Maurício Marengoni

Segmentation of optic disc and blood vessels in retinal images using wavelets, mathematical morphology and Hessian-based multi-scale filtering

Abstract The high importance of the accurate and early diagnostic has motivated the development of computer vision techniques of image processing and segmentation required for an completely automated assessment system for the retinal conditions. In this study we present a new algorithm built on wavelets transforms and mathematical morphology for detecting the optic disc and we explore the tubular characteristic of the blood vessels to segment the retinal veins and arteries. Both, optic disc and vascular structure, are landmarks for image registration and are essential for the retinal image analysis. Instead of a manual try and error method to choose the best parameters for detecting vessels as accurately as possible, we used a genetic algorithm and its sequence of generations and crossovers. However the technique of exploring the tubular characteristic of the vessels reaches its limits when the vessels are represented by, sometimes not continuous, winding lines of 1 pixel. To overcome this limitation we adopted a graph based approach using Dijkstras shortest path algorithm to track the segments and a statistic method of Student t distribution to assess whether or not the identified segment is part of the vascular structure. The proposed method was developed and tested on the Digital Retinal Images for Vessel Extraction (DRIVE) freely available database, which contains 40 annotated color eye fundus image.

Tutorial: Introdução à Visão Computacional usando OpenCV

Este tutorial apresenta conceitos introdutorios de processamento de imagens (filtros) e de visao computacional (segmentacao, classificacao, reconhecimento de padrao e rastreamento). Estes conceitos serao introduzidos utilizando a biblioteca OpenCV, que e distribuida gratuitamente e possui documentacao farta na internet, com exemplos e aplicacoes praticas. Sera mostrado como obter e como instalar a ferramenta para diversos tipos de plataformas e linguagens de desenvolvimento. Os conceitos de processamento de imagens e visao computacional serao discutidos nao apenas no aspecto teorico, mas tambem serao apresentados exemplos de implementacao para que os leitores possam entender e utilizar os exemplos apresentados neste tutorial.

Segmentation of Optic Disc and Blood Vessels in Retinal Images using Wavelets, Mathematical Morphology and Hessian-based Multi-scale Filtering

A digitized image captured by a fundus camera provides an effective, inexpensive and non-invasive resource for the assessment of vascular damage caused by diabetes, arterial hypertension, hypercholesterolemia and aging. These unhealthy conditions may have very serious consequence like hemorrhages, exudates, branch retinal vein occlusion, leading to the partial or total loss of vision capabilities. This study has focus on the computer vision techniques of image segmentation required for a completely automated assessment system for the vascular conditions of the eye. The study here presented proposes a new algorithm based on wavelets transforms and mathematical morphology for the segmentation of the optic disc and a Hessian based multiscale filtering to segment the vascular tree in color eye fundus photographs. The optic disc and vessel tree, are both essential to the analysis of the retinal fundus image. The optic disc can be identified by a bright region on the fundus image, for its segmentation we apply Haar wavelets transform to obtain the low frequencies representation of the image and then apply mathematical morphology to enhance the segmentation. The tree vessel segmentation is achieved using a Hessian-based multi-scale filtering that, based on its second order derivatives, explores the tubular shape of a blood vessel to classify the pixels as part, or not, of a vessel. The proposed method is being developed and tested based on the DRIVE database, which contains 40 color eye fundus images.

Development of a Computer Interface for People with Disabilities based on Computer Vision.

The growing of the population with disabilities in the world must be accompanied by the growing of research and development of tools that help these users on basic computer activities. This paper presents the development of a system that allows the use of personal computers using only face movements. The system can be used by people with motor disabilities who still have head movements, such as superior members amputees and tetraplegic. For the development of the proposed system, the most efficient techniques in previous works were collected and analyzed, and new ones were developed in order to build a system with high performance and precision, ensuring the digital and social inclusion of the target public. Tests have shown that the tool is easy to learn, has a good performance and can be used in everyday computer applications.

Enhancing Pedestrian Detection Using Context Information

Detecting pedestrians among other objects in a digital image is a relevant task in the field of computer vision. This paper presents a method to improve the performance of a pedestrian detection algorithm using context information. A neural network is used to classify the region below pedestrian candidates as being floor or non-floor. We assume that a pedestrian must be standing on a floor area. This scene context information is used to eliminate some of the false-positive pedestrian candidates, therefore improving detector precision. The neural network uses 10 feature channels extracted from the original image to perform the region classification. This method may be used along with a large family of pedestrian-detecting algorithms. We used the ACF-LDCF algorithm to perform the tests in this research. The result shows that this method is very effective. We achieve a gain of 7% in ACF-LDCF algorithm performance on the Caltech pedestrian benchmark.

Ground Plane Segmentation Using Artificial Neural Network for Pedestrian Detection

This paper presents a method of ground plane segmentation for urban outdoor scenes using a feedforward artificial neural network (ANN). The main motivation of this project is to obtain some contextual information from the scene for use in pedestrian detection algorithms and to provide an accuracy improvement for this algorithms. The ANN input is fed with features extracted from a patch window of the image scene. The ANN output classifies the patch as belonging or not belonging to the ground plane. After that, the classified patches are joined into a full image with the ground plane area outlined. The images used for training, test and evaluation were obtained from the widely known Caltech-USA database. The accuracy of ground plane segmentation was above 96% in the experiments which improved the precision of the pedestrian detector in 38,5%.

A Recommendation System for Paintings using Bag of Keypoints and Dominant Color Descriptors

Determining the visual description for a painting is an interesting task that can be used in different applications, like retrieval, classification and recommendation. A painting can differ from others depending on the time period it was painted, the genre and the art movement the author lived. This paper present an approach for content based image retrieval applied to art paintings using the concept of bag of keypoints and SURF detector. A descriptor for dominant color is also used and weighted for a best visual retrieval.

Detecting giant solar flares based on sunspot parameters using bayesian networks

This paper presents the use of Bayesian Networks (BN) in a new area, the detection of solar flares. The paper describes how to learn a Bayesian Network (BN) using a set of variables representing sunspots parameters such that the BN can detect and classify solar flares. Giant solar flares happen in the Suns atmosphere quite frequently and as a consequence they can affect Earth. The work described here shows the relationship between the learned networks and the causality expected by solar physicists. The data used for learning and cross validation experiments show that the network substructures are easy to learn and robust enough to predict solar flares. The systems presented here are capable of detecting the flares within 72 hours, while the current method used today does the same work within 24 hours in advance only. It is also shown that sunspot parameters change over time, so different networks can be learned and perhaps combined in order to build a robust forecast system.