Search results for "ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION"
showing 10 items of 982 documents
Hidden Markov Random Fields and Direct Search Methods for Medical Image Segmentation
2016
The goal of image segmentation is to simplify the representation of an image to items meaningful and easier to analyze. Medical image segmentation is one of the fundamental problems in image processing field. It aims to provide a crucial decision support to physicians. There is no one way to perform the segmentation. There are several methods based on HMRF. Hidden Markov Random Fields (HMRF) constitute an elegant way to model the problem of segmentation. This modelling leads to the minimization of an energy function. In this paper we investigate direct search methods that are Nelder-Mead and Torczon methods to solve this optimization problem. The quality of segmentation is evaluated on grou…
Development of a Hybrid Method to Generate Gravito-Inertial Cues for Motion Platforms in Highly Immersive Environments
2021
Motion platforms have been widely used in Virtual Reality (VR) systems for decades to simulate motion in virtual environments, and they have several applications in emerging fields such as driving assistance systems, vehicle automation and road risk management. Currently, the development of new VR immersive systems faces unique challenges to respond to the user’s requirements, such as introducing high-resolution 360° panoramic images and videos. With this type of visual information, it is much more complicated to apply the traditional methods of generating motion cues, since it is generally not possible to calculate the necessary corresponding motion properties that are needed to …
A New SOM Initialization Algorithm for Nonvectorial Data
2008
Self Organizing Maps (SOMs) are widely used mapping and clustering algorithms family. It is also well known that the performances of the maps in terms of quality of result and learning speed are strongly dependent from the neuron weights initialization. This drawback is common to all the SOM algorithms, and critical for a new SOM algorithm, the Median SOM (M-SOM), developed in order to map datasets characterized by a dissimilarity matrix. In this paper an initialization technique of M-SOM is proposed and compared to the initialization techniques proposed in the original paper. The results show that the proposed initialization technique assures faster learning and better performance in terms…
Analysis of Multi-Choice Questionnaires through Self-Organizing Maps
1998
This paper describes how Self-Organizing Maps can be used to analyse multi-choice gallups. In this method, the use of a single SOM for all available data is replaced with the use of multiple SOMs trained with subsets of gallup questions. The subgroupings located from these maps are then used to train a new concluding SOM that is more readable than any single SOM analysis would be.
Stable Automatic Unsupervised Segmentation of Retinal Vessels Using Self-Organizing Maps and a Modified Fuzzy C-Means Clustering
2011
In this paper an automatic unsupervised method for the segmentation of retinal vessels is proposed. Three features are extracted from the tested image. The features are scaled down by a factor of 2 and mapped into a Self-Organizing Map. A modified Fuzzy C-Means clustering algorithm is used to divide the neuron units of the map in 2 classes. The entire image is again input for the Self-Organizing Map and the class of each pixel will be the class of its best matching unit in the Self-Organizing Map. Finally, the vessel network is post-processed using a hill climbing strategy on the connected components of the segmented image. The experimental evaluation on the DRIVE database shows accurate ex…
Automatic Unsupervised Segmentation of Retinal Vessels Using Self-Organizing Maps and K-Means Clustering
2011
In this paper an automatic unsupervised method for the segmentation of retinal vessels is proposed. A Self-Organizing Map is trained on a portion of the same image that is tested and K-means clustering algorithm is used to divide the map units in 2 classes. The entire image is again input for the Self-Organizing Map, and the class of each pixel will be the class of the best matching unit on the Self-Organizing Map. Finally, the vessel network is post-processed using a hill climbing strategy on the connected components of the segmented image. The experimental evaluation on the publicly available DRIVE database shows accurate extraction of vessels network and a good agreement between our segm…
A multiscale approach to automatic and unsupervised retinal vessel segmentation using Self-Organizing Maps
2016
In this paper an automatic unsupervised method for retinal vessel segmentation is described. Self-Organizing Map, modified Fuzzy C-Means, STAPLE algorithms and majority voting strategy were adopted to identify a segmentation of the retinal vessels. The performance of the proposed method was evaluated on the DRIVE database.
Relative Vessel Motion Tracking using Sensor Fusion, Aruco Markers, and MRU Sensors
2017
This paper presents a novel approach for estimating the relative motion between two moving offshore vessels. The method is based on a sensor fusion algorithm including a vision system and two motion reference units (MRUs). The vision system makes use of the open-source computer vision library OpenCV and a cube with Aruco markers placed onto each of the cube sides. The Extended Quaternion Kalman Filter (EQKF) is used for bad pose rejection for the vision system. The presented sensor fusion algorithm is based on the Indirect Feedforward Kalman Filter for error estimation. The system is self-calibrating in the sense that the Aruco cube can be placed in an arbitrary location on the secondary ve…
Cloud motion detection from infrared satellite images
2002
The estimation of cloud motion from a sequence of satellite images can be considered a challenging task due to the complexity of phenomena implied. Being a non-rigid motion and implying non-linear events, most motion models are not suitable and new algorithms have to be developed. We propose a novel technique, combining a Block Matching Algorithm (BMA) and a best candidate block search along with a vector median regularisation.
Display of travelling 3D scenes from single integral-imaging capture
2016
Integral imaging (InI) is a 3D auto-stereoscopic technique that captures and displays 3D images. We present a method for easily projecting the information recorded with this technique by transforming the integral image into a plenoptic image, as well as choosing, at will, the field of view (FOV) and the focused plane of the displayed plenoptic image. Furthermore, with this method we can generate a sequence of images that simulates a camera travelling through the scene from a single integral image. The application of this method permits to improve the quality of 3D display images and videos.