Proceedings ArticleDOI
Color image segmentation by supervised pixel classification in a color texture feature space. Application to soccer image segmentation
Nicolas Vandenbroucke,Ludovic Macaire,J.-G. Postaire +2 more
- Vol. 3, pp 621-624
TLDR
An approach to color image segmentation which is considered as a supervised pixel classification problem which determines the most discriminating color texture features among a multidimensional set of color texture Features by means of an iterative feature selection procedure associated to an information criterion.Abstract:
We describe an approach to color image segmentation which is considered as a supervised pixel classification problem. The pixel classification algorithm analyses the color texture features, that is to say the texture features which are computed by tacking into account the color components of the neighbor pixels. We determine the most discriminating color texture features among a multidimensional set of color texture features by means of an iterative feature selection procedure associated to an information criterion. We successfully apply our approach to soccer image segmentation.read more
Citations
More filters
Journal ArticleDOI
Color clustering and learning for image segmentation based on neural networks
TL;DR: The experimental results show that the proposed image segmentation system has the desired ability for the segmentation of color image in a variety of vision tasks.
Journal ArticleDOI
A markov random field image segmentation model for color textured images
Zoltan Kato,Ting-Chuen Pong +1 more
TL;DR: A Markov random field image segmentation model, which aims at combining color and texture features through Bayesian estimation via combinatorial optimization (simulated annealing), and a parameter estimation method using the EM algorithm is proposed.
Journal ArticleDOI
Color image segmentation by pixel classification in an adapted hybrid color space: application to soccer image analysis
TL;DR: An original approach in order to improve the results of color image segmentation by pixel classification by classify pixels represented in the hybrid color space which is specifically designed to yield the best discrimination between the pixel classes.
Proceedings ArticleDOI
Haralick feature extraction from LBP images for color texture classification
TL;DR: A new approach for color texture classification by use of Haralick features extracted from co-occurrence matrices computed from local binary pattern (LBP) images, with a satisfying rate of well-classified images.
Book
Markov Random Fields in Image Segmentation
Zoltan Kato,Josiane Zerubia +1 more
TL;DR: The primary goal of this monograph is to demonstrate the basic steps to construct an easily applicable MRF segmentation model and further develop its multi-scale and hierarchical implementations as well as their combination in a multilayer model.
References
More filters
Journal ArticleDOI
Picture segmentation using a recursive region splitting method
TL;DR: A general segmentation method which can be applied to many different types of scenes and the potential performance of other segmentation techniques on general scenes is discussed.
Journal ArticleDOI
Digital color imaging
Gaurav Sharma,H.J. Trussell +1 more
TL;DR: Fundamental concepts of color perception and measurement are first presented using vector-space notation and terminology in order to establish the background and lay down terminology.
Journal ArticleDOI
Digital Color Imaging
Gaurav Sharma,H. Joel Trussell +1 more
TL;DR: A survey of color imaging can be found in this article, where the fundamental concepts of color perception and measurement are first presented us-ing vector-space notation and terminology, along with common mathematical models used for representing these devices.
Proceedings ArticleDOI
Color pixels classification in an hybrid color space
TL;DR: A new approach for color image segmentation is described which is considered as a problem of pixels classification, and the algorithm is applied to classify pixels of soccer color images in order to recognize the team of players.
Proceedings ArticleDOI
Soccer image sequence computed by a virtual camera
TL;DR: An image synthesis system is developed that generates an image sequence from the viewpoint of a player on the field that determines the camera parameters of a TV image and extracts players from each image and estimates their positons in the world coordinate system.