Examinando por Autor "Rodriguez-Guillen, Reinier"

Mostrando 1 - 4 de 4
  • No hay miniatura disponible
    Ítem
    Detección de Regiones de Interés en imágenes de la prueba de Papanicolaou
    (2017-01-05) Rodriguez-Guillen, Reinier; Garcia Garcia, Yainet; Orozco Monteagudo, Maykel; Taboada-Crispi, Alberto; Universidad Central "Marta Abreu" de Las Villas. Departamento de Telecomunicaciones y Electronica
    La detección de anomalías en imágenes médicas es usada en la clasificación y detección de anormalidades. El objetivo de un detector de anomalías es la identificación de las diferencias en una serie de datos, sin tener ninguna información previa de sus propiedades. El objetivo de este trabajo es la construcción de un detector de anomalías para imágenes de la prueba de Papanicolaou, para lo que se diseñó e implementó un algoritmo que determinó regiones de interés. Este algoritmo se probó con 40 imágenes, 20 que sólo contenían células normales y 20 con células anómalas. El 100% de las imágenes con células anómalas presentó regiones de interés. De las 20 imágenes con sólo células normales, sólo 9 contuvieron regiones de interés. Por otro lado, el método propuesto incluyó en las regiones de interés al 92.43% de las células anómalas.
  • No hay miniatura disponible
    Ítem
    Fast Optic Disc Localization Using Viola-Jones Algorithm
    (2019-10-02) Garcia Garcia, Yainet; Rodriguez-Guillen, Reinier; Garcia, Y; Taboada-Crispi, Alberto; Universidad Central "Marta Abreu" de Las Villas. Departamento de Telecomunicaciones y Electronica
    This paper proposes the implementation of the Viola-Jones algorithm for the Optic Disc (OD) localization in eye fundus images. A robust classifier for the detection of the region of interest (ROI), which contains the OD through the Viola-Jones algorithm was trained, and the center of the ROI for the OD localization was found. A 8776-image dataset for training (7300) and testing (1476) the detector was conformed with images from public databases: DRIVE, DRIONS, ROC, HRF, MESSIDOR, DIARETB0 and DIARETB1. A success rate of 99.6% was obtained for the OD localization in an average time of 474 ms. The Viola-Jones algorithm results a fast, accurate and low-computational cost algorithm for the OD localization and it is applicable in the detection and localization of other structures as the macula and fovea. The results are comparable with those of the state-of-the-art algorithms and, in addition, they could be improved in future works and may be applied in eye computer-aided diagnosis or periodic evaluations of the eyes in real-time mobile applications.
  • No hay miniatura disponible
    Ítem
    Jitter as the main affecting factor in the performance of PDAs
    (2019-06-23) Rodriguez-Guillen, Reinier; Ferrer-Riesgo, Carlos A.; Universidad Central "Marta Abreu" de Las Villas. Departamento de Telecomunicaciones y Electronica; Universidad Central "Marta Abreu" de Las Villas. Laboratorio de PDSI adjunto a Centro de Estudios de la Informatica
    Jitter measurement is a frequent task in the acoustic analysis of pathological voices, and it relies in the previous determination of glottal pulse boundaries. The Praat software system has become a widely used tool to obtain both the pulse boundaries and the jitter measures. However, results provided by Praat can be misleading if the internal implementations of the procedures used to obtain the pulse boundaries are ignored. This paper addresses the influence of some of these settings in the ability of Praat to obtain these markers. Simulations are conducted to evaluate the effects of different types of periodicity perturbations (jitter, shimmer, noise, and their combination) and their levels on the resulting performance. 
  • No hay miniatura disponible
    Ítem
    Measuring Periodicity Perturbations in Pathological Voice: General-Purpose Software vs. Custom-Tailored Methods
    (2019-10-02) Rodriguez-Guillen, Reinier; Ferrer-Riesgo, Carlos A.; Universidad Central "Marta Abreu" de Las Villas. Departamento de Telecomunicaciones y Electronica; Universidad Central "Marta Abreu" de Las Villas. Laboratorio de PDSI adjunto a Centro de Estudios de la Informatica
    The acoustic measurement of the severity of the symptoms present in pathological voice is an active research area, for being inexpensive and non invasive. Periodicity perturbations are among the most frequently used, requiring the previous extraction of the individual glottal pulse boundaries. In this paper we explore the performances of methods for detecting glottal pulse boundaries as implemented by freely available software (Praat, intended for phonetic studies) vs. a research-grade pulse cycle detector (reported as a super-resolution method). We compare the sequences of pulse markers as obtained by two of Praat’s internal implementations and the super-resolution method against the hand-marked reference sequence in a dataset of pathological sustained vowels from a well-known database. A group of performance measures is extracted from this comparison, using a Dynamic-Time Warping alignment procedure. The measures obtained show the pros and cons of each alternative. Researchers and clinicians must be aware of the benefits of selecting either approach.