Rotation-Invariant Texture Analysis and Classification by Artificial Neural Networks and Wavelet Transform

Autor:	HAŞİLOĞLU, Abdulsamet
Jazyk:	turečtina
Rok vydání:	2014
Předmět:	Computer Science::Graphics Computer Science::Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Texture Wavelet transform Artificial neural networks Classification ComputingMethodologies_COMPUTERGRAPHICS
Zdroj:	Volume: 25, Issue: 5 405-413 Turkish Journal of Engineering and Environmental Sciences
ISSN:	1300-0160 1303-6157
Popis:	A large number of approaches for texture analysis have been suggested for the purpose of texture classification. Recently, wavelet frames were proposed for texture features extraction. In this study, non-subsampled wavelet frame transform was used for feature extraction of 16 textures from a set of Brodatz' album by means of various wavelet families. Texture classification was accomplished by artificial neural network with a fast adaptive backpropagation algorithm. A new pyramidal-windowing algorithm is proposed, which forms randomly rotated texture windows of variable sizes texture windows for training a neural networks classifier, and perfect classification results were obtained.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=tubitakulakb::fa9f9a04b1b1a44d9652835389321d55 https://dergipark.org.tr/tr/pub/tbtkengineering/issue/12179/145306 Zobrazit plný text záznamu