Title :
A new method for multi-texture segmentation using neural networks
Author :
de Medeiros Martins, Allan ; de Almeida Filho, Wedson Torres ; Júnior, Agostinho Medeiros Brito ; Neto, Adrião Duarte Dória
fDate :
6/24/1905 12:00:00 AM
Abstract :
A simple method for texture-based segmentation of colored images combining the Hotelling transform and an unsupervised neural network is presented. The method separates the image into n regions representing n possible existing textures. The Hotelling transform is used to improve the color contrast and achieve uncorrelated color components. Auto-contrast is then applied to get a better color spreading. Finally, a set of features extracted from the transformed image is submitted to a competitive neural network for training. Once finished, the neural network parameters are used to label the image regions according to their textures
Keywords :
covariance matrices; eigenvalues and eigenfunctions; feature extraction; image colour analysis; image representation; image segmentation; image texture; neural nets; transforms; Hotelling transform; color contrast; colored images; competitive neural network; covariance matrix; eigenvectors; feature extraction; image representation; image segmentation; image textures; uncorrelated color components; unsupervised neural network; Covariance matrix; Feature extraction; Gray-scale; Image analysis; Image color analysis; Image segmentation; Image texture analysis; Karhunen-Loeve transforms; Neural networks; Pixel;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007459