Search results for "Matched filter"
showing 10 items of 14 documents
Automatic Extraction of Blood Vessels, Bifurcations and End Points in the Retinal Vascular Tree
2008
In this paper we present an effective algorithm for automated extraction of the vascular tree in retinal images, including bifurcations, crossovers and end-points detection. Correct identification of these features in the ocular fundus helps the diagnosis of important systematic diseases, such as diabetes and hypertension. The pre-processing consists in artefacts removal based on anisotropic diffusion filter. Then a matched filter is applied to enhance blood vessels. The filter uses a full adaptive kernel because each vessel has a proper orientation and thickness. The kernel of the filter needs to be rotated for all possible directions. As a consequence, a suitable kernel has been designed …
Fullin-situcharacterization of spatial light modulators in an optical correlator. Filter adaptation to operating curves
1998
Abstract In this paper we present one method for the characterization of the spatial light modulators (SLMs) of a real-time Vander Lugt type of correlator. This correlator uses two SLMs: one to introduce the scene and a second to introduce the frequency‐matched filter. The SLM characterization methods are in situ, that is in the correlator set‐up. Illumination conditions are different for each SLM, and consequently different characterization techniques must be used in each case. For the characterization of the scene SLM a diffraction method is used, while for the characterization of the filter SLM an interferometric technique is more convenient. Finally, we take into account the operating c…
Hybrid Procedure for Automated Detection of Cracking with 3D Pavement Data
2016
Pavement cracks are considered a major indicator of pavement performance. Because traditional manual crack surveys are dangerous, time consuming, and expensive, technologies have been developed to collect high-speed pavement images, and numerous algorithms have been proposed to detect cracks on pavement surface. The latest PaveVision3D Ultra system (3D Ultra) has been implemented to achieve 30-kHz three-dimensional (3D) scanning rate for 1-mm resolution pavement surface data at highway speed up to 100 km/h (60 mi/h). This paper presents the application of a hybrid procedure for automated crack detection on 3D pavement data collected using 3D Ultra. The procedure combines three different me…
Blood vessel segmentation and width estimation in ultra-wide field scanning laser ophthalmoscopy.
2014
Features of the retinal vasculature, such as vessel widths, are considered biomarkers for systemic disease. The aim of this work is to present a supervised approach to vessel segmentation in ultra-wide field of view scanning laser ophthalmoscope (UWFoV SLO) images and to evaluate its performance in terms of segmentation and vessel width estimation accuracy. The results of the proposed method are compared with ground truth measurements from human observers and with existing state-of-the-art techniques developed for fundus camera images that we optimized for UWFoV SLO images. Our algorithm is based on multi-scale matched filters, a neural network classifier and hysteresis thresholding. After …
Different strategies in optical recognition of polychromatic images.
1992
We treat two different problems in the recognition of polychromatic images: (1) recognition of an object with a given shape and color combination; (2) recognition of an object regardless of its color combination. To solve each problem we propose different strategies. The number of filters and the objects to which the filters are matched vary with the strategy. Phase-only filters have been used to achieve recognition of both problems. Computer results are given for different targets and scenes to show the behavior of the proposed strategies.
Experimental multichannel recognition capability of polychromatic objects using optical correlators
1990
Polychromatic object recognition by multichannel correlation is experimentally achieved. Model objects whose shape changes with the wavelength of the illumination beam were used. Highpass matched filters were employed. The results confirm previous numerical simulations 1.
Blood vessels and feature points detection on retinal images
2009
In this paper we present a method for the automatic extraction of blood vessels from retinal images, while capturing points of intersection/overlap and endpoints of the vascular tree. The algorithm performance is evaluated through a comparison with handmade segmented images available on the STARE project database (STructured Analysis of the REtina). The algorithm is performed on the green channel of the RGB triad. The green channel can be used to represent the illumination component. The matched filter is used to enhance vessels w.r.t. the background. The separation between vessels and background is accomplished by a threshold operator based on gaussian probability density function. The len…
Optic disc positioning and blood vessels extraction on eye fundus
2009
This paper presents two methods aimed to the optic disc positioning on the retinal images. The first is based on a template of the entire image, while the second is based on the retinal vascularisation. For this second task, also a vessel extraction method is provided. Both the algorithm have been tested on test images of the Drive Database.
Multiple Matched Spatial Filter Performed With Nonsymmetrical Fourier Transformers
1987
MULTIPLE MATCHED SPATIAL FILTER PERFORMED WITH NONSYMMETRICAL FOURIER TRANSFORMERSCARLOS FERREIRA and CARMEN VAZQUEZDepartamento de Optica. Universitat de Valencia.C/ Dr. Moliner, 50. 46100 Burjassot, Spain.1. INTRODUCTIONClassical matched spatial filters (CMSF) have been successfully employed for optical pattern recog-nition. To detect different signals, multiple matched spatial filters can be synthesized and several me-thods to perform the filters have been developed. Based on the sensitivity to input orientation of CMSF,we proposed a filter [1] where the signals to be detected were rotated by different angles when recordingthe hologram. Thus, the recognition of a signal is only achieved …
Analysis of pattern recognition by man using detection experiments.
1981
This paper addresses the problem of analyzing biological pattern recognition systems. As no complete analysis is possible due to limited observability, the theoretical part of the paper examines some principles of construction for recognition systems. The relations between measurable and characteristic variables of these systems are described. The results of the study are: 1. Human recognition systems can always be described by a model consisting of an analyzer (FA) and a linear classifier. 2. The linearity of the classifier places no limits on the universal validity of the model. The principle of organization of such a system may be put into effect in many different ways. 3. The analyzer f…