scholarly journals The Impact of Pressure on the Fingerprint Impression: Presentation Attack Detection Scheme

2021 ◽  
Vol 11 (17) ◽  
pp. 7883
Author(s):  
Anas Husseis ◽  
Judith Liu-Jimenez ◽  
Raul Sanchez-Reillo
Keyword(s):  
Error Rate ◽  
Attack Detection ◽  
Fingerprint Recognition ◽  
Classification Error ◽  
Final Decision ◽  
Classification Error Rate ◽  
Detection Scheme ◽  
Bona Fide ◽  
The Impact ◽  
Presentation Attack Detection

Fingerprint recognition systems have been widely deployed in authentication and verification applications, ranging from personal smartphones to border control systems. Recently, the biometric society has raised concerns about presentation attacks that aim to manipulate the biometric system’s final decision by presenting artificial fingerprint traits to the sensor. In this paper, we propose a presentation attack detection scheme that exploits the natural fingerprint phenomena, and analyzes the dynamic variation of a fingerprint’s impression when the user applies additional pressure during the presentation. For that purpose, we collected a novel dynamic dataset with an instructed acquisition scenario. Two sensing technologies are used in the data collection, thermal and optical. Additionally, we collected attack presentations using seven presentation attack instrument species considering the same acquisition circumstances. The proposed mechanism is evaluated following the directives of the standard ISO/IEC 30107. The comparison between ordinary and pressure presentations shows higher accuracy and generalizability for the latter. The proposed approach demonstrates efficient capability of detecting presentation attacks with low bona fide presentation classification error rate (BPCER) where BPCER is 0% for an optical sensor and 1.66% for a thermal sensor at 5% attack presentation classification error rate (APCER) for both.

scholarly journals Fingerprint Presentation Attack Detection using Referential Quality Metrics and Minutiae Count

2021 ◽  
Author(s):  
Akhilesh Verma ◽  
Anshadha Gupta ◽  
Mohammad Akbar ◽  
Arun Kumar Yadav ◽  
Divakar Yadav
Keyword(s):  
Neural Network ◽  
Error Rate ◽  
State Of The Art ◽  
User Authentication ◽  
Attack Detection ◽  
Classification Error ◽  
The Public ◽  
The Past ◽  
Biometric Systems ◽  
Presentation Attack Detection

Abstract The fingerprint presentation attack is still a major challenge in biometric systems due to its increased applications worldwide. In the past, researchers used Fingerprint Presentation Attack Detection (FPAD) for user authentication, but it suffers from reliable authentication due to less focus on reducing the ‘error rate’. In this paper, we proposed an algorithm, based on referential image quality (RIQ)-metrics and minutiae count using neural network, k-NN and SVM for FPAD. We evaluate and validate the error rate reduction with different machine learning models on the public domain, such as LivDet crossmatch dataset2015 and achieved an accuracy of 88% with a neural network, 88.6% with k-NN and 88.8% using SVM. In addition, the average classification error (ACE) score is 0.1197 for ANN, 0.1138 for k-NN and 0.1117 for SVM. Thus, the results obtained show that it was achieved a reasonable accuracy with a low ACE score with respect to other state-of-the-art methods.

Fingerprint Presentation Attack Detection Using Transfer Learning Approach

2021 ◽  
Vol 17 (1) ◽  
pp. 53-67
Author(s):  
Rajneesh Rani ◽  
Harpreet Singh
Keyword(s):  
Transfer Learning ◽  
Attack Detection ◽  
Classification Error ◽  
Learning Approach ◽  
Biometric Authentication ◽  
The Past ◽  
Liveness Detection ◽  
Fingerprint Liveness Detection ◽  
Software And Hardware ◽  
Presentation Attack Detection

In this busy world, biometric authentication methods are serving as fast authentication means. But with growing dependencies on these systems, attackers have tried to exploit these systems through various attacks; thus, there is a strong need to protect authentication systems. Many software and hardware methods have been proposed in the past to make existing authentication systems more robust. Liveness detection/presentation attack detection is one such method that provides protection against malicious agents by detecting fake samples of biometric traits. This paper has worked on fingerprint liveness detection/presentation attack detection using transfer learning for which the authors have used a pre-trained NASNetMobile model. The experiments are performed on publicly available liveness datasets LivDet 2011 and LivDet 2013 and have obtained good results as compared to state of art techniques in terms of ACE(average classification error).

scholarly journals A variant of gravitational classification

2014 ◽  
Vol 51 (1) ◽  
pp. 1-12 ◽  
Author(s):  
Tomasz Górecki ◽  
Maciej Luczak
Keyword(s):  
Gravity Field ◽  
Error Rate ◽  
Simulation Method ◽  
General Idea ◽  
Classification Error ◽  
Data Sets ◽  
Classification Error Rate ◽  
Motion Problem ◽  
The Mean ◽  
Parameter Values

Summary In this article there is proposed a new two-parametrical variant of the gravitational classification method. We use the general idea of objects' behavior in a gravity field. Classification depends on a test object's motion in a gravity field of training points. To solve this motion problem, we use a simulation method. This classifier is compared to the 1NN method, because our method tends towards it for some parameter values. Experimental results on different data sets demonstrate an improvement in efficiency and that this approach outperforms the 1NN method by providing a significant reduction in the mean classification error rate.

scholarly journals Effect of chronic and acute heat challenges on fecal microbiota composition, production, and thermoregulation traits in growing pigs1,2

2019 ◽  
Vol 97 (9) ◽  
pp. 3845-3858 ◽  
Author(s):  
Mathilde Le Sciellour ◽  
Olivier Zemb ◽  
Isabelle Hochu ◽  
Juliette Riquet ◽  
Hélène Gilbert ◽  
...  
Keyword(s):  
Heat Stress ◽  
Error Rate ◽  
Fecal Microbiota ◽  
Sensu Stricto ◽  
Growing Pigs ◽  
Partial Least Square ◽  
Least Square ◽  
Classification Error ◽  
Microbiota Composition ◽  
The Impact

Abstract The present study aimed at investigating the impact of heat challenges on gut microbiota composition in growing pigs and its relationship with pigs’ performance and thermoregulation responses. From a total of 10 F1 sire families, 558 and 564 backcross Large White × Créole pigs were raised and phenotyped from 11 to 23 wk of age in temperate (TEMP) and in tropical (TROP) climates, respectively. In TEMP, all pigs were subjected to an acute heat challenge (3 wk at 29 °C) from 23 to 26 wk of age. Feces samples were collected at 23 wk of age both in TEMP and TROP climate (TEMP23 and TROP23 samples, respectively) and at 26 wk of age in TEMP climate (TEMP26 samples) for 16S rRNA analyses of fecal microbiota composition. The fecal microbiota composition significantly differed between the 3 environments. Using a generalized linear model on microbiota composition, 182 operational taxonomic units (OTU) and 2 pathways were differentially abundant between TEMP23 and TEMP26, and 1,296 OTU and 20 pathways between TEMP23 and TROP23. Using fecal samples collected at 23 wk of age, pigs raised under the 2 climates were discriminated with 36 OTU using a sparse partial least square discriminant analysis that had a mean classification error-rate of 1.7%. In contrast, pigs in TEMP before the acute heat challenge could be discriminated from the pigs in TEMP after the heat challenge with 32 OTU and 9.3% error rate. The microbiota can be used as biomarker of heat stress exposition. Microbiota composition revealed that pigs were separated into 2 enterotypes. The enterotypes were represented in both climates. Whatever the climate, animals belonging to the Turicibacter–Sarcina–Clostridium sensu stricto dominated enterotype were 3.3 kg heavier (P < 0.05) at 11 wk of age than those belonging to the Lactobacillus-dominated enterotype. This latter enterotype was related to a 0.3 °C lower skin temperature (P < 0.05) at 23 wk of age. Following the acute heat challenge in TEMP, this enterotype had a less-stable rectal temperature (0.34 vs. 0.25 °C variation between weeks 23 and 24, P < 0.05) without affecting growth performance (P > 0.05). Instability of the enterotypes was observed in 34% of the pigs, switching from an enterotype to another between 23 and 26 wk of age after heat stress. Despite a lower microbial diversity, the Turicibacter–Sarcina–Clostridium sensu stricto dominated enterotype was better adapted to heat stress conditions with lower thermoregulation variations.

Connectionist Approach to Improving Highway Vehicle Classification Schemes

2005 ◽  
Vol 1917 (1) ◽  
pp. 182-189
Author(s):  
Valerian Kwigizile ◽  
Renatus N. Mussa ◽  
Majura Selekwa
Keyword(s):  
Neural Networks ◽  
Error Rate ◽  
Classification Problem ◽  
Vehicle Classification ◽  
Classification Error ◽  
Classification Error Rate ◽  
Pattern Recognition Problem ◽  
Vehicle Weight ◽  
Load Spectra ◽  
Set Up

The mechanistic–empirical pavement design methodology being developed under NCHRP Project 1–37A will require accurate classification of vehicles to develop axle load spectra information needed as the design input. Scheme F, used by most states to classify vehicles, can be used to develop the required load spectra. Unfortunately, the scheme is difficult to automate and is prone to errors resulting from imprecise demarcation of class thresholds. In this paper, the classification problem is viewed as a pattern recognition problem in which connectionist techniques such as probabilistic neural networks (PNN) can be used to assign vehicles to their correct classes and hence to establish optimum axle spacing thresholds. The PNN was developed, trained, and applied to field data composed of individual vehicles’ axle spacing, number of axles per vehicle, and overall vehicle weight. The PNN reduced the error rate from 9.5% to 6.2% compared with an existing classification algorithm used by the Florida Department of Transportation. The inclusion of overall vehicle weight as a classification variable further reduced the error rate from 6.2% to 3.0%. The promising results from neural networks were used to set up new thresholds that reduce classification error rate.

Using Classification Error Rate a New Image-Extraction Method of Debris Cloud at Hypervelocity Impact

2015 ◽  
Vol 63 (4) ◽  
pp. 157-165
Author(s):  
Yoshihiro OKI ◽  
Norihiko MATSUMOTO ◽  
Kiyonobu OHTANI ◽  
Sunao HASEGAWA ◽  
Kanjuro MAKIHARA
Keyword(s):  
Error Rate ◽  
Extraction Method ◽  
Hypervelocity Impact ◽  
Classification Error ◽  
Classification Error Rate ◽  
Debris Cloud

An Evaluation of Smoothed Classification Error – Rate Estimators

Technometrics ◽  
1985 ◽  
Vol 27 (2) ◽  
pp. 199-206 ◽  
Author(s):  
Steven M. Snapinn ◽  
James D. Knoke
Keyword(s):  
Error Rate ◽  
Classification Error ◽  
Classification Error Rate
Sign in / Sign up

Export Citation Format

Share Document