Moment-based texture segmentation
Pattern Recognition Letters
Unsupervised Texture Segmentation in a Deterministic Annealing Framework
IEEE Transactions on Pattern Analysis and Machine Intelligence
Filtering for Texture Classification: A Comparative Study
IEEE Transactions on Pattern Analysis and Machine Intelligence
Contour and Texture Analysis for Image Segmentation
International Journal of Computer Vision
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Efficient computation of local geometric moments
IEEE Transactions on Image Processing
Intravascular Ultrasound Tissue Characterization with Sub-class Error-Correcting Output Codes
Journal of Signal Processing Systems
FIMH '09 Proceedings of the 5th International Conference on Functional Imaging and Modeling of the Heart
AdaBoost-based approach for detecting lithiasis and polyps in USG images of the gallbladder
IVIC'11 Proceedings of the Second international conference on Visual informatics: sustaining research and innovations - Volume Part I
In-Vivo IVUS tissue classification: a comparison between RF signal analysis and reconstructed images
CIARP'06 Proceedings of the 11th Iberoamerican conference on Progress in Pattern Recognition, Image Analysis and Applications
Extraction of left ventricle borders with local and global priors from echocardiograms
Machine Vision and Applications
Hi-index | 0.00 |
This paper presents a method for accurate location of the vessel borders based on boosting of classifiers and feature selection. Intravascular Ultrasound Images (IVUS) are an excellent tool for direct visualization of vascular pathologies and evaluation of the lumen and plaque in coronary arteries. Nowadays, the most common methods to separate the tissue from the lumen are based on gray levels providing non-satisfactory segmentations. In this paper, we propose and analyze a new approach to separate tissue from lumen based on an ensemble method for classification and feature selection. We perform a supervised learning of local texture patterns of the plaque and lumen regions and build a large feature space using different texture extractors. A classifier is constructed by selecting a small number of important features using AdaBoost. Feature selection is achieved by a modification of the AdaBoost. A snake is set to deform to achieve continuity on the classified image. Different tests on medical images show the advantages.