Author: Leopoldo Altamirano Robles

Reference Fields Analysis of a Markov Random Field Model to Improve Image Segmentation

ERIKA DANAE LOPEZ ESPINOZA LEOPOLDO ALTAMIRANO ROBLES (2010)

Markov random field (MRF) models, parameters such as internal and external reference fields are used. In this paper, the influence of these parameters in the segmentation quality is analyzed, and it is shown that, for image segmentation, a MRF model with a priori energy function defined by means of non-homogeneous internal and external field has better segmentation quality than a MRF model defined only by a homogeneous internal reference field. An analysis of the MRF models in terms of segmentation quality, computational time and tests of statistical significance is done. Significance tests showed that the segmentations obtained with MRF model defined by means of non-homogeneous reference fields are significant at levels of 85% and 75%.

Article

CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA Image segmentation unsupervised segmentation Markov random field non-homogeneous random field

Reference fields analysis of a Markov random field model to improve image segmentation

ERIKA DANAE LOPEZ ESPINOZA LEOPOLDO ALTAMIRANO ROBLES (2010)

In Markov random field (MRF) models, parameters such as internal and external reference fields are used. In this paper, the influence of these parameters in the segmentation quality is analyzed, and it is shown that, for image segmentation, a MRF model with a priori energy function defined by means of non-homogeneous internal and external field has better segmentation quality than a MRF model defined only by a homogeneous internal reference field. An analysis of the MRF models in terms of segmentation quality, computational time and tests of statistical significance is done. Significance tests showed that the segmentations obtained with MRF model defined by means of non-homogeneous reference fields are significant at levels of 85% and 75%.

Article

Image segmentation Unsupervised segmentation Markov random field Non-homogeneous random field CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES

Reference Fields Analysis of a Markov Random Field Model to Improve Image Segmentation

ERIKA DANAE LOPEZ ESPINOZA LEOPOLDO ALTAMIRANO ROBLES (2010)

Markov random field (MRF) models, parameters such as internal and external reference fields are used. In this paper, the influence of these parameters in the segmentation quality is analyzed, and it is shown that, for image segmentation, a MRF model with a priori energy function defined by means of non-homogeneous internal and external field has better segmentation quality than a MRF model defined only by a homogeneous internal reference field. An analysis of the MRF models in terms of segmentation quality, computational time and tests of statistical significance is done. Significance tests showed that the segmentations obtained with MRF model defined by means of non-homogeneous reference fields are significant at levels of 85% and 75%.

Article

CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA Image segmentation unsupervised segmentation Markov random field non-homogeneous random field

Recording lifetime behavior and movement in an invertebrate model

Pablo Liedo Leopoldo Altamirano Robles JANETH CRUZ ENRIQUEZ (2011)

Characterization of lifetime behavioral changes is essential for understanding aging and aging-related diseases. However, such studies are scarce partly due to the lack of efficient tools. Here we describe and provide proof of concept for a stereo vision system that classifies and sequentially records at an extremely fine scale six different behaviors (resting, micro-movement, walking, flying, feeding and drinking) and the within-cage (3D) location of individual tephritid fruit flies by time-of-day throughout their lives. Using flies fed on two different diets, full sugar-yeast and sugar-only diets, we report for the first time their behavioral changes throughout their lives at a high resolution. We have found that the daily activity peaks at the age of 15–20 days and then gradually declines with age for flies on both diets. However, the overall daily activity is higher for flies on sugar-only diet than those on the full diet. Flies on sugar-only diet show a stronger diurnal localization pattern with higher preference to staying on the top of the cage during the period of light-off when compared to flies on the full diet. Clustering analyses of age-specific behavior patterns reveal three distinct young, middle-aged and old clusters for flies on each of the two diets. The middle-aged groups for flies on sugar-only diet consist of much younger age groups when compared to flies on full diet. This technology provides research opportunities for using a behavioral informatics approach for understanding different ways in which behavior, movement, and aging in model organisms are mutually affecting.

Article

CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES

Automatic face interpretation using fast 3D illumination-based AAM models

SALVADOR EUGENIO AYALA RAGGI Leopoldo Altamirano Robles JANETH CRUZ ENRIQUEZ (2011)

We present an innovative and fast approach for face interpretation invariant to lighting and pose. Our approach performs interpretation by fitting a parametric 3D face model to an input image using an optimization algorithm. The parameters obtained after the fitting process describe the appearance of the face. The fitting process is automatic and only requires a 2D position and a scale factor as initialization. The proposed model is a natural 3D extension of active appearance models and is based on modeling, separately and simultaneously, 3D pose, 3D shape, albedo, and lighting. Our model is capable of synthesizing faces with arbitrary 3D shape, 3D pose, albedo and lighting. In order to fit the model to an input image, we propose a fast optimization algorithm able to fit face images with non-uniform lighting and arbitrary pose. Our algorithm, based on a gradient descent approach, executes a fast update to the Jacobian by using the lighting parameters estimated in each iteration of the fitting process. We show that our method is able to accurately estimate the parameters of 3D shape and albedo, which are strongly related to identity. Experimental results, suggest that our model can be extended to face recognition under non-uniform lighting and variable pose.

Article

Active appearance models Face interpretation 3D face alignment 3D model fitting Face modeling Illumination modeling Unconstrained face analysis CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES

Minería de datos con información de contexto para la clasificación de imágenes satelitales

Data mining with context information for satellite image classification

JESUS ANTONIO GONZALEZ BERNAL LEOPOLDO ALTAMIRANO ROBLES JUAN FRANCISCO ROBLES CAMACHO (2008)

En este artículo se presenta un esquema de clasificación multi-modelos para imágenes satelitales apoyado con información de contexto con el que se mejora la precisión de una pre-clasificación obtenida con algoritmos paramétricos. El nuevo esquema utiliza una red semántica como representación de conocimiento que almacena patrones creados con un ensamble de árboles de decisión (alimentado con características espectrales, de textura y geométricas para describir a las regiones de interés) y por otro lado patrones espaciales creados a partir de una representación basada en grafos (con información de contexto a partir de relaciones espaciales entre las regiones de interés). Los resultados experimentales muestran que el esquema de clasificación propuesto mejora la precisión de la pre-clasificación de los algoritmos paramétricos al utilizar información de contexto.

This paper presents a multi-model classification schema for satellite images supported with context information to enhance the accuracy of a pre-classification obtained with parametric algorithms. This new scheme uses a semantic network as knowledge representation that stores the patterns created with a decision tree ensemble (fed with spectral, texture and geometric descriptive characteristics to describe the regions of interest) and spatial patterns created with a graph-based representation (with context information obtained from spatial relations among regions of interest). Our experimental results show that the proposed classifi cation scheme enhances the pre-classification accuracy obtained with parametric algorithms when we use context information.

Article

Percepción remota Mapas temáticos Minería de datos Clasificación Información de contexto Remote sensing Thematic maps Data mining Classification Context information CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES

Improving fingerprint verification using minutiae triplets

MIGUEL ANGEL MEDINA PEREZ MILTON GARCÍA BORROTO ANDRES EDUARDO GUTIERREZ RODRIGUEZ Leopoldo Altamirano Robles (2012)

Improving fingerprint matching algorithms is an active and important research area in fingerprint recognition. Algorithms based on minutia triplets, an important matcher family, present some drawbacks that impact their accuracy, such as dependency to the order of minutiae in the feature, insensitivity to the reflection of minutiae triplets, and insensitivity to the directions of the minutiae relative to the sides of the triangle. To alleviate these drawbacks, we introduce in this paper a novel fingerprint matching algorithm, named M3gl. This algorithm contains three components: a new feature representation containing clockwise-arranged minutiae without a central minutia, a new similarity measure that shifts the triplets to find the best minutiae correspondence, and a global matching procedure that selects the alignment by maximizing the amount of global matching minutiae. To make M3gl faster, it includes some optimizations to discard non-matching minutia triplets without comparing the whole representation. In comparison with six verification algorithms, M3gl achieves the highest accuracy in the lowest matching time, using FVC2002 and FVC2004 databases.

Article

Fingerprint verification Minutiae descriptor Minutiae triplet CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES

Acute leukemia classification by ensemble particle swarm model selection

Hugo Jair Escalante Balderas Manuel Montes y Gómez Jesús Antonio González Bernal María del Pilar Gómez Gil Leopoldo Altamirano Robles CARLOS ALBERTO REYES GARCIA CAROLINA RETA CASTRO ALEJANDRO ROSALES PEREZ (2012)

Objective: Acute leukemia is a malignant disease that affects a large proportion of the world population. Different types and subtypes of acute leukemia require different treatments. In order to assign the correct treatment, a physician must identify the leukemia type or subtype. Advanced and precise methods are available for identifying leukemia types, but they are very expensive and not available in most hospitals in developing countries. Thus, alternative methods have been proposed. An option explored in this paper is based on the morphological properties of bone marrow images, where features are extracted from medical images and standard machine learning techniques are used to build leukemia type classifiers. Methods and materials: This paper studies the use of ensemble particle swarm model selection (EPSMS), which is an automated tool for the selection of classification models, in the context of acute leukemia classification. EPSMS is the application of particle swarm optimization to the exploration of the search space of ensembles that can be formed by heterogeneous classification models in a machine learning toolbox. EPSMS does not require prior domain knowledge and it is able to select highly accurate classification models without user intervention. Furthermore, specific models can be used for different classification tasks. Results: We report experimental results for acute leukemia classification with real data and show that EPSMS outperformed the best results obtained using manually designed classifiers with the same data. The highest performance using EPSMS was of 97.68% for two-type classification problems and of 94.21% for more than two types problems. To the best of our knowledge, these are the best results reported for this data set. Compared with previous studies, these improvements were consistent among different type/subtype classification tasks, different features extracted from images, and different feature extraction regions. The performance improvements were statistically significant.Weimproved previous results by an average of 6% and there are improvements of more than 20% with some settings. In addition to the performance improvements, we demonstrated that no manual effort was required during acute leukemia type/subtype classification.

Conclusions: Morphological classification of acute leukemia usingEPSMSprovides an alternative to expensive diagnostic methods in developing countries. EPSMS is a highly effective method for the automated construction of ensemble classifiers for acute leukemia classification, which requires no significant user intervention. EPSMS could also be used to address other medical classification tasks.

Article

Ensemble learning Swarm optimization Full model selection Morphological classification Analysis of bone marrow cell images Acute leukemia classification CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA MATEMÁTICAS CIENCIA DE LOS ORDENADORES CIENCIA DE LOS ORDENADORES