Title :
Application of recurrent neural network for multi-step full-color image segmentation
Author :
Nemirovskiy, V.B. ; Stoyanov, A.K.
Author_Institution :
Tomsk Polytech. Univ., Tomsk, Russia
fDate :
June 28 2013-July 1 2013
Abstract :
Possibility of application of a recurrent neural network for segmentation of full-color images based on a clustering of color components is considered. Questions of multi-step segmentation of such images in different color models are discussed. Experimental results on multi-step segmentation of images are presented in the RGB and YUV color spaces.
Keywords :
image colour analysis; image segmentation; pattern clustering; recurrent neural nets; RGE color spaces; YUV color spaces; color components clustering; color models; multistep full-color image segmentation; recurrent neural network; Brightness; Entropy; Image color analysis; Image segmentation; Image; RGB; YUV; clustering; color space; pixel; point map; recurrent neural network; segmentation;
Conference_Titel :
Strategic Technology (IFOST), 2013 8th International Forum on
Conference_Location :
Ulaanbaatar
Print_ISBN :
978-1-4799-0931-5
DOI :
10.1109/IFOST.2013.6616891
