Wyniki wyszukiwania - Biblioteka Nauki

1

GENDER RECOGNIOTION METHODS USEFUL IN MOBILE AUTHENTICATION APPLICATIONS

100%

Stawska Z. , Milczarski P.

Information Systems in Management

|

2016

|

tom 5

|

nr 2

248-259

EN

Soft biometrics methods that involve gender, age and ethnicity are still developed. Face recognition methods often rely on gender recognition. The same applies to the methods reconstructing the faces or building 2D or 3D models of the faces. In the paper, we conduct study on different set of gender recognition methods and their mobile applications. We show the advantages and disadvantages of that methods and future challenges to the researches. In the previous papers, we examined a range variety of skin detection methods that help to spot the face in the images or video stream. On acquiring faces, we focus on gender recognition that will allow us to create pattern to build 2D and 3D automatic faces models from the images. That will result also in face recognition and authentication, also.

2

Person identification system using an identikit picture of the suspect

100%

Bobulski J. , Kubanek M.

Optica Applicata

|

2012

|

tom Vol. 42, nr 4

865--873

EN

The article presents a person identification system, which may work with an identikit picture. The identikit picture (sketch) is often used in practice as an investigative tool to search for the perpetrators of an unknown identity. With a portrait of the perpetrator of a crime, one may identify the criminal. When the face database for comparisons is large, this is labour-absorbing. With the help of a computer system of face identification, this process becomes quick and easy.

3

Cross Entropy Clustering Approach to Iris Segmentation for Biometrics Purpose

100%

Misztal K. , Spurek P. , Saeed E. , Saeed K. , Tabor J.

Schedae Informaticae

|

2015

|

tom Vol. 24

31--40

EN

This work presents the step by step tutorial for how to use cross entropy clustering for the iris segmentation. We present the detailed construction of a suitable Gaussian model which best fits for in the case of iris images, and this is the novelty of the proposal approach. The obtained results are promising, both pupil and iris are extracted properly and all the information necessary for human identification and verification can be extracted from the found parts of the iris.

4

Detection of human faces in thermal infrared images

100%

Kowalski M. Ł. , Grudzień A. , Ciurapiński W.

Metrology and Measurement Systems

|

2021

|

tom Vol. 28, nr 2

307--321

EN

The presented study concerns development of a facial detection algorithm operating robustly in the thermal infrared spectrum. The paper presents a brief review of existing face detection algorithms, describes the experiment methodology and selected algorithms. For the comparative study of facial detection three methods presenting three different approaches were chosen, namely the Viola-Jones, YOLOv2 and Faster-RCNN. All these algorithms were investigated along with various configurations and parameters and evaluated using three publicly available thermal face datasets. The comparison of the original results of various experiments for the selected algorithms is presented.

5

Complex Colour Detection Methods Used in Skin Detection Systems

100%

Milczarski P. , Stawska Z.

Information Systems in Management

|

2014

|

tom 3

|

nr 1

40-52

EN

In this paper we present high computational complexity algorithms for detecting skin and non-skin colour. Because of their complexity they are not suitable for nowadays mobile devices but can be used in systems working on more demanding machines. The selection and implementation of algorithms gives accuracy about 80-90%.

6

Possibilities for the use of biometric data in security systems

100%

Kopczewski M. , Smal T.

Zeszyty Naukowe / Wyższa Szkoła Oficerska Wojsk Lądowych im. gen. T. Kościuszki

|

2017

|

tom Nr 4

168--179

EN

Possibilities for the use of biometric data are growing and hence their practical application is also increasing. Therefore, an important element to be considered in the design, construction and exploitation of systems using biometrics is the question of identifying a specific person and assigning him or her to the relevant data contained in the documents or databases. The ability and, in some cases, the need to use biometric data results from the growing use of information technology in everyday life and the ever increasing attempts to steal the identity of those using these technologies. Modern IT systems often have a high level of security in terms of protection and access to data, and in particular the management of security systems. The article presents an outline of the theory related to the possibility of using and applying biometric data to provide security and have the ability to inspect officers of various departments. The subject of analysis also considered the possibility of using security measures in the form of biometric data identification for the purpose of securing the security services.

7

A new hand-movement-based authentication method using feature importance selection with the hotelling’s statistic

100%

Doroz R. , Wrobel K. , Porwik P. , Orczyk T.

Journal of Artificial Intelligence and Soft Computing Research

|

2022

|

tom Vol. 12, No. 1

41--59

EN

The growing amount of collected and processed data means that there is a need to control access to these resources. Very often, this type of control is carried out on the basis of biometric analysis. The article proposes a new user authentication method based on a spatial analysis of the movement of the finger’s position. This movement creates a sequence of data that is registered by a motion recording device. The presented approach combines spatial analysis of the position of all fingers at the time. The proposed method is able to use the specific, often different movements of fingers of each user. The experimental results confirm the effectiveness of the method in biometric applications. In this paper, we also introduce an effective method of feature selection, based on the Hotelling T2 statistic. This approach allows selecting the best distinctive features of each object from a set of all objects in the database. It is possible thanks to the appropriate preparation of the input data.

8

Gender recogniotion methods useful in mobile authentication applications

100%

Stawska Z. , Milczarski P.

Information Systems in Management

|

2016

|

tom Vol. 5, No. 2

248--259

EN

Soft biometrics methods that involve gender, age and ethnicity are still developed. Face recognition methods often rely on gender recognition. The same applies to the methods reconstructing the faces or building 2D or 3D models of the faces. In the paper, we conduct study on different set of gender recognition methods and their mobile applications. We show the advantages and disadvantages of that methods and future challenges to the researches. In the previous papers, we examined a range variety of skin detection methods that help to spot the face in the images or video stream. On acquiring faces, we focus on gender recognition that will allow us to create pattern to build 2D and 3D automatic faces models from the images. That will result also in face recognition and authentication, also.

9

Robust and Accurate Iris Segmentation Algorithm for Color and Noisy Eye Images

100%

Strzelczyk P.

Journal of Telecommunications and Information Technology

|

2010

|

tom nr 4

5-9

EN

Efficient and robust segmentation of iris images captured in the uncontrolled environments is one of the challenges of non-cooperative iris recognition systems. We address this problem by proposing a novel iris segmentation algorithm, which is suitable both for monochrome and color eye images. The method presented use modified Hough transform to roughly localize the possible iris and pupil boundaries, approximating them by circles. A voting mechanisms is applied to select a candidate iris regions. The detailed iris boundary is approximated by the spline curve. Its shape is determined by minimizing introduced boundary energy function. The described algorithm was submitted to the NICE.I iris image segmentation contest, when it was ranked 11th and 10th out of total 97.

10

Simulation Model of Biometric Authentication Using Multiagent Approach

100%

Kapczyński A. , Owczarek T.

Journal of Telecommunications and Information Technology

|

2010

|

tom nr 4

68-74

EN

In this article authors present the concept of application of multiagent approach in modeling biometric authentication systems. After short introduction, we present a short primer to multiagent technology. Next, we depict current state of the art related to biometrics combined with multiagent approach. In the next part of the work we present four exemplary simulation models of biometric authentication environments as well as the results of their examination.

11

Iris Recognition System Based on Zak-Gabor Wavelet Packets

100%

Czajka A. , Pacut A.

Journal of Telecommunications and Information Technology

|

2010

|

tom nr 4

10-18

EN

The paper proposes a new iris coding method based on Zak-Gabor wavelet packet transform. The essential component of the iris recognition methodology design is an effective adaptation of the transformation parameters that makes the coding sensitive to the frequencies characterizing ones eye. We thus propose to calculate the between-to-within class ratio of weakly correlated Zak-Gabor transformation coefficients allowing for selection the frequencies the most suitable for iris recognition. The Zak-Gabor-based coding is non-reversible, i.e., it is impossible to reconstruct the original iris image given the iris template. Additionally, the inference about the iris image properties from the Zak-Gabor-based code is limited, providing a possibility to embed the biometric replay attack prevention methodology into the coding. We present the final prototype system design, including the hardware, and evaluate its performance using the database of 720 iris images.

12

Face Tracking and Recognition with the Use of Particle-Filtered Local Features

100%

Stasiak Ł. A. , Pacut A.

Journal of Telecommunications and Information Technology

|

2010

|

tom nr 4

26-36

EN

A consistent particle filtering-based framework for the purpose of parallel face tracking and recognition from video sequences is proposed. A novel approach to defining randomized, particle filtering-driven local face features for the purpose of recognition is proposed. The potential of cumulating classification decisions based on the proposed feature set definition is evaluated. By applying cumulation mechanisms to the classification results determined from single frames and with the use of particle-filtered features, good recognition rates are obtained at the minimal computational cost. The proposed framework can operate in real-time on a typical modern PC. Additionally, the application of cumulation mechanisms makes the framework resistant to brief visual distortions, such as occlusions, head rotations or face expressions. A high performance is also obtained on low resolution images (video frames). Since the framework is based on the particle filtering principle, it is easily tunable to various application requirements (security level, hardware constraints).

13

Probabilistic Issues in Biometric Template Design

100%

Pacut A.

Journal of Telecommunications and Information Technology

|

2010

|

tom nr 4

75-85

EN

Since the notion of biometric template is not well defined, various concepts are used in biometrics practice. In this paper we present a systematic view on a family of template concepts based on the L1 or L2 dissimilarities. In particular, for sample vectors of independent components we find out how likely it is for the median code to be a sample vector.

14

Iris identification method using only a section of the pattern

100%

Bobulski J.

Optica Applicata

|

2018

|

tom Vol. 48, nr 1

149--160

EN

Iris based authentication methods are popular due to their reliability and dependability. This paper proposes the method of the iris recognition that instead uses only two fragments of the pattern. The presented method allows for a simpler iris extraction, as it does not use a complex conversion of an iris pattern from a circular to rectangular shape. The results obtained from this experiment show similarities to other previous ones. Importantly, the proposed method may be treated as an alternative solution. The experiment confirmed the validity of the concept for the proposed iris recognition method. Moreover, this method is quicker in comparison to the others. The additional merit of the proposed solution is the elimination of the distortion which comes from the eyelids and eyelashes at the beginning of the iris image processing. Moreover, this method does not require using additional techniques to eliminate disturbances.

15

Privacy Preserving and Secure Iris-Based Biometric Authentication for Computer Networks

100%

Strzelczyk P.

Journal of Telecommunications and Information Technology

|

2011

|

tom nr 4

115-118

EN

The iris biometrics is considered one of the most accurate and robust methods of the identity verification. The unique iris features of an individual can be presented in a compact binary form which can be easily compared with the reference template to confirm identity. However in contrast to passwords and PINs biometric authentication factors cannot be revoked and changed as they are inherently connected to our characteristics. Once the biometric information is compromised or disclosed it became useless for the purpose of authentication. Therefore there is a need to perform iris features matching without revealing the features itself and the reference template. We propose an extension of the standard irisbased verification protocol which introduces a features and template locking mechanism, which guarantee that no sensitive information is exposed. Presented solutions can be easily integrated into authentication mechanisms used in modern computer networks.

16

ALGORITHMS AND METHODS USED IN SKIN AND FACE DETECTION SUITABLE FOR MOBILE APPLICATIONS

100%

STAWSKA Z. , MILCZARSKI P.

Information Systems in Management

|

2013

|

tom 2

|

nr 3

227-238

EN

Face detection is one of the most important issues in the identification and authentication systems that use biometric features. In this paper we present algorithms for detecting skin colour. The selection and implementation of an algorithm for automated authentication system and face detection can significantly improve the effectiveness of such a system. In the paper we examine several algorithms and methods that can be used in mobile application for authentication purpose i.e. NFC payments.

17

Fingerprint identification by using artificial neural network with optical wavelet preprocessing

100%

Antowiak M. , Chałasińska-Macukow K.

Opto-Electronics Review

|

2003

|

tom Vol. 11, No. 4

327-337

EN

The advantages of optical wavelet transform used as a preprocessor for an artificial neural network are investigated. We show by digital simulation that this set-up can successfully identify and discriminate complex biometric images, such as fingerprints. The achieved capabilities include limited shift-, rotation-, scale- and intensity - invariance. We also show that the edges-enhancement filter, applied before the wavelet transform, significantly improves abilities of the system.

18

COMPACT: biometric dataset of face images acquired in uncontrolled indoor environment

100%

Włodarczyk M. , Kacperski D. , Sankowski W. , Grabowski K.

Computer Science

|

2019

|

tom Vol. 20 (1)

3--26

EN

Biometric databases are important components that help improve the performanceof state-of-the-art recognition applications. The availability of more andmore challenging data is attracting the attention of researchers, who are systematicallydeveloping novel recognition algorithms and increasing the accuracyof identification. Surprisingly, most of the popular face datasets (like LFW orIJBA) are not fully unconstrained. The majority of the available images werenot acquired on-the-move, which reduces the amount of blurring that is causedby motion or incorrect focusing. Therefore, the COMPACT database for studyingless-cooperative face recognition is introduced in this paper. The datasetconsists of high-resolution images of 108 subjects acquired in a fully automatedmanner as people go through the recognition gate. This ensures that the collecteddata contains real-world degradation factors: different distances, expressions,occlusions, pose variations, and motion blur. Additionally, the authorsconducted a series of experiments that verified the face-recognition performanceon the collected data.

19

Ograniczenia w pomiarach biometrycznych

100%

Gołembiewski J.

Pomiary Automatyka Kontrola

|

2007

|

tom R. 53, nr 9 bis

384--385

PL

Pomiary biometryczne mogą służyć do identyfikacji lub weryfikacji osób. W artykule, na przykładzie systemu biometrycznego rozpoznawania twarzy i rozpoznawania dłoni, przedstawiono ograniczenia występujące w pomiarach biometrycznych. W trybie identyfikacji wyznaczany jest wzorzec biometryczny, który jest następnie porównywany ze zbiorem wszystkich disteobtcg wzorców. W trybie weryfikacji, sprawdzany jest wzorzec przypisany wcześniej kontrolowanej osobie, z uzyskanym w trakcie pomiarów biometrycznych. Błąd fałszywej akcetacji dla identyfikacji powinien być mniejszy od setnych części procenta. Dla weryfikacji wskaźnik ten może osiągać wartość kilku procent.

EN

Biometrics measurements can be applied to person`s identyfication or verification. In paper, using as example the biometric system recognising face and palm, some limitations existing in biometric measurements are discussed. In the identification case the system is trained with patterns of severan persons, a biometric template is calculated, and then is matched against every known template. In the verification mode a person`s identity is claimed a priori and is compared with the person`s individual template. False acceptance rate for identificatio should be less than 0.01% and several percentage for verification, respectively.

20

Polish Personal Identity Card as a Tool for Identity Theft

100%

Owoc M.

Journal of Telecommunications and Information Technology

|

2015

|

tom nr 2

23--24

EN

This article discusses the changes that are the result of entry the new personal ID card issued in Poland. The new document contains less information about the owner, i.e. height, eye color or signature, so that the risk of identity theft is signicantly greater.