Biometrics (ICB 2007), 27-29 Aug, Seoul, SOUTH KOREA (pp. 868-877). Berlin: Springer Berlin/Heidelberg
Open this publication in new window or tab >>Pyramid Based Interpolation for Face-Video Playback in Audio Visual Recognition
2007 (English)In: Advances in Biometrics: International Conference, ICB 2007, Seoul, Korea, August 27-29, 2007, Proceedings / [ed] Stan Z. Li And Seong-Whan Lee, Berlin: Springer Berlin/Heidelberg, 2007, p. 868-877Conference paper, Published paper (Refereed)
Abstract [en]

Biometric systems, such as face tracking and recognition, are increasingly being used as a means of security in many areas. The usability of these systems depend not only on how accurate they are in terms of detection and recognition but also on how well they withstand attacks. In this paper we developed a text-driven face-video signal from the XM2VTS database. The synthesized video can be used as a means of playback attack for face detection and recognition systems. We use Hidden Markov Model to recognize the speech of a person and use the transcription file for reshuffling the image sequences as per the prompted text. The discontinuities in the new video are significantly minimized by using a pyramid based multi-resolution frame interpolation technique. The playback can also be used to test liveness detection systems that rely on lip-motion to speech synchronization and motion of the head while posing/speaking. Finally we suggest possible approaches to enable biometric systems to stand against this kind of attacks. Other uses of our results include web-based video communication for electronic commerce.

Place, publisher, year, edition, pages
Berlin: Springer Berlin/Heidelberg, 2007
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 4642
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-14933 (URN)10.1007/978-3-540-74549-5_91 (DOI)000249584900091 ()2-s2.0-37849029242 (Scopus ID)9783540745488 (ISBN)
Conference
International Conference on Biometrics (ICB 2007), 27-29 Aug, Seoul, SOUTH KOREA
Available from: 2011-04-04 Created: 2011-04-04 Last updated: 2018-03-23Bibliographically approved
Teferi, D., Faraj, M. I. & Bigun, J. (2007). Text Driven Face-Video Synthesis Using GMM and Spatial Correlation. In: Ersboll, B K, Pedersen, K S (Ed.), Image analysis: 15th Scandinavian Conference, SCIA 2007, Aalborg, Denmark, June 10-14, 2007 ; proceedings. Paper presented at 15th Scandinavian Conference on Image Analysis, Aalborg, Denmark, June 10-14, 2007 (pp. 572-580). Berlin: Springer Berlin/Heidelberg
Open this publication in new window or tab >>Text Driven Face-Video Synthesis Using GMM and Spatial Correlation
2007 (English)In: Image analysis: 15th Scandinavian Conference, SCIA 2007, Aalborg, Denmark, June 10-14, 2007 ; proceedings / [ed] Ersboll, B K, Pedersen, K S, Berlin: Springer Berlin/Heidelberg, 2007, p. 572-580Conference paper, Published paper (Refereed)
Abstract [en]

Liveness detection is increasingly planned to be incorporated into biometric systems to reduce the risk of spoofing and impersonation. Some of the techniques used include detection of motion of the head while posing/speaking, iris size in varying illumination, fingerprint sweat, text-prompted speech, speech-to-lip motion synchronization etc. In this paper, we propose to build a biometric signal to test attack resilience of biometric systems by creating a text-driven video synthesis of faces. We synthesize new realistic looking video sequences from real image sequences representing utterance of digits. We determine the image sequences for each digit by using a GMM based speech recognizer. Then, depending on system prompt (sequence of digits) our method regenerates a video signal to test attack resilience of a biometric system that asks for random digit utterances to prevent play-back of pre-recorded data representing both audio and images. The discontinuities in the new image sequence, created at the connection of each digit, are removed by using a frame prediction algorithm that makes use of the well known block matching algorithm. Other uses of our results include web-based video communication for electronic commerce and frame interpolation for low frame rate video.

Place, publisher, year, edition, pages
Berlin: Springer Berlin/Heidelberg, 2007
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 4522
Keywords
Image analysis
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-2130 (URN)000247364000058 ()2-s2.0-38049080023 (Scopus ID)2082/2525 (Local ID)978-3-540-73039-2 (ISBN)2082/2525 (Archive number)2082/2525 (OAI)
Conference
15th Scandinavian Conference on Image Analysis, Aalborg, Denmark, June 10-14, 2007
Available from: 2008-11-12 Created: 2008-11-12 Last updated: 2018-03-23Bibliographically approved
Teferi, D. & Bigun, J. (2006). Building video databases to boost performance quantification – the DXM2VTS database. In: Timo Honkela, Tapani Raiko, Jukka Kortela & Harri Valpola (Ed.), Proceedings of The Ninth Scandinavian Conference on Artificial Intelligence (SCAI 2006). Paper presented at The Ninth Scandinavian Conference on Artificial Intelligence (SCAI 2006), Helsinki University of Technology Espoo, Finland, October 25-27, 2006 (pp. 75-82). Helsinki: Finnish Artificial Intelligence society FAIS
Open this publication in new window or tab >>Building video databases to boost performance quantification – the DXM2VTS database
2006 (English)In: Proceedings of The Ninth Scandinavian Conference on Artificial Intelligence (SCAI 2006) / [ed] Timo Honkela, Tapani Raiko, Jukka Kortela & Harri Valpola, Helsinki: Finnish Artificial Intelligence society FAIS , 2006, p. 75-82Conference paper, Published paper (Refereed)
Abstract [en]

Building a biometric database is an expensive task which requires high level of cooperation from a large number of participants. Currently, despite increased demand for large multimodal databases, there are only a few available. The XM2VTS database is one of the most utilized audio-video databases in the research community although it has been increasingly revealed that it cannot quantify performance of a recognition system in the presence of complex background, illumination, and scale variability. However, producing such databases could mean repeatedly recording a multitude of audio-video data outdoors, which makes it a very difficult task if not an impossible one. This is mainly due to the additional demands put on participants. This work presents a novel approach to audio-visual database collection and maintenance to boost the performance quantification of recognition methods and to increase the efficiency of multimodal database construction. To this end we present our segmentation procedure to separate the background of a high-quality video recorded under controlled studio conditions with the purpose to replace it with an arbitrary complex background. Furthermore, we present how an affine transformation and synthetic noise can be incorporated into the production of the new database to simulate real noise, e.g. motion blur due to translation, zooming and rotation. The entire system is applied to the XM2VTS database, which already consists of several terabytes of data, to produce the DXM2VTS – Damascened XM2VTS database essentially without an increase in resource consumption, i.e. storage space, video operator time, and time of clients populating the database. As a result, the DXM2VTS database is a damascened (sewn together) composition of two independently recorded real image sequences that consist of a choice of complex background scenes and the the original XM2VTS database.

Place, publisher, year, edition, pages
Helsinki: Finnish Artificial Intelligence society FAIS, 2006
Series
Publications of the Finnish Artificial Intelligence Society, ISSN 1796-623X
Keywords
video databases, performance quantification
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-2119 (URN)2-s2.0-84862527843 (Scopus ID)2082/2514 (Local ID)2082/2514 (Archive number)2082/2514 (OAI)
Conference
The Ninth Scandinavian Conference on Artificial Intelligence (SCAI 2006), Helsinki University of Technology Espoo, Finland, October 25-27, 2006
Available from: 2008-11-11 Created: 2008-11-11 Last updated: 2018-03-23Bibliographically approved

Search in DiVA

Show all publications