This paper presents a morphological-based approach for melanoma segmentation. By using color math... more This paper presents a morphological-based approach for melanoma segmentation. By using color mathematical tools based on HSI lexicographic order, we show that it is possible to detect the melanoma lesion with accuracy. Experimental results have shown the efficiency of the methodology onto benign and malignant melanoma databases.
This database containing 396 color fundus images that were acquired at the Department of Ophthalm... more This database containing 396 color fundus images that were acquired at the Department of Ophthalmology of the Hospital de Clínicas, Facultad de Ciencias Médicas, Universidad Nacional de Asunción, Paraguay. The acquisition of retinal images was done taking into account a clinical procedure. The acquisition of the retinographies was made through the Visucam 500 camera of the Zeiss brand. Expert ophthalmologists have classified the dataset. These data can help doctors and researchers in the detection of cases of Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR), in their different stages. The classification of fundus images have been done in 7 categories: i) No DR signs (20 images), ii) mild NPDR (4 images), iii) moderate NPDR (58 images), iv) severe NPDR (92 images), v) very severe NPDR (83 images), vi) PDR (70 images) and vii) Advanced PDR (69 images).
2015 Latin American Computing Conference (CLEI), 2015
Due to its versatility, the image processing area offers a very wide range of techniques to solve... more Due to its versatility, the image processing area offers a very wide range of techniques to solve challenges in an effective way linked to fields such as medicine, agriculture, biology, industrial automation and document processing. Therefore a correct and advanced training of professionals in this area is an important task. In this sense, a new educational image processing tool is currently being developed at the Facultad Politecnica of the Universidad Nacional of Asuncion. The development focused on improving the interaction between students and teachers and also showing new advances in digital image processing area. To achieve this goal, a tool is being developed to be expanded in the future to be adapted to new challenges and different audiences. The first stage of development was completed, which allowed developing an extendable basic tool in the near future.
Diabetic retinopathy is a complication of a widespread eye disease named diabetes mellitus. Diabe... more Diabetic retinopathy is a complication of a widespread eye disease named diabetes mellitus. Diabetes mellitus, due to the increased glucose levels, may damage the retina’s blood vessels and cause visual complications and eventually blindness. Therefore, early detection and adequate assessment of disease progression are crucial for adequate treatment. The most widely used method for diagnosing diabetic retinopathy is the analysis of retinal fundus images obtained by retinography. Deep Learning-based methods have shown promising results as a diagnostic tool for diabetic retinopathy, achieving, in some cases, performance close to the human inspection of images. However, the performance of these methods relies heavily on fine-tuning the algorithm hyperparameters and big data sets. In this work, we propose training a Deep Learning network with evolutionary algorithms to classify three stages of Diabetic Retinopathy: i) no sign of diabetic retinopathy, ii) Non-proliferative diabetic retin...
This paper presents an optimized method for establishing the authorship of questioned handwritten... more This paper presents an optimized method for establishing the authorship of questioned handwritten documents, on the basis of a forensic analysis and a computational model using texture descriptors. The proposed method uses two classes of texture descriptors: model-based, using fractal geometry, and statistical, using GLCM (Gray-Level Co-occurrence Matrix) and Haralick’s descriptors. The proposed method also uses an SVM (Support Vector Machine) as a classifier and generator of the writer-independent training. The results demonstrate the robustness of the writer-independent obtained from the features by using texture descriptors and robustness in the amount low of samples used as references for comparison and the number of feature used. The results appear promising, in the order of 97.7 %, and are consistent with those obtained in other studies that used the same database.
Studies in Health Technology and Informatics, 2021
Ocular toxoplasmosis (OT) is commonly diagnosed through the analysis of fundus images of the eye ... more Ocular toxoplasmosis (OT) is commonly diagnosed through the analysis of fundus images of the eye by a specialist. Despite Deep Learning being widely used to process and recognize pathologies in medical images, the diagnosis of ocular toxoplasmosis(OT) has not yet received much attention. A predictive computational model is a valuable time-saving option if used as a support tool for the diagnosis of OT. It could also help diagnose atypical cases, being particularly useful for ophthalmologists who have less experience. In this work, we propose the use of a deep learning model to perform automatic diagnosis of ocular toxoplasmosis from images of the eye fundus. A pretrained residual neural network is fine-tuned on a dataset of samples collected at the medical center of Hospital de Clínicas in Asunción, Paraguay. With sensitivity and specificity rates equal to 94% and 93%,respectively, the results show that the proposed model is highly promising. In order to replicate the results and ad...
This article presents a database containing 757 color fundus images acquired at the Department of... more This article presents a database containing 757 color fundus images acquired at the Department of Ophthalmology of the Hospital de Clínicas, Facultad de Ciencias Médicas (FCM), Universidad Nacional de Asunción (UNA), Paraguay. Firstly, the retinal images were acquired with a clinical procedure presented in this paper. The acquisition of the retinographies was made through the Visucam 500 camera of the Zeiss brand. Next, two expert ophthalmologists have classified the dataset. These data can help physicians and researchers in the detection of cases of Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR), in their different stages. The dataset generated will be useful for ophthalmologists and researchers to work on automatic detection algorithms for Diabetic Retinopathy (DR).
2014 IEEE 26th International Conference on Tools with Artificial Intelligence, 2014
This paper addresses the problem of recognizing gestures which are captured using the Kinect sens... more This paper addresses the problem of recognizing gestures which are captured using the Kinect sensor in a educational game devoted to the deaf community. Different strategies are evaluated to deal with the problem of having few samples for training. We have experimented a Leave One Out Training and Testing (LOOT) strategy and an HMM-based ensemble of classifiers. A dataset containing 181 videos of gestures related to nine signs commonly used in educational games is introduced, which is available for research purposes. The experimental results have shown that the proposed ensemble-based method is a promising strategy to deal with problems where few training samples are available.
This database contains 598 panoramic radiographs, whose dimensions are 2041 x 1024 and are in a J... more This database contains 598 panoramic radiographs, whose dimensions are 2041 x 1024 and are in a JPEG format. <br> These images were acquired with Owandy I-max Touch panoramic radiography equipment belonging to the <em>Departamento de Radiología de la Facultad de Odontología, Universidad Nacional de Asunción, </em>located in Asuncion, Paraguay<em>.</em>
2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA), 2016
Fire detection is a very important task to save human lives and ecological systems. On literature... more Fire detection is a very important task to save human lives and ecological systems. On literature, several fire detection methods use a color mapping function to help on detection process. In this context, we propose a new method based on fire probabilistic color mapping. Using Entropy rules was possible to improve the metric rates. We also numerically evaluate the quality of published fire segmentation techniques and the new one using some segmentation metrics onto two datasets: one for training and test with 226 images and second with 110 images for test. With better performance than compared methods in True Positive (81.33%), Accuracy (89.90%), F-Measure (82.58%) and True Negative rates for not-fire images (98.16%), the results show that our proposed method is more accurate for extracting fire region, indicating the effectiveness contribution of our fire probabilistic color mapping using entropy.
This paper presents a morphological-based approach for melanoma segmentation. By using color math... more This paper presents a morphological-based approach for melanoma segmentation. By using color mathematical tools based on HSI lexicographic order, we show that it is possible to detect the melanoma lesion with accuracy. Experimental results have shown the efficiency of the methodology onto benign and malignant melanoma databases.
This database containing 396 color fundus images that were acquired at the Department of Ophthalm... more This database containing 396 color fundus images that were acquired at the Department of Ophthalmology of the Hospital de Clínicas, Facultad de Ciencias Médicas, Universidad Nacional de Asunción, Paraguay. The acquisition of retinal images was done taking into account a clinical procedure. The acquisition of the retinographies was made through the Visucam 500 camera of the Zeiss brand. Expert ophthalmologists have classified the dataset. These data can help doctors and researchers in the detection of cases of Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR), in their different stages. The classification of fundus images have been done in 7 categories: i) No DR signs (20 images), ii) mild NPDR (4 images), iii) moderate NPDR (58 images), iv) severe NPDR (92 images), v) very severe NPDR (83 images), vi) PDR (70 images) and vii) Advanced PDR (69 images).
2015 Latin American Computing Conference (CLEI), 2015
Due to its versatility, the image processing area offers a very wide range of techniques to solve... more Due to its versatility, the image processing area offers a very wide range of techniques to solve challenges in an effective way linked to fields such as medicine, agriculture, biology, industrial automation and document processing. Therefore a correct and advanced training of professionals in this area is an important task. In this sense, a new educational image processing tool is currently being developed at the Facultad Politecnica of the Universidad Nacional of Asuncion. The development focused on improving the interaction between students and teachers and also showing new advances in digital image processing area. To achieve this goal, a tool is being developed to be expanded in the future to be adapted to new challenges and different audiences. The first stage of development was completed, which allowed developing an extendable basic tool in the near future.
Diabetic retinopathy is a complication of a widespread eye disease named diabetes mellitus. Diabe... more Diabetic retinopathy is a complication of a widespread eye disease named diabetes mellitus. Diabetes mellitus, due to the increased glucose levels, may damage the retina’s blood vessels and cause visual complications and eventually blindness. Therefore, early detection and adequate assessment of disease progression are crucial for adequate treatment. The most widely used method for diagnosing diabetic retinopathy is the analysis of retinal fundus images obtained by retinography. Deep Learning-based methods have shown promising results as a diagnostic tool for diabetic retinopathy, achieving, in some cases, performance close to the human inspection of images. However, the performance of these methods relies heavily on fine-tuning the algorithm hyperparameters and big data sets. In this work, we propose training a Deep Learning network with evolutionary algorithms to classify three stages of Diabetic Retinopathy: i) no sign of diabetic retinopathy, ii) Non-proliferative diabetic retin...
This paper presents an optimized method for establishing the authorship of questioned handwritten... more This paper presents an optimized method for establishing the authorship of questioned handwritten documents, on the basis of a forensic analysis and a computational model using texture descriptors. The proposed method uses two classes of texture descriptors: model-based, using fractal geometry, and statistical, using GLCM (Gray-Level Co-occurrence Matrix) and Haralick’s descriptors. The proposed method also uses an SVM (Support Vector Machine) as a classifier and generator of the writer-independent training. The results demonstrate the robustness of the writer-independent obtained from the features by using texture descriptors and robustness in the amount low of samples used as references for comparison and the number of feature used. The results appear promising, in the order of 97.7 %, and are consistent with those obtained in other studies that used the same database.
Studies in Health Technology and Informatics, 2021
Ocular toxoplasmosis (OT) is commonly diagnosed through the analysis of fundus images of the eye ... more Ocular toxoplasmosis (OT) is commonly diagnosed through the analysis of fundus images of the eye by a specialist. Despite Deep Learning being widely used to process and recognize pathologies in medical images, the diagnosis of ocular toxoplasmosis(OT) has not yet received much attention. A predictive computational model is a valuable time-saving option if used as a support tool for the diagnosis of OT. It could also help diagnose atypical cases, being particularly useful for ophthalmologists who have less experience. In this work, we propose the use of a deep learning model to perform automatic diagnosis of ocular toxoplasmosis from images of the eye fundus. A pretrained residual neural network is fine-tuned on a dataset of samples collected at the medical center of Hospital de Clínicas in Asunción, Paraguay. With sensitivity and specificity rates equal to 94% and 93%,respectively, the results show that the proposed model is highly promising. In order to replicate the results and ad...
This article presents a database containing 757 color fundus images acquired at the Department of... more This article presents a database containing 757 color fundus images acquired at the Department of Ophthalmology of the Hospital de Clínicas, Facultad de Ciencias Médicas (FCM), Universidad Nacional de Asunción (UNA), Paraguay. Firstly, the retinal images were acquired with a clinical procedure presented in this paper. The acquisition of the retinographies was made through the Visucam 500 camera of the Zeiss brand. Next, two expert ophthalmologists have classified the dataset. These data can help physicians and researchers in the detection of cases of Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR), in their different stages. The dataset generated will be useful for ophthalmologists and researchers to work on automatic detection algorithms for Diabetic Retinopathy (DR).
2014 IEEE 26th International Conference on Tools with Artificial Intelligence, 2014
This paper addresses the problem of recognizing gestures which are captured using the Kinect sens... more This paper addresses the problem of recognizing gestures which are captured using the Kinect sensor in a educational game devoted to the deaf community. Different strategies are evaluated to deal with the problem of having few samples for training. We have experimented a Leave One Out Training and Testing (LOOT) strategy and an HMM-based ensemble of classifiers. A dataset containing 181 videos of gestures related to nine signs commonly used in educational games is introduced, which is available for research purposes. The experimental results have shown that the proposed ensemble-based method is a promising strategy to deal with problems where few training samples are available.
This database contains 598 panoramic radiographs, whose dimensions are 2041 x 1024 and are in a J... more This database contains 598 panoramic radiographs, whose dimensions are 2041 x 1024 and are in a JPEG format. <br> These images were acquired with Owandy I-max Touch panoramic radiography equipment belonging to the <em>Departamento de Radiología de la Facultad de Odontología, Universidad Nacional de Asunción, </em>located in Asuncion, Paraguay<em>.</em>
2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA), 2016
Fire detection is a very important task to save human lives and ecological systems. On literature... more Fire detection is a very important task to save human lives and ecological systems. On literature, several fire detection methods use a color mapping function to help on detection process. In this context, we propose a new method based on fire probabilistic color mapping. Using Entropy rules was possible to improve the metric rates. We also numerically evaluate the quality of published fire segmentation techniques and the new one using some segmentation metrics onto two datasets: one for training and test with 226 images and second with 110 images for test. With better performance than compared methods in True Positive (81.33%), Accuracy (89.90%), F-Measure (82.58%) and True Negative rates for not-fire images (98.16%), the results show that our proposed method is more accurate for extracting fire region, indicating the effectiveness contribution of our fire probabilistic color mapping using entropy.
Uploads
Papers by Jacques Facon