Biometrics systems have significantly improved person identification and authentication, playing an important role in personal, national, and global security. However, these systems might be deceived ...(or spoofed) and, despite the recent advances in spoofing detection, current solutions often rely on domain knowledge, specific biometric reading systems, and attack types. We assume a very limited knowledge about biometric spoofing at the sensor to derive outstanding spoofing detection systems for iris, face, and fingerprint modalities based on two deep learning approaches. The first approach consists of learning suitable convolutional network architectures for each domain, whereas the second approach focuses on learning the weights of the network via back propagation. We consider nine biometric spoofing benchmarks - each one containing real and fake samples of a given biometric modality and attack type - and learn deep representations for each benchmark by combining and contrasting the two learning approaches. This strategy not only provides better comprehension of how these approaches interplay, but also creates systems that exceed the best known results in eight out of the nine benchmarks. The results strongly indicate that spoofing detection systems based on convolutional networks can be robust to attacks already known and possibly adapted, with little effort, to image-based attacks that are yet to come.
•A review of hierarchical segmentation methods, both general and superpixel ones.•Formal categorization of dense and sparse hierarchical segmentation approaches.•Introduction of a new method within ...each aforementioned category.•State-of-the-art superpixel segmentation results combining our methods.
We investigate the intersection between hierarchical and superpixel image segmentation. Two strategies are considered: (i) the classical region merging, that creates a dense hierarchy with a higher number of levels, and (ii) the recursive execution of some superpixel algorithm, which generates a sparse hierarchy with fewer levels. We show that, while dense methods can capture more intermediate or higher-level object information, sparse methods are considerably faster and usually with higher boundary adherence at finer levels. We first formalize the two strategies and present a sparse method, which is faster than its superpixel algorithm and with similar boundary adherence. We then propose a new dense method to be used as post-processing from the intermediate level, as obtained by our sparse method, upwards. This combination results in a unique strategy and the most effective hierarchical segmentation method among the compared state-of-the-art approaches, with efficiency comparable to the fastest superpixel algorithms.
Dijkstra’s algorithm (DA) is one of the most useful and efficient graph-search algorithms, which can be modified to solve many different problems. It is usually presented as a tool for finding a ...mapping which, for every vertex
v
, returns a shortest-length path to
v
from a fixed single source vertex. However, it is well known that DA returns also a correct optimal mapping when multiple sources are considered and for path-value functions more general than the standard path-length. The use of DA in such general setting can reduce many image processing operations to the computation of an optimum-path forest with path-cost function defined in terms of local image attributes. In this paper, we describe the general properties of a path-value function defined on an arbitrary finite graph which, provably, ensure that Dijkstra’s algorithm indeed returns an optimal mapping. We also provide the examples showing that the properties presented in a 2004 TPAMI paper on the image foresting transform, which were supposed to imply proper behavior of DA, are actually insufficient. Finally, we describe the properties of the path-value function of a graph that are provably necessary for the algorithm to return an optimal mapping.
•A deeper theoretical background about the Optimum-Path Forest (OPF) classifier with k-neighborhood (OPFk) is presented.•A new, faster and less prone to error training step is also proposed.•A faster ...classification algorithm for the OPFk classifier is presented.•An extensive experimental evaluation is conducted.•New insights about future research concerning OPFk are also discussed.
Display omitted
Graph-based pattern recognition techniques have been in the spotlight for many years, since there is a constant need for faster and more effective approaches. Among them, the Optimum-Path Forest (OPF) framework has gained considerable attention in the last years, mainly due to the promising results obtained by OPF-based classifiers, which range from unsupervised, semi-supervised and supervised learning. In this paper, we consider a deeper theoretical explanation concerning the supervised OPF classifier with k-neighborhood (OPFk), as well as we proposed two different training and classification algorithms that allow OPFk to work faster. The experimental validation against standard OPF and Support Vector Machines also validates the robustness of OPFk in real and synthetic datasets.
A crucial quest in neuroimaging is the discovery of image features (biomarkers) associated with neurodegenerative disorders. Recent works show that such biomarkers can be obtained by image analysis ...techniques. However, these techniques cannot be directly compared since they use different databases and validation protocols. In this paper, we present an extensive study of image descriptors for the diagnosis of Alzheimer Disease (AD) and introduce a new one, named
Residual Center of Mass
(RCM). The RCM descriptor explores image moments and other techniques to enhance brain regions and select discriminative features for the diagnosis of AD. For validation, a Support Vector Machine (SVM) is trained with the selected features to classify images from normal subjects and patients with AD. We show that RCM with SVM achieves the best accuracies on a considerable number of exams by 10-fold cross-validation — 95.1
%
on 507 FDG-PET scans and 90.3
%
on 1374 MRI scans.
Purpose
Automated segmentation of brain structures (objects) in MR three‐dimensional (3D) images for quantitative analysis has been a challenge and probabilistic atlases (PAs) are among the most ...well‐succeeded approaches. However, the existing models do not adapt to possible object anomalies due to the presence of a disease or a surgical procedure. Post‐processing operation does not solve the problem, for example, tissue classification to detect and remove such anomalies inside the resulting segmentation mask, because segmentation errors on healthy tissues cannot be fixed. Such anomalies very often alter the shape and texture of the brain structures, making them different from the appearance of the model. In this paper, we present an effective and efficient adaptive probabilistic atlas, named AdaPro, to circumvent the problem and evaluate it on a challenging task — the segmentation of the left hemisphere, right hemisphere, and cerebellum, without pons and medulla, in 3D MR‐T1 brain images of Epilepsy patients. This task is challenging due to temporal lobe resections, artifacts, and the absence of contrast in some parts between the structures of interest.
Methods
In AdaPro, we first build one probabilistic atlas per object of interest from a training set with normal 3D images and the corresponding 3D object masks. Second, we incorporate a texture classifier based on convex optimization which dynamically indicates the regions of the target 3D image where the PAs (shape constraints) should be further adapted. This strategy is mathematically more elegant and avoids problems with post‐processing. Third, we add a new object‐based delineation algorithm based on combinatorial optimization and diffusion filtering. AdaPro can then be used to locate and delineate the objects in the coordinate space of the atlas or of the test image. We also compare AdaPro with three other state‐of‐the‐art methods: an statistical shape model based on synergistic object search and delineation, and two methods based on multi‐atlas label fusion (MALF).
Results
We evaluate the methods quantitatively on 3D MR‐T1 brain images of 2T and 3T from epilepsy patients, before and after temporal lobe resections, and on the template and native coordinate spaces. The results show that AdaPro is considerably faster and consistently more accurate than the baselines with statistical significance in both coordinate spaces.
Conclusion
AdaPro can be used as a fast and effective step for brain tissue segmentation and it can also be easily extended to segment subcortical brain structures. By choice of its components, probabilistic atlas, texture classifier, and delineation algorithm, it can also be extended to other organs and imaging modalities.
ABSTRACT The quality perception of fruits and vegetables is a key factor for marketing and consumption. Quality determination is carried out subjectively by the consumer and with objective methods, ...many of which are destructive. The use of optical techniques and real-time screening, including determination of quality attributes by non-destructive methods, represents operational advantages for grading and selection systems. This work aimed to search for correlation between the tomato ripeness indexes with Biospeckle Laser (BSL) data. The epidermis color (CIE L*a*b), firmness, pH, Total Titratable Acidity (TTA), Total Soluble Solids (TSS), (oBrix), and respiration were measured. These data were correlated with BSL numerically by the Moment of Inertia (MI) and the Average Value of Difference (AVD). A high correlation was found with respiration and pH by the MI method, and with TTA, flavor, and respiration by the AVD method.
Objective
Ova and parasite (O&P) examination is recommended for the laboratory diagnosis of agents causing parasitic infections; however, this exam requires scientific and technological improvements ...to enhance its diagnostic validity. Dissolved air flotation (DAF) is an efficient technical principle separating suspended solids in a liquid medium. We aimed to develop and validate a new procedure for intestinal parasite detection with DAF.
Methods
In this study, we collected samples from 500 volunteers, screened them by direct examination, and transferred the material to tubes using the Three Faecal Test (TF‐Test) for triplicate DAF tests. We evaluated physical–chemical parameters and DAF prototype components through quantifying parasites recovered from floated and non‐floated regions of the flotation column. The DAF operation protocol was validated with the gold standard results.
Results
The 10% saturated volume proportion and cationic surfactant showed regularity and high parasite recovery (80%). Modifications of the needle device did not influence parasite recovery (p > 0.05). Sensitivity, specificity, accuracy and kappa agreement obtained with the DAF protocol were 91%, 100%, 93% and substantial (k = 0.64), respectively.
Conclusion
The DAF principle could be used to process faecal samples in routine laboratory exams, enabling intestinal parasite detection.
Nowadays, fraud detection is important to avoid nontechnical energy losses. Various electric companies around the world have been faced with such losses, mainly from industrial and commercial ...consumers. This problem has traditionally been dealt with using artificial intelligence techniques, although their use can result in difficulties such as a high computational burden in the training phase and problems with parameter optimization. A recently-developed pattern recognition technique called optimum-path forest (OPF), however, has been shown to be superior to state-of-the-art artificial intelligence techniques. In this paper, we proposed to use OPF for nontechnical losses detection, as well as to apply its learning and pruning algorithms to this purpose. Comparisons against neural networks and other techniques demonstrated the robustness of the OPF with respect to commercial losses automatic identification.
•A new meta-heuristic optimization approach to speed up Optimum-Path Forest clustering.•Intrusion detection in computer networks by means of Optimum-Path Forest clustering.•Comparison of several ...meta-heuristics for Optimum-Path Forest optimization.
We propose a nature-inspired approach to estimate the probability density function (pdf) used for data clustering based on the optimum-path forest algorithm (OPFC). OPFC interprets a dataset as a graph, whose nodes are the samples and each sample is connected to its k-nearest neighbors in a given feature space (a k-nn graph). The nodes of the graph are weighted by their pdf values and the pdf is computed based on the distances between the samples and their k-nearest neighbors. Once the k-nn graph is defined, OPFC finds one sample (root) at each maximum of the pdf and propagates one optimum-path tree (cluster) from each root to the remaining samples of its dome. Clustering effectiveness will depend on the pdf estimation, and the proposed approach efficiently computes the best value of k for a given application. We validate our approach in the context of intrusion detection in computer networks. First, we compare OPFC with data clustering based on k-means, and self-organization maps. Second, we evaluate several metaheuristic techniques to find the best value of k.