Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Abstract-In the current panorama the conclusive identification of a laryngeal pathology relies inevitably on the observation of the vocal folds by means of laryngoscopical techniques. This inspection technique is inconvenient for a number... more
Abstract-In the current panorama the conclusive identification of a laryngeal pathology relies inevitably on the observation of the vocal folds by means of laryngoscopical techniques. This inspection technique is inconvenient for a number of reasons, such as its high cost, the duration of the inspection, and, above all, the fact that it is an invasive technique.
Zernike moments in elimination of the slant deviation on isolated handwritten digits. The method consists of exploiting the elliptic characteristics of the minor order Zernike moments to calculate the image deviation. To realize the... more
Zernike moments in elimination of the slant deviation on isolated handwritten digits. The method consists of exploiting the elliptic characteristics of the minor order Zernike moments to calculate the image deviation. To realize the experiments we have used the NIST SD-19 database, improving the success rate without the slant deviation method.
Research Interests:
Research Interests:
Speech articulation may be an important resource to study neuromotor activity in relation with neurological diseases, such as Parkinson’s, Alzheimer’s or Amyotrophic Lateral Sclerosis. Through the present work a biomechanical model for... more
Speech articulation may be an important resource to study neuromotor activity in relation with neurological diseases, such as Parkinson’s, Alzheimer’s or Amyotrophic Lateral Sclerosis. Through the present work a biomechanical model for the joint structure of the jaw and tongue is introduced. This model allows putting into relation formant trajectories with jaw-tongue kinematics in terms of dorso-ventral and rostro-caudal movements of the structure. The reconstruction of the absolute velocity of the system from inverse filtering estimates of the first two formants allows the introduction of the velocity distribution histograms as descriptors of articulation behavior. A study case using recordings separated in time from a patient suffering from Amyotrophic Lateral Sclerosis, compared to distributions from a normative control is presented. It may be seen that patient’s distributions show larger contents for low ranges of velocity and smaller contents for high velocity ranges compared to the control distribution. Global comparisons of velocity distribution profiles between the control and patient’s records using Information Theory measurements may be used to monitor illness conditions and progress.
Research Interests:
Research Interests: Humanities and Art
Research Interests:
Research Interests:
Research Interests:
Successful acquisition of handwriting skills as a child can have important consequences for later education. Possible graphomotor or handwriting disabilities (GD and HD, respectively) could reduce quality of life but effective remediation... more
Successful acquisition of handwriting skills as a child can have important consequences for later education. Possible graphomotor or handwriting disabilities (GD and HD, respectively) could reduce quality of life but effective remediation depends on proper diagnosis. However, current approaches to diagnosis and assessment of GD and HD have several limitations and knowledge gaps, e.g. they are subjective, they do not facilitate identification of specific manifestations, etc. The aim of this work is to address the limitations of current approaches and introduce a new scale (GHDRS - Graphomotor and Handwriting Disabilities Rating Scale) that will enable experts to perform objective and complex computer-aided diagnosis and assessment of GD and HD. The scale supports quantification of 17 manifestations associated with the process/product of drawing/handwriting. In addition, we provide normative data for Czech children attending up to the fourth grade of a primary school. Finally, the who...
Research Interests:
Research Interests:
Currently, there are more and more frequent studies focused on the evaluation of Alzheimer’s disease (AD) from the automatic analysis of the speech of patients, in order to detect the presence of the disease in an individual or for the... more
Currently, there are more and more frequent studies focused on the evaluation of Alzheimer’s disease (AD) from the automatic analysis of the speech of patients, in order to detect the presence of the disease in an individual or for the evolutionary control of the disease. However, studies focused on analyzing the effect of the methodology used to generate the spontaneous speech of the speaker who undergoes this type of analysis are rare. The objective of this work is to study two different strategies to facilitate the generation of the spontaneous speech of a speaker for further analysis: the use of a human interviewer that promotes the generation of speech through an interview and the use of an automatic system (an automatic interviewer) that invites the speaker to describe certain visual stimuli. In this study, a database called Cross-Sectional Alzheimer Prognosis R2019 has been created, consisting of speech samples from speakers recorded using both methodologies. The speech recor...
Research Interests:
Research Interests:
el Aula Moises Diaz∗, Ester González-Sosa†, Aythami Morales†, Patricia Henrı́quez∗ and Miguel Angel Ferrer∗ ∗Instituto Universitario para el Desarrollo Tecnológico y la Innovación en Comunicaciones (IDeTIC) Universidad de Las Palmas de... more
el Aula Moises Diaz∗, Ester González-Sosa†, Aythami Morales†, Patricia Henrı́quez∗ and Miguel Angel Ferrer∗ ∗Instituto Universitario para el Desarrollo Tecnológico y la Innovación en Comunicaciones (IDeTIC) Universidad de Las Palmas de Gran Canaria, España Email: {mdiaz, phenriquez, mferrer}@idetic.eu †Biometric Recognition Group ATVS EPS, Universidad Autónoma de Madrid, España Email: {ester.gonzalezs, aythami.morales}@uam.es
Research Interests: Humanities and Art
Research Interests:
Speech articulation may be an important resource to study neuromotor activity in relation with neurological diseases, such as Parkinson’s, Alzheimer’s or Amyotrophic Lateral Sclerosis. Through the present work a biomechanical model for... more
Speech articulation may be an important resource to study neuromotor activity in relation with neurological diseases, such as Parkinson’s, Alzheimer’s or Amyotrophic Lateral Sclerosis. Through the present work a biomechanical model for the joint structure of the jaw and tongue is introduced. This model allows putting into relation formant trajectories with jaw-tongue kinematics in terms of dorso-ventral and rostro-caudal movements of the structure. The reconstruction of the absolute velocity of the system from inverse filtering estimates of the first two formants allows the introduction of the velocity distribution histograms as descriptors of articulation behavior. A study case using recordings separated in time from a patient suffering from Amyotrophic Lateral Sclerosis, compared to distributions from a normative control is presented. It may be seen that patient’s distributions show larger contents for low ranges of velocity and smaller contents for high velocity ranges compared t...
Research Interests:
Resumen—Motivados con la norma del Espacio Europeo de Educación Superior (EEES) de evaluar la asistencia a clase, los profesores recogen las firmas manuscritas de sus alumnos matriculados como evidencia de su asistencia. Esta evidencia es... more
Resumen—Motivados con la norma del Espacio Europeo de Educación Superior (EEES) de evaluar la asistencia a clase, los profesores recogen las firmas manuscritas de sus alumnos matriculados como evidencia de su asistencia. Esta evidencia es susceptible de ser impostada mediante la falsificación de las firmas de aquellos alumnos que no asisten a clase. Aprovechando la aceptación de este medio que verifica la asistencia a clase, en este artı́culo se propone un sistema basado en las nuevas tecnologı́as para automáticamente verificar las firmas manuscritas de los alumnos. Ası́ mismo, en este artı́culo se proponen y se comparan dos alternativas de sistemas de verificación automática de firmas capaces de detectar a los impostores. Palabras clave: Verificación automática de firmas manuscritas, sistemas avanzados, ayudas al profesor.
Research Interests:
Parkinson’s disease is manifested as well in handwriting as in voice. Previous researches have carried out different procedures to estimate the dysfunctions of the illness in voice and handwriting separately. This paper proposes one... more
Parkinson’s disease is manifested as well in handwriting as in voice. Previous researches have carried out different procedures to estimate the dysfunctions of the illness in voice and handwriting separately. This paper proposes one parameter to evaluate the influence of the illness on both voice and handwriting as the symptoms affecting both has a common origin. Specifically, the parameter proposed is based on the Kinematic Theory of rapid human movements. It allows to quantify the deficits caused by Parkinson’s disease in both handwriting and voice. The velocity profile obtained to characterize voice between the first and second formant is computed by a spatio-temporal approximation. In handwriting, the velocity profile is obtained from the sampled positions of the pen on a digital tablet. Once the velocity profile is derived, it is transformed to fit into the lognormal model in which similarities between voice and handwriting has been found for performance of these tasks by Parki...
Research Interests:
Research Interests:
Research Interests:
La docencia de las asignaturas de robótica, presta una gran atención a los sistemas de referencia. Los alumnos deben saber cómo representar la posición y orientación de un sistema respecto a otro. Para que los alumnos capten el concepto... more
La docencia de las asignaturas de robótica, presta una gran atención a los sistemas de referencia. Los alumnos deben saber cómo representar la posición y orientación de un sistema respecto a otro. Para que los alumnos capten el concepto de los distintos sistemas de referencia y de su representación se pueden utilizar software de simulación como Matlab. Pero la experiencia demuestra que el uso de un robot plantea varias ventajas respecto al método de programas de simulación. Por una parte, el hacer que el robot haga algo que ha sido programado por los alumnos, hace que estos tengan una gran satisfacción personal, al tiempo que hace que los conceptos se adquieran más fácilmente.
En este trabajo se presenta el proyecto de Innovación Educativa Acción Tutorial on-line, concedido al Grupo de Innovación Educativa en Sistemas de Telecomunicación de la Universidad de Las Palmas de Gran Canaria, que tiene como objetivos... more
En este trabajo se presenta el proyecto de Innovación Educativa Acción Tutorial on-line, concedido al Grupo de Innovación Educativa en Sistemas de Telecomunicación de la Universidad de Las Palmas de Gran Canaria, que tiene como objetivos el proporcionar un estudio sobre herramientas virtuales para tutorías online en ingeniería y usar la herramienta en las diferentes asignaturas de los profesores participantes. Se expone la motivación del proyecto, la metodología empleada, la planificación de las experiencias y los resultados preliminares.
Research Interests:
Research Interests:
e-VOICE, sistema de evaluacion remota del sistema fonador, es un proyecto financiado por la catedra Telefonica de la Universidad de Las Palmas de Gran Canaria cuyo objetivo ha sido desarrollar una herramienta software para la evaluacion,... more
e-VOICE, sistema de evaluacion remota del sistema fonador, es un proyecto financiado por la catedra Telefonica de la Universidad de Las Palmas de Gran Canaria cuyo objetivo ha sido desarrollar una herramienta software para la evaluacion, via web, de la calidad de la voz de pacientes, con patologias laringea y del sistema fonador, a partir de una grabacion de voz. La voz es el principal medio de comunicacion entre las personas, forma parte de nuestra imagen corporal y en muchos casos es una herramienta importante de trabajo. Entre el 5 y el 7% de la poblacion de los paises industrializados sufre algun trastorno de las cuerdas vocales que requiere la atencion del especialista, aumentado este porcentaje hasta el 22,5% en colectivos como profesores, cantantes, locutores y comerciales que emplean la voz como su instrumento de trabajo. Para la evaluacion clinica de un paciente afectado por una patologia laringea, las tecnicas basadas en la inspeccion visual directa de las cuerdas vocales ...
Research Interests: Humanities and Art
Research Interests:
Research Interests: Philosophy and Humanities
ABSTRACT Automatic latent fingerprint identification is a useful tool for criminal investigation. However, the accuracy of identification reported in the state-of-the-art literature is low due to the distortion in latent fingerprint... more
ABSTRACT Automatic latent fingerprint identification is a useful tool for criminal investigation. However, the accuracy of identification reported in the state-of-the-art literature is low due to the distortion in latent fingerprint images. In this paper, we describe a new algorithm based on the use of clustering which is independent of the minutiae descriptors. The proposed technique improves the robustness of identification in the presence of large non-linear deformation which is associated with latent fingerprint images. The new algorithm finds multiple overlapping clusters of matching minutiae pairs which are merged together to find matching minutiae. Several experiments performed using latent fingerprint databases show that our proposed algorithm achieves higher accuracy than those presented in state-of-the-art literature. Moreover, the results show that the proposed algorithm is successful in dealing with the large distortion associated with latent fingerprints formed under the worst conditions.
Research Interests:
This paper proposes a new sclera vessel recognition technique. The vesselpatterns of sclera are unique for each individual and this can be utilized to identify a person uniquely. In this research we have used a time adaptive active... more
This paper proposes a new sclera vessel recognition technique. The vesselpatterns of sclera are unique for each individual and this can be utilized to identify a person uniquely. In this research we have used a time adaptive active contour-based region growing technique for sclera segmentation. Prior to that, we have made some tonal and illumination correction to get a clearer sclera area without the distributing vessel structure. This is because the presence of complex vessel structures occasionally affects the region-growing process. The sclera vessels are not prominent in the images, so in order to make them clearly visible, a local image enhancement process using a Haar high pass filter is incorporated. To get the total orientation of the vessels, we have used Orientated Local Binary Pattern (OLBP). The OLBP images of each class are used for template matching for classification by calculating the minimum Hamming Distance. We have used the UBIRIS version 1 dataset for the experimentation of our research. The proposed approach has achieved high recognition accuracy employing the above-mentioned dataset.
Research Interests:
Hyperspectral analysis is employed in many different areas, such as medicine, environmental studies, security and forensics. Focusing on law enforcement, ink discrimination has become an important factor for the detection of fraudulent... more
Hyperspectral analysis is employed in many different areas, such as medicine, environmental studies, security and forensics. Focusing on law enforcement, ink discrimination has become an important factor for the detection of fraudulent documents. This paper proposes an approach for ink analysis in handwritten documents and pen verification using hyperspectral analysis and Least Square SVM classification. The proposed method obtains immediate results in a non-contact way from the document or test sample. The first step is to determine the best possible lighting conditions. Then a detailed study is made of components and properties of the ink and pens used. This paper proposes a classification method based on the hyperspectral characteristics of the ink derived from its physical properties. Furthermore, a database of hyperspectral curves of several types of inks is made, which is used to obtain the characteristics of different inks. The proposed method for automated ink type identification is tested using 25 different pens and more than 1000 samples. The achieved discrimination between types of ink was 87.5%. The experimental protocol includes three different scenarios.