Important Dates


Authors Registration Deadline:
December 28, 2018

Participation Registration Deadline:
December 31, 2018

Camera-Ready Papers Due:
December 10, 2018

Conference Dates:
January 22 - 24, 2019

Our Sponsors



TUTORIAL SPEAKERS

Dr. Mayank Vatsa,
Vice President (Publications), IEEE Biometrics Council; Head, Infosys Center for Artificial Intelligence; Associate Professor, IIIT-Delhi, India; Adjunct Associate Professor, West Virginia University, USA

Mayank Vatsa received the M.S. and Ph.D. degrees in computer science from West Virginia University, Morgantown, WV, USA, in 2005 and 2008, respectively. He is currently an Associate Professor with the Indraprastha Institute of Information Technology, Delhi, India.

He has authored more than 150 publications in refereed journals, book chapters, and conferences. His research has been funded by the Unique Identification Authority of India and DIT. He was a recipient of the FAST Award Project by DST, India. His areas of interest are biometrics, image processing, machine learning, and information fusion.

He is a senior member of IEEE, member of the Computer Society and the Association for Computing Machinery. He was a recipient of several Best Paper and Best Poster Awards at international conferences. He is also an Area Editor of the IEEE Biometric Compendium, an Area Chair of the Information Fusion (Elsevier) journal, and the PC Co-Chair of the 2013 International Conference on Biometrics and the 2014 International Joint Conference on Biometrics.

Title: Adversarial Perturbations in Deep Learning

Abstract:
Deep neural network architecture based models have high expressive power and learning capacity. However, they are essentially a black box method since it is not easy to mathematically formulate the functions that are learned within its many layers of representation. Realizing this, many researchers have started to design methods to exploit the drawbacks of deep learning based algorithms questioning their robustness and exposing their singularities. The research on adversarial learning has three key components: (i) creating adversarial images, (ii) detecting whether an image is adversely altered or not, and (iii) mitigating the effect of the adversarial perturbation process. These adversaries create different kinds of effect on the input and detecting them requires the application of a combination of hand-crafted as well as learned features; for instance, some of the existing attacks can be detected using principal components while some hand-crafted attacks can be detected using well-defined image processing operations. This tutorial will focus on these three key ideas related to adversarial learning (aka perturbations, detection, and mitigation), building from basics of adversarial learning to discussing new algorithms for detection and mitigation, and conclude with some of the research questions in this spectrum.


Prof. C. V. Jawahar
IIIT Hyderabad, India.

C. V. Jawahar is the Amazon Chair professor at IIIT Hyderabad, India. He received his PhD from IIT Kharagpur and has been with IIIT Hyderabad since 2000. At IIIT Hyderabad, Jawahar leads a group focusing on computer vision and machine learning. In the recent years, he has been looking into a set of problems that overlap with vision, language and learning. He is also interested in applications in road safety, assistive technologies, healthcare, education, cultural heritage and entertainment. He has served as a chair for previous editions of ACCV, WACV, IJCAI, ICDAR, ICCV and ICVGIP. Presently, he is an area editor of CVIU and an associate editor of IEEE PAMI. He is a Fellow of IAPR and INAE.

Title: Understanding and Recognizing Face in the Era of Deep Learning

Abstract:
In this tutorial, we look at how the face understanding and recognition has advanced in the recent years with the advances in deep learning. Aimed at students and researchers, this tutorial introduces the basics of deep neural network architectures with focus on face recognition and associated tasks. Then we look at recent advances in this space and the applications that are emerging. Also learning related issues (data, loss functions, amount of supervision) with focus on faces are discussed.



Prof. Josef Bigun,
Halmstad University, Sweden

Josef Bigun obtained his M.Sc. and Ph.D. degrees from Linkoeping University, in 1983 and 1988 respectively. In 1988, he joined the Swiss Federal Institute of Technology in Lausanne where he worked as Adjoint Scientifique until 1998 with the exception that in 1997 he was Visiting Professor at the Royal Institute of Technology, (KTH) Stockholm.

He has been elected Professor to the Signal Analysis Chair, his current position, at Halmstad University and Chalmers Institute of Technology in 1998. He has been in technical and organizational committees of several national and international conferences. In particular he co-chaired the first international conference on Audio and Video Based Person Authentication in 1997. He has been contributing as a referee or as an editorial board member of international journals including Image and Vision Computing, Pattern Recognition Letters and IEEE Image Processing. He served in the executive committees of several scientific associations, including the international association for pattern recognition, IAPR.

He has contributed to the initiation and progress of several national, e.g. VR and SSF projects, and international projects consortia, e.g. the EU projects BBfor2, BIOSECURE, IT-VIRSBS and ACTS-M2VTS. His scientific interests include a broad field in Computer Vision and pattern recognition including biometric signal analysis, texture analysis, motion analysis, 3-D modelling and understanding of the biological recognition mechanisms of audio-visual signals. He has been awarded the grades of fellow of IAPR, and fellow of IEEE.

Title: Image processing for fingerprints by wave and particle natures of local images

Abstract:
In physics, a planar wave has no precise location or extension. Particles are the opposite, they have precise location and extension. Images are a major signal type on which many recognition applications are built, including fingerprint recognition. A region in an image can be modeled well by either a texture which is a repetitive pattern (wave) or as an object with a precise location and extension (particle), i.e. the opposite of a texture. Sub regions of a texture are self similar upon a translation within the texture whereas objects are not repetitive no matter how small the sub-region is made. One can say that it is possible to define an anchor point representing the location of an image particle as well as a direction.

A fingerprint ridge structure is an example of a wave pattern, whereas a minutia, a delta or a core in the same fingerprint represent each a particle region in the sense of the above. In this tutorial, local fingerprint images will be modelled as a combination of waves and particles. Some regions are best described as waves others as particles. Thus there should be a mechanism that tells which regions possess wave nature and which regions object nature.

To that end Tools that will allow to extract:

  • wave features
  • particle features

of local images, using complex valued filters will be presented. The tools are intended to contribute to explainable feature extraction in fingerprints in a systematic way. Explainability is not a wish but a demand from courts using fingerprints as proof.