Dmitry O. Gorodnichy

Government of Canada · Canada Border Services Agency

This report reviews commercial off-the-shelf (COTS) solutions and related patents for face recognition in video surveillance applications. Commercial products are analyzed using such criteria as processing speed, feature selection techniques, ability to perform screening against the watch list, and ability to perform both still-to-video and video-t...

Face recognition in video is an example of the problem which is outstandingly well performed by humans, compared to the performance of machine-built recognition systems. This phenomenon is generally attributed to the following three main factors pertaining to the way human brain processes and memorizes information, which can be succinctly labeled a...

Within the last decade there has been a considerable amount of interest in pseudo-inverse autoassociative neural networks (PINNs), which are networks designed with the pseudo-inverse learning rule. This interest is attributed to their high capacity and retrieval capability: the limit of 0.5N for the associative capacity (N being the number of neuro...

ty masses. The problem is that in order to apply this rule, the data are required to be DS-independent [3]. This means that the sources of the data have to be different, which in most cases they are not. Thus, there is a need to investigate other combination rules for the evidential approach. The issue of sparse data Another question is how to comb...

Human nose, while being in many cases the only facial feature clearly visible during the head motion, seems to be very undervalued in face tracking technology. This paper shows theoretically and by experiments conducted with ordinary USB cameras that, by properly defining nose as an extremum of the 3D curvature of the nose surface, nose becomes the...

Design and Evaluation of Automated �Behaviour Screening Technology�(the AVATAR project) Data Science Graduate Student Seminar,�Department of Math/Stat, uOttawa

Presentation from uOttawa AI Grad Student seminar on Automated Multi-modal Behaviour Screening (AVATAR) project

The historical NEXUS iris kiosks log dataset collected by the CBSA from 2003 till 2014 has become the focus of scientific attention due to its involvement in the iris aging debate between NIST and University of Notre Dame researchers. To facilitate this debate, this paper provides additional details on how this dataset was collected, its various pr...

This report presents the deliverables for the "Roadmap for Biometrics at the Border" (CSSP-2015-TI-2158) study conducted by the Canada Border Services Agency (CBSA) in partnership with University of Arizona (UA) and San Diego State University (SDSU) through support from the Defence Research and Development Canada, Canadian Safety and Security Progr...

Artificial intelligence (including machine learning, data science, advanced analytics) has been successfully applied in many social and economic spheres, including weather forecasting, targeted political campaigns, automated detection of targets and events, optimization of system performance, and maximizing profits of various industries. In our wor...

Official Extended summary (Автореферат) of the Ph.D. dissertation (in Ukrainian) "Investigation and Design of High Performance Fully-Connected Neural Networks", "Исследование и разработка высокопроизводительных полных нейросетей",

This paper presents a technology readiness assessment framework called PROVE-IT(), which allows one to access the readiness of face recognition and video analytic technologies for video surveillance applications, and the roadmap for the deployment of technologies for automated recognition of people and their activities in video, based on the propos...

This report presents the list of the new and revised biometric terms recommended for automated border control and video surveillance applications. These terms have been developed by the CBSA Science and Engineering Directorate as a result of its work on the “PROVE-IT(FRiV)”, “PROVE-IT(VA)” and “ART in ABC" studies, which were conducted by the direc...

This report presents the outcomes of the “Risk analysis of face and iris biometrics in border/access control applications” (CSSP-2013-CP-1020) study conducted by the Canada Border Services Agency in partnership with the University of Calgary through support from the Defence Research and Development Canada, Canadian Safety and Security Program (CSSP...

Recognizing individuals of interest from faces captured with video cameras raises several challenges linked to changes in capture conditions (e.g., variation in illumination and pose). Moreover, in person re-identification applications, the facial models needed for matching are typically designed a priori, with a limited amount of reference samples...

This paper revisits the concept of an authentication machine (A-machine) that aims at identifying/verifying humans. Although A-machines in the closed-set application scenario are well understood and commonly used for access control utilizing human biometrics (face, iris, and fingerprints), open-set applications of A-machines have yet to be equally...

This paper introduces a formalization of the Au-tomated Border Control (ABC) machines deployed worldwide as part of the eBorder infrastructure for automated traveller clearance. Proposed formalization includes classification of the eBorder technologies, definition of the basic components of the ABC machines, identification of their key properties,...

This paper concerns the problem of real-time watch-list screening (WLS) using face recognition (FR) technology. The risk of flagging innocent travellers can be very high when deploying a FR system for WLS since: (i) faces captured in surveillance video vary considerably due to pose, expression, illumination, and camera inter-operability; (ii) refer...

For applications of face recognition (FR) in video surveillance, it is often costly or unfeasible to collect several high quality reference samples a priori to design representative facial models. Moreover, changes in capture conditions and human physiology create divergence between facial models and input captures. Multiple classifier systems (MCS...

This report surveys work done by academia in developing Face Recognition solutions for video-surveillance applications. We present an architecture of a generic system for face recognition in video and review academic systems reported in the academic literature suitable for video-surveillance applications. Recommendations on the selection of systems...

This report presents a survey of evaluation datasets, metrics and practices used by the scienti�c community pertaining to the evaluation of video analytics in the video surveillance context. The focus of the survey is on the task of visually tracking people in video, and its application to loitering and tailgating detection. The related key results...

This report is a supplement to Technical Report ’‘Evaluation methodology for face recognition technology in video surveillance applications” (by E. Granger and D. Gorodnichy) [1]. It presents complete evaluation results of three Commercial Off-The-Shelf (COTS) Face Recognition (FR) systems: Cognitec, PittPatt and Neurotechnology — obtained on the C...

One of the most critical tasks in automated face recognition technology is the extraction of facial features from a facial images. The most critical task in each face recognition (FR) technology, which contributes the most to the success of particular FR products in particular applications and which is highly protected by industries developing thos...

This report reviews metrics, methodologies and data-sets used for evaluation of face recognition in video (FRiV) and establishes a multi-level evaluation methodology that is suitable for video surveillance applications. The developed methodology is particularly tailored for such video surveillance applications as screening of faces against the want...

This report surveys work done by academia in developing Face Recognition solutions for video-surveillance applications. We present an architecture of a generic system for face recognition in video and review academic systems reported in the academic literature suitable for video-surveillance applications. Recommendations on the selection of systems...

This report provides the history and background information related to the PROVE-IT(VA) project conducted by the CBSA under the funding from Defence Research and Development Canada (DRDC) Centre for Security Science (CSS) Public Security Technical Program (PSTP). The key outcomes from the Interdepartmental Video Technology for National Security (VT...

This report presents a survey of the state of the art in automatic Unattended/Left-behind Objects Detection (ULOD) in various premises (metro stations, train stations and airports), followed by the technology readiness level (TRL) assessment based thereon. The survey overviews recent academic advances in this area and also focuses on current commer...

This presentation defines automated border control (ABC) systems as a part of a larger eBorder traveller clearance process which deals with granting travellers an entry to a country. Three generations of the ABC are established. Gen-1 ABC are kiosk systems such as Canada's NEXUS or UK IRIS, which process low-risk pre-cleared travellers. Gen-2 ABC a...

For applications of face recognition (FR) in video surveillance, it is often costly or unfeasible to collect several high quality reference samples a priori to design representative facial models. Moreover, changes in capture conditions and human physiology create divergence between facial models and input captures. Multiple classifier systems (MCS...

In video surveillance, person re-identification refers to recognizing individuals of interest from faces captured across a network of video cameras. Face recognition in such applications is challenging because faces are captured with limited spatial and temporal constraints. In addition, facial models for recognition are commonly designed using lim...

Systems for face re-identification over a network of video surveillance cameras are designed with a limited amount of reference data, and may operate under complex environments. Furthermore, target individuals provide a small proportion of the facial captures for design and during operations, and these proportions may change over time according to...

Several ensemble-based techniques have been proposed to design pattern recognition systems when data has imbalanced class distributions, although class proportions may change over time according to the operational environment. For instance, in video surveillance applications, face recognition (FR) is employed to detect the presence of target indivi...

Video-based face screening is essentially a detection problem where faces captured in video sequences are matched against the facial models of individuals of interest. This problem is associated with several operational challenges, from lighting and pose changes, to natural aging of target individuals, and to the limited availability of reference s...

Biometric privacy-enhancing technologies (PET) include two major groups: Biometric Encryption and Cancelable Biometrics. They enhance both privacy and security of a biometric system, thus embodying the Privacy by Design principles in a way that benefits the individual and minimizes the privacy risks. In this paper, the results of independent third-...

To improve accuracy and reliability, Boolean combination (BC) can efficiently integrate the responses of multiple biometric systems in the ROC space. However, BC techniques assume that recognition systems are conditionally-independent and that their ROC curves are convex. These assumptions are rarely valid in practice, where systems face complex en...

Video-based face recognition of individuals involves matching facial regions captured in video sequences against the model of individuals enrolled to a face recognition system. Due to a limited control over operational conditions, classification systems applied to face matching are confronted with complex pattern recognition environments that chang...

Biometric systems for recognizing faces in video streams have become relevant in a growing number of private and public sector applications, among them screening for individuals of interest in dense and moving crowds. In practice, the performance of these systems typically declines because they encounter a variety of uncontrolled conditions that ch...

Boolean combination (BC) techniques have been shown to efficiently integrate the responses of multiple diversified classifiers in the ROC space to improve the overall accuracy and reliability of pattern recognition systems. In practice, since class distributions are often imbalanced and change over time, the BC of classifiers, and thus selection of...

We present an interactive video event detection system for the TRECVID 2012 Surveillance Event Detection (SED) task [16]. Inspired by previous TRECVID submissions, the underlying approach is built on combining automated detection of temporal regions of interest through the extraction of binary spatio-temporal keypoint descriptors in observed video-...

Researchers now acknowledge that the ultimate goal for biometric technologies to be error-free may never be achieved for any biometric modality. The key interest therefore for any biometric modality is to know its current performance limits. For the iris modality, which is intensively used for trusted traveller programs in many countries, the quest...

C-BET is the Comprehensive Biometrics Evaluation Toolkit developed by CBSA in order to analyze the suitability of biometric systems for fully-automated border/access control applications. Following the multi-order score analysis and the threshold-validated analysis defined within the C-BET framework, the paper presents the results of the C-BET eval...