Start Projects IPASs

Non-COoperative bioMetric system for Positive AuthentiCaTion (COMPACT)

The goal of the project

The scientific goal of the project is to design non-cooperative, high-throughput biometric positive authentication system based on features fusion of iris pattern, periocular and  face image as well as methods and devices for acquisition of such images with sufficient content of distinctive features. The authentication process (see fig. 1) is planned to be mainly based on iris pattern and to be supported by face biometric since iris pattern achieves the best biometric efficiency (lowest error rates).


Fig. 1. Authentication process based on iris pattern

The essence of the project is to enable the automatic identification of people that were previously registered by the system on the basis of observations carried out by the specialized vision systems under unconstrained imaging conditions, at a distance and on the move. Authors plan to use results of their previous work concerning their academic iris recognition system and apply the developed algorithms and methods to a practical system. The other assumption is to realize system able to acquire biometric samples with level of cooperation significantly lower than in case of the Iris-On-The-Move technology. It is assumed that the authorized subject should be inside an area around the system rather than the straight path like in the IOM (see fig. 2). The last key assumption is the high throughput of the system, understood as a number of persons that could be successfully authorized per time interval – not less than in IOM technology, i.e., 30 persons per minute. Using the modern FPGA or/and multicore DSP technology it may be possible to recognize several subjects at the same time increasing significantly the throughput of the system. This could be possible only when wider area is observed by the vision systems like it was already mentioned.


Fig. 2. Iris-On-The-Move® gate for less-constrained iris-based identification

The key problem for iris-based biometric system design is image acquisition issue. Acquisition of good quality image of object of 1,2cm2 area from the subject at-a-distance and on-the-move is the most challenging task in the whole authorization process. Thus, multibiometrics is the tool that allows for fusion of other features that could have been captured during acquisition process. In the case of iris-based systems this can be periocular region: eyebrows and skin texture and color. In the frame of the project the following methods will be developed: new methods for image acquisition, subject tracking, sample quality assessment and features fusion. It should be emphasized that some of the mentioned techniques were described by the other researchers that developed biometric systems for less-constrained scenarios: Hanna, Wheeler, Yoon, Venugopalan. However, there were research systems and they were not commercially implemented. The authors plan to collect those experiences and implement such system using the recent technological advances in imaging devices and embedded processing systems (see fig 3, 4).


Fig. 3. Subject tracking technique using Pan-Tilt-Zoom camera


Fig. 4. Small objects image acquisition technique using WFOV (Wide-Field-Of-View) i NFOV (Narrow-Field-Of-View) cameras

The essence of the problem

The biometric authentication has recently gained great importance due to the increasing demand for authorized and automated access to goods and services. Thanks to the technological and scientific advances, it became possible to use biometrics of high level of confidence, that require no interaction with a person being authorized (e.g., iris, gait, face), in everyday use. This enabled the successful biometric authentication on a small or medium scale while maintaining the great convenience of using the system. However due to many problems with acquisition of good quality biometric samples especially in unconstrained conditions, the biometrics is one of the most rapidly evolving branch of science nowadays, and use of iris biometric as a separate, independent identifier (recognition rate ≤ 10-3) is an area of activity of many research centers worldwide. Although there are known solutions for positive biometric authentication (identification or verification) there is still a place for innovations in the area of automated biometric recognition under unconstrained conditions using iris pattern and face image. Such systems must deal with variations of many parameters, such as: exposition, wavelength of illumination, ambient light reflections from the eye’s surface, perspective fluctuations as well as cheat attempts, etc.

These problems are going to be considered by the authors within this project. Moreover, biometric authentication systems that use fusion of two biometrics: iris and face, have not been described enough so far. Other innovative issue is requirement of a high throughput of the system. The authors plan to authenticate several subjects at the same time by using a distributed computing environment, which is a new approach in this field.

Detailed characteristic of final result

The final result of the project will be the first polish, high-throughput system for biometric identification based on iris pattern and face image able to identify people in a highly unconstrained conditions at a distance and on the move. Such system may be installed at the airports, stadiums or other public facilities, where the authorized fast access is an important issue.