Edgar Omar Molina Molina
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Edgar Omar Molina Molina has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Edgar Chávez
CICESE-Ciencias de la Computación
1 shared publication- Hugo Hidalgo
CICESE, Ensenada, Mexico
1 shared publication - Josué Álvarez-Borrego
Centro de Investigación Científica y de Educación Superior de Ensenada
1 shared publication Julia Diaz
CICESE-Ciencias de la Computación
1 shared publication- Selene Solorza-Calderón
Univ. Autónoma de Baja California (Mexico)
1 shared publication - Victor Hugo Diaz Ramirez
Instituto Politécnico Nacional - CITEDI, Tijuana, Mexico
1 shared publication
Latest Publications
- Open Access
- 15 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (14) , 7879
Breast Cancer Image Classification Using Phase Features and Deep Ensemble Models
Breast cancer is a leading cause of mortality among women worldwide. Early detection is crucial for increasing patient survival rates. Artificial intelligence, particularly convolutional neural networks (CNNs), has enabled the development of effective diagnostic systems by digitally processing mammograms. CNNs have been widely used for the classification of breast cancer in images, obtaining accurate results similar in many cases to those of medical specialists. This work presents a hybrid feature extraction approach for breast cancer detection that employs variants of EfficientNetV2 network and convenient image representation based on phase features. First, a region of interest (ROI) is extracted from the mammogram. Next, a three-channel image is created using the local phase, amplitude, and orientation features of the ROI. A feature vector is constructed for the processed mammogram using the developed CNN model. The size of the feature vector is reduced using simple statistics, achieving a redundancy suppression of . The reduced feature vector is classified as either malignant or benign using a classifier ensemble. Experimental results using a training/testing ratio of 70/30 on 15,506 mammography images from three datasets produced an accuracy of , a precision of , a recall of , and an F1-score of with the modified EfficientNetV2 model and stacking classifier. However, an accuracy of , a precision of , a recall of , and an F1-score of were obtained using only CSAW-M dataset images.- 15 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (14) , 7879
Open AccessBreast Cancer Image Classification Using Phase Features and Deep Ensemble Models
Breast cancer is a leading cause of mortality among women worldwide. Early detection is crucial for increasing patient survival rates. Artificial intelligence, particularly convolutional neural networks (CNNs), has enabled the development of effective diagnostic systems by digitally processing mammograms. CNNs have been widely used for the classification of breast cancer in images, obtaining accurate results similar in many cases to those of medical specialists. This work presents a hybrid feature extraction approach for breast cancer detection that employs variants of EfficientNetV2 network and convenient image representation based on phase features. First, a region of interest (ROI) is extracted from the mammogram. Next, a three-channel image is created using the local phase, amplitude, and orientation features of the ROI. A feature vector is constructed for the processed mammogram using the developed CNN model. The size of the feature vector is reduced using simple statistics, achieving a redundancy suppression of . The reduced feature vector is classified as either malignant or benign using a classifier ensemble. Experimental results using a training/testing ratio of 70/30 on 15,506 mammography images from three datasets produced an accuracy of , a precision of , a recall of , and an F1-score of with the modified EfficientNetV2 model and stacking classifier. However, an accuracy of , a precision of , a recall of , and an F1-score of were obtained using only CSAW-M dataset images. - Open Access
- 27 August 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (17) , 5954
Classification of Dermoscopy Skin Lesion Color-Images Using Fractal-Deep Learning Features
The detection of skin diseases is becoming one of the priority tasks worldwide due to the increasing amount of skin cancer. Computer-aided diagnosis is a helpful tool to help dermatologists in the detection of these kinds of illnesses. This work proposes a computer-aided diagnosis based on 1D fractal signatures of texture-based features combining with deep-learning features using transferred learning based in Densenet-201. This proposal works with three 1D fractal signatures built per color-image. The energy, variance, and entropy of the fractal signatures are used combined with 100 features extracted from Densenet-201 to construct the features vector. Because commonly, the classes in the dataset of skin lesion images are imbalanced, we use the technique of ensemble of classifiers: K-nearest neighbors and two types of support vector machines. The computer-aided diagnosis output was determined based on the linear plurality vote. In this work, we obtained an average accuracy of 97.35%, an average precision of 91.61%, an average sensitivity of 66.45%, and an average specificity of 97.85% in the eight classes’ classification in the International Skin Imaging Collaboration (ISIC) archive-2019.
- 27 August 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (17) , 5954
Open AccessClassification of Dermoscopy Skin Lesion Color-Images Using Fractal-Deep Learning Features
The detection of skin diseases is becoming one of the priority tasks worldwide due to the increasing amount of skin cancer. Computer-aided diagnosis is a helpful tool to help dermatologists in the detection of these kinds of illnesses. This work proposes a computer-aided diagnosis based on 1D fractal signatures of texture-based features combining with deep-learning features using transferred learning based in Densenet-201. This proposal works with three 1D fractal signatures built per color-image. The energy, variance, and entropy of the fractal signatures are used combined with 100 features extracted from Densenet-201 to construct the features vector. Because commonly, the classes in the dataset of skin lesion images are imbalanced, we use the technique of ensemble of classifiers: K-nearest neighbors and two types of support vector machines. The computer-aided diagnosis output was determined based on the linear plurality vote. In this work, we obtained an average accuracy of 97.35%, an average precision of 91.61%, an average sensitivity of 66.45%, and an average specificity of 97.85% in the eight classes’ classification in the International Skin Imaging Collaboration (ISIC) archive-2019.
- Open Access
- 22 June 2018
- Published by Universitat Politecnica de Valencia in Revista Iberoamericana de Automática e Informática Industrial
- Vol. 15 (3) , 252-261
Algoritmos de Binarización Robusta de Imágenes con Iluminación No Uniforme
La binarización es una técnica básica de procesamiento digital de imágenes. Los métodos de binarización han sido progresivamente mejorados para tratar con imágenes en condiciones más realistas. De particular importancia es considerar la condición de iluminación no uniforme de las imágenes a binarizar, presente cuando se realiza la adquisición de imágenes con equipo no especializado (e.g. un teléfono celular). En este trabajo se propone un nuevo enfoque para la binarización de imágenes de texto que fueron adquiridas bajo iluminación no uniforme. La idea central es obtener una iluminación más uniforme (apropiada para binarización) a partir de la fusión de dos imágenes iluminadas complementariamente. Para probar el desempeño de nuestra propuesta capturamos un conjunto grande de imágenes de texto reales, obtenidas con un teléfono celular, con diversas condiciones de iluminación no uniforme. Comparamos nuestra propuesta con diversas técnicas del estado del arte y mostramos que tenemos mejores resultados usando distintas métricas de binarización.
- 22 June 2018
- Published by Universitat Politecnica de Valencia in Revista Iberoamericana de Automática e Informática Industrial
- Vol. 15 (3) , 252-261
Open AccessAlgoritmos de Binarización Robusta de Imágenes con Iluminación No Uniforme
La binarización es una técnica básica de procesamiento digital de imágenes. Los métodos de binarización han sido progresivamente mejorados para tratar con imágenes en condiciones más realistas. De particular importancia es considerar la condición de iluminación no uniforme de las imágenes a binarizar, presente cuando se realiza la adquisición de imágenes con equipo no especializado (e.g. un teléfono celular). En este trabajo se propone un nuevo enfoque para la binarización de imágenes de texto que fueron adquiridas bajo iluminación no uniforme. La idea central es obtener una iluminación más uniforme (apropiada para binarización) a partir de la fusión de dos imágenes iluminadas complementariamente. Para probar el desempeño de nuestra propuesta capturamos un conjunto grande de imágenes de texto reales, obtenidas con un teléfono celular, con diversas condiciones de iluminación no uniforme. Comparamos nuestra propuesta con diversas técnicas del estado del arte y mostramos que tenemos mejores resultados usando distintas métricas de binarización.