Showing papers by "Miguel Ferrer published in 2017"

A Behavioral Handwriting Model for Static and Dynamic Signature Synthesis

Abstract: The synthetic generation of static handwritten signatures based on motor equivalence theory has been recently proposed for biometric applications. Motor equivalence divides the human handwriting action into an effector dependent cognitive level and an effector independent motor level. The first level has been suggested by others as an engram, generated through a spatial grid, and the second has been emulated with kinematic filters. Our paper proposes a development of this methodology in which we generate dynamic information and provide a unified comprehensive synthesizer for both static and dynamic signature synthesis. The dynamics are calculated by lognormal sampling of the 8-connected continuous signature trajectory, which includes, as a novelty, the pen-ups. The forgery generation imitates a signature by extracting the most perceptually relevant points of the given genuine signature and interpolating them. The capacity to synthesize both static and dynamic signatures using a unique model is evaluated according to its ability to adapt to the static and dynamic signature inter- and intra-personal variability. Our highly promising results suggest the possibility of using the synthesizer in different areas beyond the generation of unlimited databases for biometric training.

Generation of Duplicated Off-Line Signature Images for Verification Systems

Abstract: Biometric researchers have historically seen signature duplication as a procedure relevant to improving the performance of automatic signature verifiers. Different approaches have been proposed to duplicate dynamic signatures based on the heuristic affine transformation, nonlinear distortion and the kinematic model of the motor system. The literature on static signature duplication is limited and as far as we know based on heuristic affine transforms and does not seem to consider the recent advances in human behavior modeling of neuroscience. This paper tries to fill this gap by proposing a cognitive inspired algorithm to duplicate off-line signatures. The algorithm is based on a set of nonlinear and linear transformations which simulate the human spatial cognitive map and motor system intra-personal variability during the signing process. The duplicator is evaluated by increasing artificially a training sequence and verifying that the performance of four state-of-the-art off-line signature classifiers using two publicly databases have been improved on average as if we had collected three more real signatures.

SSERBC 2017: Sclera segmentation and eye recognition benchmarking competition

Abstract: This paper summarises the results of the Sclera Segmentation and Eye Recognition Benchmarking Competition (SSERBC 2017) It was organised in the context of the International Joint Conference on Biometrics (IJCB 2017) The aim of this competition was to record the recent developments in sclera segmentation and eye recognition in the visible spectrum (using iris, sclera and peri-ocular, and their fusion), and also to gain the attention of researchers on this subject In this regard, we have used the Multi-Angle Sclera Dataset (MASD version 1) It is comprised of2624 images taken from both the eyes of 82 identities Therefore, it consists of images of 164 (82×2) eyes A manual segmentation mask of these images was created to baseline both tasks Precision and recall based statistical measures were employed to evaluate the effectiveness of the segmentation and the ranks of the segmentation task Recognition accuracy measure has been employed to measure the recognition task Manually segmented sclera, iris and peri-ocular regions were used in the recognition task Sixteen teams registered for the competition, and among them, six teams submitted their algorithms or systems for the segmentation task and two of them submitted their recognition algorithm or systems The results produced by these algorithms or systems reflect current developments in the literature of sclera segmentation and eye recognition, employing cutting edge techniques The MASD version 1 dataset with some of the ground truth will be freely available for research purposes The success of the competition also demonstrates the recent interests of researchers from academia as well as industry on this subject

Stability-based system for bearing fault early detection

Abstract: Novel Stability-based system for early bearing fault detection.Novel use of Dynamic Time Warping and Direct Matching Point techniques.Findings on continuous monitoring of vibration signals with low false alarms for faultsFindings on two publicly available databases under several machining conditions. This paper presents a new and straightforward system for bearing fault detection. The system computes the stability of two vibration signals by using the direct matching points (DMP) of an elastic and non-linear align function. It is able to find discriminant properties in the stability of fault-free and faulty bearing vibration signals from the early and late stages of the fault in critical bearing parts. Because training data constitutes one of the critical challenges in most expert and intelligent systems, one of the novelties of the proposed stability-based system is that it requires neither training nor fine-tuning. A significant impact on the robustness of the system is demonstrated using two publicly available vibration signal databases under several load conditions, with real faults, during multiple machine working states. Experimental results validate the use of the proposed stability-based system for predictive maintenance in bearings.

Long-term changes in autumn migration dates at the Strait of Gibraltar reflect population trends of soaring birds

Abstract: A growing body of work shows that climate change is the cause of a number of directional shifts in the spring phenology of migratory birds. However, changes in autumn phenology are less well studied and their consistency across species, as well as their association with population trends, remains uncertain. We investigate changes in the autumn migration dates of 11 species of soaring birds over the Strait of Gibraltar over a 16-year period. Using models corrected for phylogeny, we assessed whether ecological and morphological characteristics, as well as population trends, account for interspecific shifts in migration times. We recorded different phenological changes in different periods of the migration season and suggest that these differences are due to age-dependent responses. The variable best predicting advances in migration dates was population trend: species that did not advance their autumn migration dates were those showing a decline in their European breeding populations. We repeated our tests on a dataset representing the migration date of soaring birds across Pyrenees and found that population trends at this site also predicted phenological shifts. Our results suggest that flexibility in migratory strategy and population trends may be related, such that different adaptive capacity in migration timing may be more relevant than other ecological traits in determining the conservation status of migratory birds in Europe and perhaps in other regions. This article is protected by copyright. All rights reserved.

Natural expansion versus translocation in a previously human-persecuted bird of prey

Abstract: Many threatened species in Europe have been expanding their distributions during recent decades owing to protection measures that overcome historical human activity that has limited their distributions. Range expansion has come about via two processes, natural expansion from existing range and reintroductions to new ranges. Reintroductions may prove to be a better way to establish populations because individuals are less subject to competitive relationships lowering breeding success than individuals expanding from existing populations. Whether this is true, however, remains uncertain. We compared success of breeding pairs of an expanding and a reintroduced population of spanish imperial eagles monitored for over 15 years in the south of Spain. We found significant differences in productivity between breeding pairs of each population. Newly established territories in reintroduction areas were almost three times more productive than new territories established as individuals expanded out from an existing population. We conclude that among these eagle populations reintroduced to new areas may fare as well or better than individuals expanding out form existing populations.

How to plan reintroductions of long-lived birds.

Abstract: Reintroductions have been increasingly used for species restoration and it seems that this conservation tool is going to be more used in the future. Nevertheless, there is not a clear consensus about the better procedure for that, consequently a better knowledge of how to optimize this kind of management is needed. Here we examined the dynamics of released long-lived bird populations (lesser kestrel, Falco naumanni, Bonelli's eagle Aquila fasciata, and bearded vulture Gypaetus barbatus) in object-oriented simulated reintroduction programs. To do that, number of young per year and number of years of released necessary to achieve a successful reintroduced population were calculated. We define a successful reintroduction as one in which when the probability of extinction during two times the maximum live-span period for the species (20, 50, and 64 years respectively) was less than 0.001 (P 0.00). Results showed that a similar total number of young (mean 98.33±5.26) must be released in all the species in all the scenarios in order to get a successful reintroduction. Consequently, as more young per year are released the new population is going to be larger at the end of the simulations, the lesser the negative effects in the donor population and the lowest the total budget needed will be.

Recovering Western On-Line Signatures from Image-Based Specimens

Abstract: This article propose a complete framework to recover the dynamic properties (i.e. velocity and pressure) of an on-line Western signature from an image-based signature. The framework is based on classical approaches to recover the writing order of the strokes and a novel process to recover the kinematic properties from thinned trajectories. In order to evaluate the quality of the recovered signatures and the impact of each stage of our framework, the performance of a signature verification system on obtained signatures in each stage are compared to the performance with real signatures. As a proof of concepts, in this study we use the first 50 users of BiosecurID signature database since they contain both the on-line and off-line version of Western signatures.

Factors affecting plasma chemistry values of the black-browed albatross Thalassarche melanophrys

Abstract: Blood chemical reference values and variations in them in long-lived endangered birds are of metabolic, veterinary, ecological and/or taxonomic interest. In the present study, we for the first time provide such reference values and test the influence of sex, age, and nest location on up to 11 plasma values in nesting black-browed albatrosses (Thalassarche melanophrys) that we sampled in 2015 on the Falkland Islands. Our results showed that differences between sexes were not significant for any of the parameters for which we tested. We found insignificant differences in metabolically related parameters in nestlings being raised in the middle of nesting colonies and those being raised at the edges of the colonies indicating that nest location did not affect the nutritional status or health of young, developing albatrosses. Conversely, age had a significant effect on a number of metabolites, inorganic ions and enzymatic activity. In particular, age-related differences in glucose, triglyceride, urea, and uric acid suggested that the relative metabolic rate was higher in nestling than in adult albatrosses.

Better nutritional condition changes the distribution of juvenile dispersal distances: an experiment with Spanish imperial eagles

Abstract: We investigated the distribution of juvenile dispersal distances of a territorial long-lived species with deferred maturity, the Spanish imperial eagle Aquila adalberti. Here we used a reintroduction program as an experimental approach to test predictions of different hypotheses about the distribution of juvenile dispersal distances: competition and wandering behavior. We determined maximal juvenile dispersal distances of 59 young eagles; 1) 30 wild non-manipulated individuals, and 2) 29 tranlocated young under an ad libitum feeding program, released with adults breeding in the area. The competitive displacement hypothesis predicts a leptokurtic distribution of distances in wild non-manipulated young as well as in released young. Under the ‘wandering’ hypothesis, however, a leptokurtic distribution is expected in wild young but a normal distribution would be expected in young released (with adults in the release area), owing to a general improvement in the nutritional status of released young that have been fed ad libitum, as is usual in reintroduction programs. Additionally, a negative relationship between hatching date and dispersal distances is expected in wild young but no relationship in released young under ad libitum feeding. Mean maximum dispersal distances for all the juvenile eagles was 142.8 km. No differences between sexes were found, nor between populations or between wild and reintroduced young. Wild young distances were not normally distributed, being closer to a Poisson distribution. In contrast, released young with adults (under ad libitum feeding) showed a normal distribution. Wild birds showed a significant negative relationship between dispersal distance and hatching date, with young that hatched late in the season dispersing shorter distances. However, released young under ad libitum feeding showed no significant relationship between hatching date and dispersal distance. These results support the ‘wandering’ hypothesis as the main driver of the distribution of dispersal distances.

Physiological Conditions of Parent and Offspring Black-Browed Albatrosses Thalassarche melanophris

Abstract: Capsule: In Black-browed Albatrosses Thalassarche melanophris nutritional condition is correlated between parents and their offspring.Aims: To test resource allocation hypotheses analysing the relationship between parental and offspring nutritional condition.Methods: We measured blood chemistry parameters related with nutritional condition in 24 parents and their nestlings in a colony of Black-browed Albatrosses.Results: There were no significant differences in blood parameters between sexes or location of the nest within the colony, neither among adults nor among nestlings. We found a significant positive correlation between parents and the nutritional condition of their offspring, measured as urea, uric acid and beta-hydroxybutyrate concentrations in blood.Discussion: These relationships demonstrate that condition of the young seems to be merely a reflection of parental condition. An interesting relationship between alkaline phosphatase concentration in adults and nutritional condition of their ...

Sclera vessel pattern synthesis based on a non-parametric texture synthesis technique

Abstract: This work proposes a sclera vessel texture pattern synthesis technique. Sclera texture was synthesized by a non-parametric based texture regeneration technique. A small number of classes from the UBIRIS version: 1 dataset was employed as primitive images. An appreciable result was achieved which solicits the successful synthesis of sclera texture patterns. It is difficult to get a huge collection real sclera data and hence such synthetic data will be useful to the researchers.

Two-steps perceptual important points estimator in 8-connected curves from handwritten signature

Abstract: Estimating the salient points in 8-connected curves from handwritten signature is a difficult task due to their relation to the writer neuromotor system. This paper faces up this topic proposing a two-steps perceptual important points estimation method: the first step estimates the sharper salient points by a curvature analysis at multiple scales, whereas the second step estimates the smoother salient points relying on circular shapes between estimated salient points in step one. In this approach, both sharper and smoother salient points represent the set of perceptual important points in an eight connected signature trajectory. Our validations, conducted on 2112 signatures from 132 users of the BiosecurID database, are focused on i) evaluating the number of estimated perceptual important points; ii) evaluating their locations in the trajectory and iii) evaluating the accuracy of the estimated duration of the signatures from the number of perceptual important points. The obtained results are encouraging for new developments in handwriting analysis based on this procedure.

Using UAVs to Map Aquatic Bird Colonies

Abstract: In this chapter, we present the results of several flight campaigns carried out in 2015 and 2016 using multirotor Unmanned Airborne Vehicles (UAVs) over Slender-billed Gull (Chroicocephalus genei) colonies in the Donana Nature Space, south west Spain. The images were taken at different times during the breeding season. The requirements for the flight campaigns were to acquire sufficient visible and nadir pictures at 5 cm pixel resolution and to cover the entire nesting colony with maximum overlap. Although we carried out the flights under clear skies, low wind speed was not always possible, causing a few blurred pictures. After georeferencing and mosaicking the set of raw pictures, we adopted photo-interpretation as the first technique to identify and delineate birds, either lying, standing or flying. A nest position was assigned when the clear pattern of a lying birds was recognised. We then selected a set of breeding individuals (nests) to train a supervised classification in semi-automatic nest delineation. We applied two different algorithms and tested their accuracy in identifying gulls with an independent set of manually delineated individuals. We chose the best method according to the accuracy results and applied it to the whole colony. We found major issues for nest identification and delineation for nests under tree and shrub canopies. The different campaigns and flight characteristics were useful to improve bird identification accuracy. As a result, we provided estimates of the number of breeding pairs per year to managers and cross-checked these with estimates from the ground monitoring and colony sampling. As an added value, the spatial coordinates of nests can be used for spatial analysis and investigate nest aggregation, density and distribution in order to reveal spatial relationships with environmental factors such as distance to colony edges, distance to colony centroid, distance to predators, etc.

A decision-level fusion strategy for multimodal ocular biometric in visible spectrum based on posterior probability

Abstract: In this work, we propose a posterior probability-based decision-level fusion strategy for multimodal ocular biometric in the visible spectrum employing iris, sclera and peri-ocular trait To best of our knowledge this is the first attempt to design a multimodal ocular biometrics using all three ocular traits Employing all these traits in combination can help to increase the reliability and universality of the system For instance in some scenarios, the sclera and iris can be highly occluded or for completely closed eyes scenario, the peri-ocular trait can be relied on for the decision The proposed system is constituted of three independent traits and their combinations The classification output of the trait which produces highest posterior probability is to consider as the final decision An appreciable reliability and universal applicability of ocular trait are achieved in experiments conducted employing the proposed scheme

The new communication network for an internet of everything based security/safety/general management/visitor's services for the Papal Basilica and Sacred Convent of Saint Francis in Assisi, Italy

Abstract: The Papal Basilica and the Sacred Convent of St. Francis in Assisi, Italy together represent a unique and specific cultural heritage site where the mortal remains of St. Francis have been housed since 1230 AD. Millions of pilgrims and visitors from all over the world visit this site each year. In 2000 AD, together with other Franciscan sites in the surrounding area, it achieved UNESCO World Heritage status. Unique and complex cultural heritage sites, such as this, require a significant effort to ensure visitor security and safety. Along with such needs are cultural heritage preservation and protection as well as accessibility for visitors, with particular reference to visitors with disabilities, and for personnel normally present for site management, including the Friar's community. These aims can be achieved using integrated systems and innovative technologies, such as Internet of Everything (IoE) which can connect people, things (mobile terminals, smart sensors, devices, actuators; wearable devices; etc.), data/information/knowledge and particular processes. The purpose of this paper is to illustrate the methodology and show the results obtained from the study and the design of a new communication network for Internet of Everything based security/safety/general management and visitors' services of the Papal Basilica and Sacred Convent of Saint Francis in Assisi.

An Automatic Student Verification System Utilising Off-Line Thai Name Components

Abstract: This research proposed an automatic student identification and verification system utilising off-line Thai name components. The Thai name components consist of first and last names. Dense texture-based feature descriptors were able to yield encouraging results when applied to different handwritten text recognition scenarios. As a result, the authors employed such features in investigating their performance on Thai name component verification system. In this research, Dense-Local Binary Pattern, Dense-Local Directional Pattern, and Local Binary Pattern combined with Local Directional Pattern were employed. A base-line shape/feature i.e. Hidden Markov Model (HMM) was also utilised in this study. As there is no dataset on Thai name verification in the literature, a dataset is proposed for a Thai name verification system. The name component samples were collected from high school students. It consists of 8,400 name components (first and last names) from 100 students. Each student provided 60 genuine name components, and each of the name components was forged by 12 other students. An encouraging result was found employing the above-mentioned features on the proposed dataset.

Assessing the common authorship of a set of questioned signature images

Abstract: This paper assesses the common authorship of a set of questioned signature images. Our proposal consists in generating as many models as available questioned signatures. Each model is trained with one questioned signature and artificial duplicates worked out from it. The duplication procedure is based on neurocognitive distortions which are inspired from human writing processes. Once the similarity of each signature is evaluated with each model, a similarity score matrix is calculated. The cohesion of this matrix is used to assess whether all specimens were produced either by the same or by more than one writer.

Estudio de diferentes parámetros para la detección de esclerosis lateral amiotrófica a partir del movimiento articulatorio

Abstract: Amyotrophic lateral sclerosis (ALS) is a degenerative neuromuscular disease, one of its early symptoms being a progressive difficulty to speak (ALS dysarthria). To improve its diagnosis and monitoring, a new method based on articulatory movement estimation has been developed. As a result, two articulatory movement parameters are presented as well as their relationship with the illness grade.

Linking face images captured from the optical phenomenon in the wild for forensic science

Abstract: This paper discusses the possibility of use of some challenging face images scenario captured from optical phenomenon in the wild for forensic purpose towards individual identification Occluded and under cover face images in surveillance scenario can be collected from its reflection on a surrounding glass or on a smooth wall that is under the coverage of the surveillance camera and such scenario of face images can be linked for forensic purposes Another similar scenario that can also be used for forensic is the face images of an individual standing behind a transparent glass wall To investigate the capability of these images for personal identification this study is conducted This work investigated different types of features employed in the literature to establish individual identification by such degraded face images Among them, local region based featured worked best To achieve higher accuracy and better facial features face image were cropped manually along its close bounding box and noise removal was performed (reflection, etc) In order to experiment we have developed a database considering the above mentioned scenario, which will be publicly available for academic research Initial investigation substantiates the possibility of using such face images for forensic purpose