scispace - formally typeset
Search or ask a question
Author

Inês Aparecida Gasparotto Boaventura

Bio: Inês Aparecida Gasparotto Boaventura is an academic researcher from Sao Paulo State University. The author has contributed to research in topics: Biometrics & Image segmentation. The author has an hindex of 2, co-authored 3 publications receiving 78 citations.

Papers
More filters
Proceedings ArticleDOI
06 Dec 2012
TL;DR: This paper proposes a latent fingerprint segmentation algorithm whose goal is to separate the fingerprint region (region of interest) from background, and utilizes both ridge orientation and frequency features.
Abstract: Latent fingerprints are routinely found at crime scenes due to the inadvertent contact of the criminals' finger tips with various objects. As such, they have been used as crucial evidence for identifying and convicting criminals by law enforcement agencies. However, compared to plain and rolled prints, latent fingerprints usually have poor quality of ridge impressions with small fingerprint area, and contain large overlap between the foreground area (friction ridge pattern) and structured or random noise in the background. Accordingly, latent fingerprint segmentation is a difficult problem. In this paper, we propose a latent fingerprint segmentation algorithm whose goal is to separate the fingerprint region (region of interest) from background. Our algorithm utilizes both ridge orientation and frequency features. The orientation tensor is used to obtain the symmetric patterns of fingerprint ridge orientation, and local Fourier analysis method is used to estimate the local ridge frequency of the latent fingerprint. Candidate fingerprint (foreground) regions are obtained for each feature type; an intersection of regions from orientation and frequency features localizes the true latent fingerprint regions. To verify the viability of the proposed segmentation algorithm, we evaluated the segmentation results in two aspects: a comparison with the ground truth foreground and matching performance based on segmented region.

77 citations

Proceedings ArticleDOI
15 Aug 2018
TL;DR: The Multi-Scale Local Mapped Pattern (MSLMP) applied for facial recognition was described and a new processing technique was developed based on the average gray levels of the images of the database for deal with difficult databases like MUCT.
Abstract: Facial recognition is one of the most used biometric technologies in automated systems which ensure a person's identity for authorizes access and monitoring. The acceptance of face use has several advantages over other biometric technologies since it is natural, it does not require sophisticated equipment, data acquisition is based on non-invasive approaches, and it can be done remotely, cooperatively or not. Although many facial recognition studies have been done, problems with light variation, facial occlusion, position, expression, and aging are still challenges, because they influence the performance of facial recognition systems and motivate the development of more reliable recognition systems that deal with these problems. In this paper, we describe the Multi-Scale Local Mapped Pattern (MSLMP) applied for facial recognition. Techniques based on genetic algorithms and image processing were applied to increase the performance of the method. The obtained results reach up to 100% of accuracy for some face Database. A very difficult database to deal is the MUCT database which was created in 2010 with the aim of providing images with a high variation of lighting, age, positions, and ethnicities in the facial biometry literature, which makes it a highly difficult database in relation to automated recognition. A new processing technique was developed based on the average gray levels of the images of the database for deal with difficult databases like MUCT. The results obtained with our techniques for MUCT database are superior to results obtained for recognition techniques applied to this database available in the literature.

7 citations

Book ChapterDOI
20 Jun 2021
TL;DR: In this article, a new texture descriptor based on the well-known dense Scale-Invariant Feature Transform (SIFT) is proposed, in which their descriptors are summarized using a set of signal processing functions.
Abstract: Fingerprint-based authentication systems represent what is most common in biometric authentication systems. Today’s simplest tasks, such as unlocking functions on a personal cell phone, may require its owner’s fingerprint. However, along with the advancement of this category of systems, have emerged fraud strategies that aim to guarantee undue access to illegitimate individuals. In this case, one of the most common frauds is that in which the impostor presents manufactured biometry, or spoofing, to the system, simulating the biometry of another user. In this work, we propose a new framework that makes two filtered versions of the fingerprint image in order to increase the amount of information that can be useful in the process of detecting fraud in fingerprint images. Besides, we propose a new texture descriptor based on the well-known dense Scale-Invariant Feature Transform (SIFT): the statistical dense SIFT, in which their descriptors are summarized using a set of signal processing functions. The proposed methodology is evaluated in benchmarks of two editions of LivDet competitions, assuming competitive results in comparison to techniques that configure the state of the art of the problem.

3 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: A dictionary-based approach is proposed for automatic latent segmentation and enhancement towards the goal of achieving “lights-out” latent identification systems and experimental results show that the proposed algorithm outperforms the state-of-the-art segmentations and enhancement algorithms and boosts the performance of a state- of- the-art commercial latent matcher.
Abstract: Latent fingerprint matching has played a critical role in identifying suspects and criminals. However, compared to rolled and plain fingerprint matching, latent identification accuracy is significantly lower due to complex background noise, poor ridge quality and overlapping structured noise in latent images. Accordingly, manual markup of various features (e.g., region of interest, singular points and minutiae) is typically necessary to extract reliable features from latents. To reduce this markup cost and to improve the consistency in feature markup, fully automatic and highly accurate ("lights-out" capability) latent matching algorithms are needed. In this paper, a dictionary-based approach is proposed for automatic latent segmentation and enhancement towards the goal of achieving "lights-out" latent identification systems. Given a latent fingerprint image, a total variation (TV) decomposition model with L1 fidelity regularization is used to remove piecewise-smooth background noise. The texture component image obtained from the decomposition of latent image is divided into overlapping patches. Ridge structure dictionary, which is learnt from a set of high quality ridge patches, is then used to restore ridge structure in these latent patches. The ridge quality of a patch, which is used for latent segmentation, is defined as the structural similarity between the patch and its reconstruction. Orientation and frequency fields, which are used for latent enhancement, are then extracted from the reconstructed patch. To balance robustness and accuracy, a coarse to fine strategy is proposed. Experimental results on two latent fingerprint databases (i.e., NIST SD27 and WVU DB) show that the proposed algorithm outperforms the state-of-the-art segmentation and enhancement algorithms and boosts the performance of a state-of-the-art commercial latent matcher.

140 citations

Journal ArticleDOI
TL;DR: Li et al. as discussed by the authors proposed an automated latent fingerprint recognition algorithm that utilizes Convolutional Neural Networks (ConvNets) for ridge flow estimation and minutiae descriptor extraction, and extract complementary templates (two minutia templates and one texture template) to represent the latent.
Abstract: Latent fingerprints are one of the most important and widely used evidence in law enforcement and forensic agencies worldwide. Yet, NIST evaluations show that the performance of state-of-the-art latent recognition systems is far from satisfactory. An automated latent fingerprint recognition system with high accuracy is essential to compare latents found at crime scenes to a large collection of reference prints to generate a candidate list of possible mates. In this paper, we propose an automated latent fingerprint recognition algorithm that utilizes Convolutional Neural Networks (ConvNets) for ridge flow estimation and minutiae descriptor extraction, and extract complementary templates (two minutiae templates and one texture template) to represent the latent. The comparison scores between the latent and a reference print based on the three templates are fused to retrieve a short candidate list from the reference database. Experimental results show that the rank-1 identification accuracies (query latent is matched with its true mate in the reference database) are 64.7 percent for the NIST SD27 and 75.3 percent for the WVU latent databases, against a reference database of 100K rolled prints. These results are the best among published papers on latent recognition and competitive with the performance (66.7 and 70.8 percent rank-1 accuracies on NIST SD27 and WVU DB, respectively) of a leading COTS latent Automated Fingerprint Identification System (AFIS). By score-level (rank-level) fusion of our system with the commercial off-the-shelf (COTS) latent AFIS, the overall rank-1 identification performance can be improved from 64.7 and 75.3 to 73.3 percent (74.4 percent) and 76.6 percent (78.4 percent) on NIST SD27 and WVU latent databases, respectively.

139 citations

Proceedings ArticleDOI
TL;DR: FingerNet as mentioned in this paper combines domain knowledge and the representation ability of deep learning for fingerprint extraction, and achieves state-of-the-art performance on the NIST SD27 latent database and FVC 2004 slap database.
Abstract: Minutiae extraction is of critical importance in automated fingerprint recognition. Previous works on rolled/slap fingerprints failed on latent fingerprints due to noisy ridge patterns and complex background noises. In this paper, we propose a new way to design deep convolutional network combining domain knowledge and the representation ability of deep learning. In terms of orientation estimation, segmentation, enhancement and minutiae extraction, several typical traditional methods performed well on rolled/slap fingerprints are transformed into convolutional manners and integrated as an unified plain network. We demonstrate that this pipeline is equivalent to a shallow network with fixed weights. The network is then expanded to enhance its representation ability and the weights are released to learn complex background variance from data, while preserving end-to-end differentiability. Experimental results on NIST SD27 latent database and FVC 2004 slap database demonstrate that the proposed algorithm outperforms the state-of-the-art minutiae extraction algorithms. Code is made publicly available at: https://github.com/felixTY/FingerNet.

93 citations

Journal ArticleDOI
TL;DR: A new image decomposition scheme, called the adaptive directional total variation (ADTV), is proposed to achieve effective segmentation and enhancement for latent fingerprint images in this work, leading to improved feature detection and latent matching performance.
Abstract: A new image decomposition scheme, called the adaptive directional total variation (ADTV) model, is proposed to achieve effective segmentation and enhancement for latent fingerprint images in this work. The proposed model is inspired by the classical total variation models, but it differentiates itself by integrating two unique features of fingerprints; namely, scale and orientation. The proposed ADTV model decomposes a latent fingerprint image into two layers: cartoon and texture. The cartoon layer contains unwanted components (e.g., structured noise) while the texture layer mainly consists of the latent fingerprint. This cartoon-texture decomposition facilitates the process of segmentation, as the region of interest can be easily detected from the texture layer using traditional segmentation methods. The effectiveness of the proposed scheme is validated through experimental results on the entire NIST SD27 latent fingerprint database. The proposed scheme achieves accurate segmentation and enhancement results, leading to improved feature detection and latent matching performance.

77 citations

Journal ArticleDOI
TL;DR: The process of automatic latent fingerprint matching is divided into five definite stages, and the existing algorithms, limitations, and future research directions in each of the stages are discussed.
Abstract: Latent fingerprint has been used as evidence in the court of law for over 100 years. However, even today, a completely automated latent fingerprint system has not been achieved. Researchers have identified several important challenges in latent fingerprint recognition: 1) low information content; 2) presence of background noise and nonlinear ridge distortion; 3) need for an established scientific procedure for matching latent fingerprints; and 4) lack of publicly available latent fingerprint databases. The process of automatic latent fingerprint matching is divided into five definite stages, and this paper discusses the existing algorithms, limitations, and future research directions in each of the stages.

72 citations