Automatic 3D-Reconstruction of the Ocular Fundus from Stereo Images
نویسندگان
چکیده
The methods of computer vision allow the 3D-reconstruction of an object from 2D stereo image pairs. The EU-Project Glaucad studies the glaucoma disease regarding appropriate geometric characterizations. Our task within this project is to develop a module for automatic 3D-reconstruction of the ocular fundus out of the uncalibrated stereo images. These reconstructions will be used to analyze the changes of the ocular fundus of glaucoma patients. Using methods of computer vision two main demands turned out to produce precise results: A good image preprocessing to compensate the partly changing and difficult recording conditions and a precise registration as prerequisite for the later calculation steps.
منابع مشابه
3D Fundus Shape Reconstruction and Display From Stereo Fundus Images
I I A new method to recover and display 3D fundus lobictkn ~ow"w*n shape, inner bottom shape of eyeball, from stereo fundus image pair is developed. For the fundus stereo images, a simple stereo technique does not work, because the fundus is observed through eye lens and a contact wide-angle enlarging lens. In this yf lvLq: method, utilizing the fact that fundus forms a part of sphere, we ident...
متن کاملAutomatic Detection of Microaneurysms in Color Fundus Images using a Local Radon Transform Method
Introduction: Diabetic retinopathy (DR) is one of the most serious and most frequent eye diseases in the world and the most common cause of blindness in adults between 20 and 60 years of age. Following 15 years of diabetes, about 2% of the diabetic patients are blind and 10% suffer from vision impairment due to DR complications. This paper addresses the automatic detection of microaneurysms (MA...
متن کامل3D Surface Reconstruction of Optical Disc
This article deals with retinal surface reconstruction obtained with the fundus camera. Two stereo images (photographs) are used to estimate the disparity, which is connected to the depth in the scene. New gradient-based method is used to perform the first estimate of disparity, followed by several postprocessing steps to eliminate errors.
متن کاملThree-dimensional buildings reconstruction from IKONOS stereo images
High resolution IKONOS stereo imagery provides an important data source for threedimensional scene extraction. In urban areas, it has been long a challenge topic to automatically extract urban objects from images due to the high object density and scene complexity. In this paper, we propose a new method for automatic 3d building reconstruction from IKONOS stereo images. Our approach is based on...
متن کاملAutomatic 3D Point Set Reconstruction from Stereo Laparoscopic Images using Deep Neural Networks
In this paper, an automatic approach to predict 3D coordinates from stereo laparoscopic images is presented. The approach maps a vector of pixel intensities to 3D coordinates through training a six layer deep neural network. The architectural aspects of the approach is presented and in detail and the method is evaluated on a publicly available dataset with promising results.
متن کامل