Search results for "segmentation"
showing 10 items of 674 documents
Fuzzy Distributed Genetic Approaches for Image Segmentation
2010
This paper presents a new image segmentation algorithm (called FDGA-Seg) based on a combination of fuzzy logic, multiagent systems and genetic algorithms. We propose to use a fuzzy representation of the image site labels by introducing some imprecision in the gray tones values. The distributivity of FDGA-Seg comes from the fact that it is designed around a MultiAgent System (MAS) working with two different architectures based on the master-slave and island models. A rich set of experimental segmentation results given by FDGA-Seg is discussed and compared to the ICM results in the last section.
Statistical Shape and Probability Prior Model for Automatic Prostate Segmentation
2011
International audience; Accurate prostate segmentation in Trans Rectal Ultra Sound (TRUS) images is an important step in different clinical applications. However, the development of computer aided automatic prostate segmentation in TRUS images is a challenging task due to low contrast, heterogeneous intensity distribution inside the prostate region, imaging artifacts like shadow, and speckle. Significant variations in prostate shape, size and contrast between the datasets pose further challenges to achieve an accurate segmentation. In this paper we propose to use graph cuts in a Bayesian framework for automatic initialization and propagate multiple mean parametric models derived from princi…
MRF Model-Based Approach for Image Segmentation Using a Chaotic MultiAgent System
2006
In this paper, we propose a new Chaotic MultiAgent System (CMAS) for image segmentation. This CMAS is a distributed system composed of a set of segmentation agents connected to a coordinator agent. Each segmentation agent performs Iterated Conditional Modes (ICM) starting from its own initial image created initially from the observed one by using a chaotic mapping. However, the coordinator agent receives and diversifies these images using a crossover and a chaotic mutation. A chaotic system is successfully used in order to benefit from the special chaotic characteristic features such as ergodic property, stochastic aspect and dependence on initialization. The efficiency of our approach is s…
Bollard Segmentation and Position Estimation From Lidar Point Cloud for Autonomous Mooring
2022
This article presents a computer-aided object detection and localization method from lidar 3-D point cloud data. This topic of interest is in the framework of autonomous mooring, where the ship is tied to the rigid structure on-shore (bollard) for autonomous maritime navigation. Using shape and features priors, unlike matching the whole object template to the experimental 3-D point cloud representation of the scene, two customized algorithms: 1) 3-D feature matching (3-DFM) and 2) mixed feature-correspondence matching (MFCM) are presented. The proposed algorithms discriminate and extract the 3-D points corresponding to the noncooperative bollard's surface from the background, thus capable o…
A stochastic shape and orientation model for fibres with an application to carbon nanotubes
2012
Methods are introduced for analysing the shape and orientation of planar fibres from greyscale images of fibrous systems. The sequence of image processing techniques needed for segmentation of fibres is described. The identified fibres were interpreted as deformed line segments for which two shape and two orientation parameters are estimated by the maximum likelihood method. The methods introduced are shown to perform quite well for simulated systems of deformed line segments with known properties. They were applied to TEM images of carbon nanotubes embedded in polycarbonate.
Routing Design in Wireless Sensor Networks and a Solution for Healthcare Environments
2011
This work presents the software implementation of a tissue engineering image analysis tool through the study of several biomaterials by means of different microscopy techniques (optical, scanning electron, and atomic force microscopy). With this tool, different quantitative information has been extracted from the microscopy image analysis of these biomaterials, as the number of objects, their mean size and the area they cover. Morphological characteristics, as the roundness or the porosity have been also obtained. All these quantitative information has permitted an statistical analysis over the obtained results.
Reliability of manual segmentation of cornea, contact lens and tear film using a high-resolution OCT
2015
In this study, we aimed to evaluate the intra/inter-session and intra/inter-observer variability of manual segmentation of thickness of the pre-lens tear film, contact lens (CL), post-lens tear film, epithelium, bowman’s layer, stroma and the whole cornea and CLs with a flat and a steep fit, using a commercial high-resolution spectral domain optical coherence tomographer (OCT). Two different observers obtained three repeated measures in two separate sessions. A high correlation was found between the values obtained by the two different observers, except for the thinner layers, epithelium, and Bowman’s layer. Inter-observer analysis showed a high consistency in the measurements obtained by b…
Snapshot RGB mapping of skin melanin and hemoglobin.
2015
The concept of snapshot red-green-blue (RGB) multispectral imaging was applied for skin chromophore mapping. Three monochromatic spectral images have been extracted from a single RGB image dataset at simultaneous illumination of skin by 473-, 532-, and 659-nm laser lines. The spectral images were further transformed into distribution maps of skin melanin, oxyhemoglobin, and deoxyhemoglobin, related to pigmented and vascular skin malformations. The performance and clinical potential of the proposed technique are discussed
An automated procedure for computing the packing properties of dense and locked sands by image analysis of thin sections
2014
The macroscopic mechanical behaviour of dense sands originates to a great extent from their microstructural characteristics such as the coordination number, the grain contact and the packing density indexes. The study of intergranular contacts and the reckoning of these indexes may be carried out on planar images of the grains either by means of time-consuming visual inspection assisted by CAD or by automatic image analysis. An innovative method for the automatic determination of microstructural characteristics of sands based on image analysis of thin section is proposed. Tests performed on a locked sand show that the proposed method is much more effective, convenient and faster than the us…
Constrained Clusterwise Linear Regression
2005
In market segmentation, Conjoint Analysis is often used to estimate the importance of a product attributes at the level of each single customer, clustering, successively, the customers whose behavior can be considered similar. The preference model parameter estimation is made considering data (usually opinions) of a single customer at a time, but these data are usually very few as each customer is called to express his opinion about a small number of different products (in order to simplify his/her work). In the present paper a Constrained Clusterwise Linear Regression algorithm is presented, that allows simultaneously to estimate parameters and to cluster customers, using, for the estimati…