A New Multi-filter Framework with Statistical Dense SIFT Descriptor for Spoofing Detection in Fingerprint Authentication Systems

Contreras, Rodrigo Colnago; Nonato, Luís Gustavo; Boaventura, Maurílio; Boaventura, Inês Aparecida Gasparotto; Coelho, Bruno Gomes; Viana, Monique Simplicio

doi:10.1007/978-3-030-87897-9_39

Cited by 5 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, some recent studies also show that dense sampling method can improve the performance of image classification and recognition algorithm more effectively than corner detection method speckle detection method and region detection method and other local invariant feature detection methods [12][13][14]. For feature description, there are many methods, the most famous of which is SIFT descriptor, because its performance is very good, so it has a very wide range of applications in image classification and recognition [15].…”

Section: Brief Introduction Of "Feature Bag" Methods and "Spatial Pyr...mentioning

confidence: 99%

Research on Image Classification and Key Technologies Based on 3D Feature Extraction Algorithm

Lei

Jia

2022

Journal of Sensors

View full text Add to dashboard Cite

Image classification and recognition has a very wide range of applications in computer vision, which involves many fields, such as image retrieval, image analysis, and robot positioning. Especially with the rise of brain science and cognitive science research, as well as the increasing diversification of imaging means, three-dimensional image data mainly based on magnetic resonance image plays an increasingly important role in image classification and recognition, especially in medical image classification and recognition. However, due to the high dimensional characteristics of human magnetic resonance images, human readability is reduced. Therefore, classification and recognition of 3-dimensional images is still a challenge. In order to better extract local features from images and effectively use their spatial information, this paper improved the “feature bag” and “spatial pyramid matching” algorithms on the basis of 3D feature extraction algorithm and proposed an image classification framework based on 3D feature extraction algorithm. Firstly, the multiresolution “3D spatial pyramid” algorithm, the multiscale image segmentation and image representation method, and the SVM classifier and feature fusion method are described. Secondly, the gender information contained in the magnetic resonance images is classified and recognized on the three databases selected in the experiment. Experimental results show that this method can effectively utilize the spatial information of three-dimensional images and achieve satisfactory results in the classification and recognition of human magnetic resonance images.

show abstract

Section: Brief Introduction Of "Feature Bag" Methods and "Spatial Pyr...mentioning

confidence: 99%

Research on Image Classification and Key Technologies Based on 3D Feature Extraction Algorithm

Lei

Jia

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Besides, in the preliminary content of this work [22], three different versions of the developed tool were evaluated. In this work, ten usable instances are considered to solve the problem of detecting life in fingerprints, which are detailed below.…”

Section: Parameters For the Proposed Methods And Practical Instancesmentioning

confidence: 99%

“…The strategy was successfully used in texture analysis to classify malaria parasites and was able to improve the accuracy of classifiers compared to BOVW-based representation techniques. Furthermore, in the preliminary version of this work [22], a specific variant, restricted to the dense version of SIFT descriptor was used in the fingerprint spoofing detection problem. However, to the best of our knowledge, no generalization of this representation of matrix-based pattern descriptors has been proposed and, consequently, little experimentation has been conducted on the problem of detecting fingerprint spoofings.…”

Section: Mapping Descriptors As a Handcrafted Featurementioning

confidence: 99%

“…In detail, software-level detection techniques are divided into two main categories [18]: those based on neural networks, more specifically convolutional neural networks [19], whether deep or not; and those based on handcrafted features [20] that must be used in some classifier, so that the most common features are those produced by texture descriptors, by statistical measurements or by analysis of the region of interest. Regarding this second category, some researchers propose the use of some processes that favor the detection of fraud in biometrics, such as [21,22]: the use of a preprocessing step in the fingerprint images before the construction of features; the use of elaborate techniques for detecting regions of interest; conducting feature reduction to increase the classifier's accuracy; between others. In these cases, it is said that the technique composes a framework based on handcrafted features for spoofing detection in BASs, since the steps of the proposed technique are the same, differing only by the construction of the features that must represent the biometrics.…”

Section: Introductionmentioning

confidence: 99%

“…This work is an extended version of our preliminary work [22]. In this work, we propose a new framework based on handcrafted features to detect fingerprint spoofing.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Multi-Filter Framework for Texture Image Representation Improvement Using Set of Pattern Descriptors to Fingerprint Liveness Detection

Contreras

Nonato

Boaventura³

et al. 2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

The use of user recognition and authentication systems has become very common and is part of everyday routines for many people, guaranteeing access to the automatic teller machines, entrance to the gym or even to smartphones. Among all the biometrics that can be analyzed in this type of system, the fingerprint is the most considered due to the ease of collection, the uniqueness of each user, and the large amount of solid theories and computational libraries available in the scientific literature. However, in recent years, the falsification of these biometrics with synthetic materials, known as spoofing, has become a real threat to these systems. To circumvent these effects without the addition of hardware devices, techniques based on the analysis of texture pattern descriptors were developed. In this work, we propose a new framework based on steps of data augmentation, image processing and replication, and feature fusion and reduction. The method has as main objective to improve the ability of classifiers, or sets of classifiers, to recognize life in fingerprints. Furthermore, it is proposed a generalization of vector representation of patterns described in matrix form from the systematic use of sets of mapping functions. All the proposed material was analyzed on the well-established benchmark of the Liveness Detection competition of the 2009, 2011, 2013 and 2015 editions, presenting an average accuracy of 97.77% and being a competitive strategy in relation to the other techniques that make up the state of the art of specialized literature.

show abstract

An Experimental Analysis on Mapping Strategies for Cepstral Coefficients Multi-projection in Voice Spoofing Detection Problem

Contreras,

Viana,

Guido

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A New Multi-filter Framework with Statistical Dense SIFT Descriptor for Spoofing Detection in Fingerprint Authentication Systems

Cited by 5 publications

References 41 publications

Research on Image Classification and Key Technologies Based on 3D Feature Extraction Algorithm

Research on Image Classification and Key Technologies Based on 3D Feature Extraction Algorithm

A New Multi-Filter Framework for Texture Image Representation Improvement Using Set of Pattern Descriptors to Fingerprint Liveness Detection

An Experimental Analysis on Mapping Strategies for Cepstral Coefficients Multi-projection in Voice Spoofing Detection Problem

Contact Info

Product

Resources

About