Wyniki wyszukiwania - BazTech

1

Biometrics gait system based on motion sensors embedded in a mobile phone: a case study for a two-day training set

Sawicki Aleksander, Saeed Khalid

International Journal of Electronics and Telecommunications

|

2025

|

Vol. 71, No. 2

545-553

EN

This paper presents the results of a study on developing a gait biometrics system based on motion sensors (an accelerometer and gyroscope), embedded in a smartphone. The experiments were conducted using a publicly available 13-person data corpus, with subjects participating in three data collection sessions. The study used CNN, CNN with attention and Multi-Input CNN neural networks. The training scenario from the first day resulted in an accuracy of 0.66 F1 score, 0.71 F1 score for training with the samples from the second day and 0.90 F1 score in the combined sets. It has been shown that it is more profitable to combine historical data than to update it with newer samples. Enriching the training set with a set of 30% synthetic samples produced by the LSTM-MDN generative models allowed to increase to accuracy to 0.94 F1-score. It was shown that synthetic samples can improve the generalization properties of the CNN network.

2

Forearm vein pattern recognition using features from visible and NIR images

Choraś Ryszard S.

Studia Informatica : systems and information technology

|

2024

|

vol. 1 (30)

5--19

EN

Forearm vein recognition is one of many available methods used for iden-tification. However, forearm veins can be considered more secure compared to otherbiometric traits because the veins are inside the human body and therefore not easilymanipulated. Veins possess several properties that make a good biometric feature forpersonal identification: 1) they are difficult to damage and modify; 2) they are difficultto simulate using a fake template; and 3) vein information can represent the liveness ofperson. Features were extracted from each pair of visible and NIR images. For the visibleimages, feature extraction was done using the Gabor filter. For the NIR forearm images,a crossing number was used to extract properties of the veins e.g. bifurcation. We presentthe results of the recognition of forearm veins patterns that show the suitability of themethod for biometric identification purposes.

3

Evaluating neural network models for predicting dynamic signature signals

Zalasiński Marcin, Cader Andrzej, Patora-Wysocka Zofia, Xiao Min

Journal of Artificial Intelligence and Soft Computing Research

|

2024

|

Vol. 14, No. 4

361--372

EN

A signature is a biometric attribute commonly used for identity verification. It can be represented by a shape created with a classic pen, but it can also contain dynamic information. This information is acquired using a digital input device, such as a graphic tablet or a digital screen and stylus. Information about the dynamics of the signing process is stored in the form of signals that change over time, including pen velocity, pressure, and more. These dynamics are characteristic of an individual and are difficult for a human to forge. However, it is an interesting research issue whether the values of signals describing a dynamic signature can be predicted using artificial intelligence methods. Predicting the dynamics of the signals describing a signature would benefit various scientific problems, including improving the quality of reference signals by detecting anomalies, creating signature templates better suited to individuals, and more effectively detecting potential forgeries by identity verification systems. In this paper, we propose a method for predicting dynamic signature signals using an artificial neural network. The method was evaluated using samples collected in the DeepSignDB database, distributed by BiDA Lab.

4

Subjective tests of speaker recognition for selected voice disguise techniques

Staroniewicz Piotr

International Journal of Electronics and Telecommunications

|

2024

|

Vol. 70, No. 3

615-620

EN

Research work on the effectiveness of voice disguise techniques is important for the development of biometric systems (surveillance) as well as phonoscopic research (forensics). A speaker recognition system or a listener can be deliberately or non-deliberately misled by technical or natural methods. It is important to determine the impact of these techniques on both automatic systems and live listeners. This paper presents the results of listening tests conducted on a group of 40 people. The effectiveness of speaker recognition was investigated using selected natural (chosen from four groups of deliberate natural techniques: phonation, phonemic, prosodic and deformation) and technical (pitch shifting, GSM coding) voice disguise techniques. The results were related to the previously obtained outcomes for the automatic method of verification carried out using a classical speaker recognition system based on MFCC (Mel Frequency Cepstral Coefficients) parameterisation and GMM (Gaussian Mixture Models) classification.

5

Analiza potencjału ataków wykorzystujących syntetycznie wygenerowane głosy na systemy biometrycznej weryfikacji mówców oraz wykrywania materiałów deepfake

Bartuzi-Trokielewicz Ewelina

Cybersecurity and Law

|

2024

|

Vol. 12 (2)

25--36

PL

Postęp technologiczny w dziedzinie głębokiego uczenia znacząco przyczynił się do roz-woju syntezowania głosu, umożliwił tworzenie realistycznych nagrań audio, które mogą naśladować indywidualne cechy głosów ludzkich. Chociaż ta innowacja otwiera nowe możliwości w dziedzinie technologii mowy, niesie ze sobą również poważne obawy dotyczące bezpieczeństwa, zwłaszcza w kontekście potencjalnego wykorzystania technologii deepfake do celów przestępczych. Przeprowadzone badanie koncentrowało się na ocenie wpływu syntetycznych głosów na systemy biometrycznej weryfikacji mówców w języku polskim oraz skuteczności wykrywania deepfake’ów narzędziami dostępnymi publicznie, z wykorzystaniem dwóch głównych metod generowania głosu, tj. przekształcenia tekstu na mowę oraz konwersji mowy. Jednym z głównych wniosków analizy jest potwierdzenie zdolności syntetycznych głosów do zachowania charakterystycznych cech biometrycznych i otwierania drogi przestępcom do nieautoryzowanego dostępu do zabezpieczonych systemów lub danych. To podkreśla potencjalne zagrożenia dla indywidualnych użytkowników oraz instytucji, które polegają na technologiach rozpoznawania mówcy jako metodzie uwierzytelniania i wskazuje na konieczność wdrażania modułów wykrywania ataków. Badanie ponadto pokazało, że deepfaki odnalezione w polskiej części internetu dotyczące promowania fałszywych inwestycji lub kierowane w celach dezinformacji najczęściej wykorzystują popularne i łatwo dostępne narzędzia do syntezy głosu. Badanie przyniosło również nowe spojrzenie na różnice w skuteczności metod kon-wersji tekstu na mowę i klonowania mowy. Okazuje się, że metody klonowania mowy mogą być bardziej skuteczne w przekazywaniu biometrycznych cech osobniczych niż metody konwersji tekstu na mowę, co stanowi szczególny problem z punktu widzenia bezpieczeństwa systemów weryfikacji. Wyniki eksperymentów podkreślają potrzebę dalszych badań i rozwoju w dziedzinie bezpieczeństwa biometrycznego, żeby skutecznie przeciwdziałać wykorzystywaniu syntetycznych głosów do nielegalnych działań. Wzrost świadomości o potencjalnych zagrożeniach i kontynuacja pracy nad ulepszaniem technologii weryfikacji mówców są ważne dla ochrony przed coraz bardziej wyrafinowanymi atakami wykorzystującymi technologię deepfake.

EN

Technological advancements in the field of deep learning have significantly contributed to the development of voice synthesis, enabling the creation of realistic audio recordings that can mimic the individual characteristics of human voices. While this innovation opens up new possibilities in the field of speech technology, it also raises serious security concerns, especially in the context of the potential use of deepfake technology for criminal purposes. Our study focuses on assessing the impact of synthetic voices on biometric speaker verification systems in Polish and the effectiveness of detecting deepfakes with publicly available tools, considering two main approaches to voice generation: text-to-speech conversion and speech conversion. One of the main findings of our research is the confirmation that synthetic voices are capable of retaining biometric characteristics, which could allow criminals unauthorized access to protected systems or data. The analysis showed that the greater the biometric similarity between the „victim’s” voice and the „criminal’s” synthetic voice, the more difficult it is for verification systems to distinguish between real and fake voices. This highlights the potential threats to individual users and institutions that rely on speaker recognition technologies as a method of authentication. Our study also provides a new perspective on the differences in the effectiveness of text-to-speech conversion methods versus speech cloning. It turns out that speech cloning methods may be more effective in conveying individual biometric characteristics than text-to-speech conversion methods, posing a particular problem from the security perspective of verification systems. The results of the experiments underscore the need for further research and development in the field of biometric security to effectively counteract the use of synthetic voices for illegal activities. Increasing awareness of potential threats and continuing work on improving speaker verification technologies are crucial for protecting against increasingly sophisticated attacks utilizing deepfake technology.

6

Biometrics-based generation of Diffie-Hellman key exchange parameters

Kovačević Aldin, Saračević Muzafer, Hasić Amor

Computer Science

|

2024

|

T. 25 (3)

421--434

EN

When two parties need to securely communicate over an insecure channel, Diffie-Hellman is often employed as the key exchange algorithm. This paper presents two novel approaches to generating Diffie-Hellman parameters for key exchange based on user biometrics, namely their fingerprint data. Fingerprint templates are extracted as bit strings via a fingerprint scanner and later usedas inputs. In one approach, the whole fingerprint template is utilized as a user’s private key. In the second approach, fingerprint data is scrambled into smaller chunks and rearranged into two strings that serve as the user’s private key and the basis for prime p. Both approaches were implemented and tested experimentally. After analysis, the second approach that uses scrambled fingerprint data shows better execution times and improved security and usability considerations.

7

Recognition of human gait based on ground reaction forces and combined data from two gait laboratories

Derlatka Marcin, Skublewska-Paszkowska Maria, Powroźnik Paweł, Smołka Jakub, Łukasik Edyta, Borysiewicz Agnieszka, Borkowski Piotr, Czerwiński Dariusz

Acta Mechanica et Automatica

|

2024

|

Vol. 18, no. 2

361--366

EN

In a world in which biometric systems are used more and more often within our surroundings while the number of publications related to this topic grows, the issue of access to databases containing information that can be used by creators of such systems becomes important. These types of databases, compiled as a result of research conducted by leading centres, are made available to people who are interested in them. However, the potential combination of data from different centres may be problematic. The aim of the present work is the verification of whether the utilisation of the same research procedure in studies carried out on research groups having similar characteristics but at two different centres will result in databases that may be used to recognise a person based on Ground Reaction Forces (GRF). Studies conducted for the needs of this paper were performed at the Bialystok University of Technology (BUT) and Lublin University of Technology (LUT). In all, the study sample consisted of 366 people allowing the recording of 6,198 human gait cycles. Based on obtained GRF data, a set of features describing human gait was compiled which was then used to test a system’s ability to identify a person on its basis. The obtained percentage of correct identifications, 99.46% for BUT, 100% for LUT and 99.5% for a mixed set of data demonstrates a very high quality of features and algorithms utilised for classification. A more detailed analysis of erroneous classifications has shown that mistakes occur most often between people who were tested at the same laboratory. Completed statistical analysis of select attributes revealed that there are statistically significant differences between values attained at different laboratories.

8

Electronic anti-theft protection for vehicles of people with special needs

Góral Piotr, Pawłowski Paweł, Nowacki Wiktor, Wróbel Jakub

Systemy Logistyczne Wojsk

|

2023

|

Vol. 59, no. 2

287--298

EN

The article presents an electronic anti-theft protection subsystem that was incorporated into the vehicle control system dedicated to people with special communication needs. The aim of the work was to design and test an electronic subsystem allowing for the acquisition and quick analysis of fingerprint images, checking whether they belong to the vehicle owner and generating a signal allowing the vehicle to be started. The following hypothesis was put forward: it is possible to use artificial intelligence for accurate, automatic classification of fingerprint images acquired in a system with a single-chip microcomputer in order to identify a person. The research niche includes the use of biometrics in electronic anti-theft security adapted to people with special needs. This solution reduces the risk of theft and unauthorized use of special vehicles tailored to the owners’ individual needs. The use of a commercial algorithm offered by the sensor manufacturer or the use of artificial neural networks for the classification of fingerprints was considered. The results of research on the accuracy of fingerprint recognition obtained from the developed subsystem are presented. The experiments performed based on the NASNetLarge artificial neural network model confirmed the possibility of achieving recognition accuracy for the test set of 99.99%. Additionally, practical aspects of the applicability of the presented device in an electric vehicle control system supporting the movement of people with physical and/or intellectual disabilities were discussed. The presented solution, after minor modifications, can be used in access security systems for protected rooms, as well as vehicles and military equipment.

PL

W artykule zaprezentowano elektroniczny podsystem zabezpieczeń przed kradzieżą, który został włączony w system sterowania pojazdu dedykowanego dla osób o szczególnych potrzebach komunikacyjnych. Celem pracy było zaprojektowanie i przebadanie podsystemu elektronicznego pozwalającego na pozyskanie i szybką analizę obrazów odcisków palców, sprawdzenie czy należą do właściciela pojazdu i generowanie sygnału zezwalającego na uruchomienie pojazdu. Postawiono następującą hipotezę: możliwe jest wykorzystanie sztucznej inteligencji do dokładnej, automatycznej klasyfikacji obrazów z liniami papilarnymi, pozyskanych w systemie z mikrokomputerem jednoukładowym, w celu identyfikacji osoby. Nisza badawcza obejmuje wykorzystanie obszaru biometrii w elektronicznych zabezpieczeniach antykradzieżowych dostosowanych do osób o szczególnych potrzebach. Rozwiązanie to pozwala na zmniejszenie ryzyka kradzieży oraz użytkowania przez osoby niepowołane pojazdów specjalnych dostosowanych do indywidualnych potrzeb właścicieli. Rozważono wykorzystanie algorytmu komercyjnego, oferowanego przez producenta czujnika lub wykorzystanie sztucznych sieci neuronowych celem klasyfikacji odcisków placów. Przedstawiono wyniki przeprowadzonych badań nad dokładnością rozpoznawania odcisków palców uzyskane z opracowanego podsystemu. Przeprowadzone eksperymenty w oparciu o model sztucznej sieci neuronowej NASNetLarge potwierdziły możliwość osiągniecia dokładności rozpoznawania dla zbioru testowego na poziomie 99,99%. Dodatkowo, omówiono praktyczne aspekty stosowalności przedstawionego urządzenia w systemie stero- wania pojazdem elektrycznym wspomagającym poruszanie się osób z niepełnosprawnościami fizycznymi i/lub intelektualnymi. Zaprezentowane rozwiązanie, po niewielkich modyfikacjach, może zostać użyte w systemach zabezpieczeń dostępu do pomieszczeń chronionych, a także pojazdów i sprzętu wojskowego.

9

Iris Recognition Based on Local Grey Extremum Values with CNN-based approaches

Malinowski Kamil, Saeed Khalid

Machine Graphics and Vision

|

2023

|

Vol. 32, No. 3/4

205--232

EN

One of the most important steps in the operation of biometric systems based on iris recognition of the human eye is pattern comparison. However, the comparison of the recorded pattern with the pattern stored in the database of the biometric system cannot function properly without effective extraction of key features from the iris image. In the presented work, we propose an iris recognition system based on image feature extraction and extreme grey shade analysis. Harris-Laplace, RANSAC and SIFT descriptor algorithms were used to find and describe key points. In the experimental part, two methods were used to compare descriptors: the Brute Force method and the Siamese Network method. IIT Delhi Iris Database (version 1.0), MMU v2 database, UBIRIS v1, UBIRIS v2 image databases were used for the study. The proposed method utilizes a different approach when using the generalized corner extraction algorithm (Harris-Laplace algorithms) for comparing iris patterns. In addition, we prove that the use of the descriptor and the Siamese neural networks significantly improves the results obtained in the original method based on paths alone in the case of well contrasted infrared images with very low resolutions.

10

Use of artificial intelligence in remote biometric identification systems

Czaplicki Kamil

GIS Odyssey Journal

|

2023

|

Vol. 3, no. 2

107--115

EN

Work is currently underway to regulate the use of artificial intelligence. The article presents the ideas and principles of creating remote biometric identification systems using AI technologies. Risks to privacy and possible scenarios for the use of such systems are presented.

11

Learning-free deep features for multispectral palm-print classification

Aounallah Asma, Meraoumia Abdallah, Bendjenna Hakim

Computer Science

|

2023

|

T. 24 (2)

243--271

EN

The feature-extraction step is a major and crucial step in analyzing and understanding raw data, as it has a considerable impact on system accuracy. Despite the very acceptable results that have been obtained by many handcrafted methods, these can unfortunately have difficulty representing features in the cases of large databases or with strongly correlated samples. In this context, we attempt to examine the discriminability of texture features by proposing a novel, simple, and lightweight method for deep feature extraction to characterize the discriminative power of different textures. We evaluated the performance of our method by using a palm print-based biometric system, and the experimental results (using the CASIA multispectral palm--print database) demonstrate the superiority of the proposed method over the latest handcrafted and deep methods.

12

Gender-aware speaker's emotion recognition based on 1-D and 2-D features

Kasprzak Włodzimierz, Hryciów Mateusz

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

1011--1015

EN

An approach to speaker's emotion recognition based on several acoustic feature types and 1D convolutional neural networks is described. The focus is on selecting the best speech features, improving the baseline model configuration and integrating in the solution a gender classification network. Features include a Mel-scale spectrogram and MFCC- , Chroma-, prosodic- and pitch-related features. Especially, the question whether to use 2-D maps of features or reduce them to 1-D vectors by averaging, is experimentally resolved. Well--known speech datasets RAVDESS, Tess, Crema-D and Savee are used in experiments. It appeared, that the best performing model consists of two convolutional networks for gender-aware classification and one gender classifier. The Chroma features have been found to be obsolete, and even disturbing, given other speech features. The f1 accuracy of proposed solution reached 73.2% on the RAVDESS dataset and 66.5% on all four datasets combined, improving the baseline model by 7.8% and 3%, respectively. This approach is an alternative to other proposed models, which reported accuracy scores of 60% - 71% on the RAVDESS dataset.

13

System weryfikacji tożsamości na bazie Kaldi

Dustor Adam

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2022

|

nr 4

299--302

PL

W artykule omówiono system weryfikacji tożsamości zbudowany w oparciu o specjalistyczny i otwarty pakiet oprogramowania Kaldi oraz przetestowany na dużej i darmowej bazie VoxCeleb przy wykorzystaniu wektorów tożsamości do modelowania głosu. Omówiono także problematykę zasobów mowy wykorzystywanych do testowania głosowych systemów biometrycznych. Przedstawiono wpływ wymiarowości wektorów tożsamości na błędy weryfikacji.

EN

This paper discusses a speaker verification system built with the help of free software Kaldi and tested with the VoxCeleb dataset. The problems with the speaker recognition datasets are also discussed. The results for speaker verification system based on i-vectors are shown as well as the influence of dimensionality of i-vectors on verification errors.

14

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

Doroz Rafal, Wrobel Krzysztof, Porwik Piotr, Orczyk Tomasz

Journal of Artificial Intelligence and Soft Computing Research

|

2022

|

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.

15

Detection of human faces in thermal infrared images

Kowalski Marcin Ł., Grudzień Artur, Ciurapiński Wiesław

Metrology and Measurement Systems

|

2021

|

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.

16

Wizerunek twarzy w identyfikacji i weryfikacji tożsamości

Lewandowski Remigiusz

Kwartalnik Bellona

|

2021

|

Nr 2

31--44

PL

Identyfikatory naturalne są najstarszym i zarazem najdynamiczniej rozwijanym środkiem weryfikacji tożsamości człowieka. Rozwój ten dotyczy zwłaszcza zaawansowanych technik biometrycznych z elementami sztucznej inteligencji. W artykule zostały przedstawione - na tle innych środków identyfikacji człowieka - podstawowe zasady weryfikacji tożsamości na podstawie wizerunku twarzy.

EN

Natural means of identification are the oldest and most dynamically developed ways of verifying human identity. Their development concerns in particular advanced biometric techniques with elements of artificial intelligence. This article presents - against the background of other means of human identification - the basic principles used to verify identity based on the image of the face.

17

Dwuczynnikowe uwierzytelnianie klienta serwisu webowego poprzez weryfikację twarzy i jej mimiki z wykorzystaniem sztucznych sieci neuronowych

Mikulski Mateusz, Piotrowski Zbigniew

Elektronika : konstrukcje, technologie, zastosowania

|

2021

|

Vol. 62, nr 7

17--21

PL

Artykuł przedstawia przykładową implementację uwierzytelniania użytkownika aplikacji internetowej z użyciem danych biometrycznych w postaci twarzy oraz wyrażanej przez twarz emocji. Proces uwierzytelniania polega na porównaniu danych modelowych z danymi wprowadzonych podczas rejestracji do aplikacji.

EN

The article presents an example implementation of web application user authentication with the use of biometric data in the form of a face and emotions expressed by the face. The authentication process consists in comparing the model data with the data entered during registration to the application.

18

Electronic voting – the use of biometric methods for granting, withdrawal and recovery of voters’ permissions

Sobota Marcin, Błoński Kamil, Brożek Oliwia

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2020

|

z. 144

459--468

EN

Purpose: The research paper presents the issues of voting with the use of electronic communication, with emphasis on the mechanisms of granting, withdrawal and recovery of permissions covered by biometric methods. Design/methodology/approach: The work presents a theoretical model. Findings: The proposed solutions ensure compliance with the basic requirements for e-voting, including verification of permissions, ensuring the secrecy of the vote and the possibility of verifying the vote cast by the voter. Practical implications: The presented model of granting, withdrawal and recovery of voters’ permission can be used as a part of practical electronic voting systems. Originality/value: The authors presented a conceptual model of the use of biometrics to grant rights. The authors have not encountered in literature any examples of the use of biometrics for this purpose. Actually, anyone practically used system does not use biometry in the described scope.

19

Wybrane metody rozpoznawania osób na podstawie odcisków palców

Grad Leszek

Przegląd Teleinformatyczny

|

2020

|

T. 8, Nr 1-4 (26)

59--74

PL

W artykule przedstawiono zagadnienie rozpoznawania tożsamości osób na podstawie odcisków palców. Przedstawiono aktualny stan wiedzy, wybrane metody i techniki zarówno opisu obrazu linii papilarnych, jak i metody klasyfikacji.

EN

The paper considers the issue of the identity recognition of persons on the basis of fingerprints. The current state of knowledge, selected methods and techniques of fingerprint image description and classification methods are presented.

20

Comparison of methods for correcting outliers in ECG-based biometric identification

Jun Su, Szmajda Miroslaw, Khoma Volodymyr, Khoma Yuriy, Sabodashko Dmytro, Kochan Orest, Wang Jinfei

Metrology and Measurement Systems

|

2020

|

Vol. 27, nr 3

387--398

EN

The aim of this paper is to compare the efficiency of various outlier correction methods for ECG signal processing in biometric applications. The main idea is to correct anomalies in various segments of ECG waveform rather than skipping a corrupted ECG heartbeat in order to achieve better statistics. Experiments were performed using a self-collected Lviv Biometric Dataset. This database contains over 1400 records for 95 unique persons. The baseline identification accuracy without any correction is around 86%. After applying the outlier correction the results were improved up to 98% for autoencoder based algorithms and up to 97.1% for sliding Euclidean window. Adding outlier correction stage in the biometric identification process results in increased processing time (up to 20%), however, it is not critical in the most use-cases.