Altun, HalisSinekli, RecaiTekbas, UgurKarakaya, FuatPeker, Murat2024-11-072024-11-072011978-161284919-5https://doi.org/10.1109/INISTA.2011.5946088https://hdl.handle.net/11480/10982TUBITAK; IEEE2011 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2011 -- 15 June 2011 through 18 June 2011 -- Istanbul-Kadikoy -- 85879Color detection is generally a primary stage in most of the image processing application, if the application is based on the color information, such as road sign detection, face detection, skin color detection, object detection and object tracking etc. As the performance of subsequent modules in an image processing application is adversely affected by the previous modules, the accuracy of color detection with a high performance inevitably becomes crucial in some applications. This paper introduces a method for an efficient color detection in RGB space using an ensemble of experts in hierarchical structure. In this structure, a set of experts is assigned to evaluate R, G, B components of a pixel and then constructs a degree of membership to the set of predefined class of colors for the given pixel. Then a master neural network constructs its final decision based on the membership probabilities provided by the set of experts. Qualitative and quantitative evaluations of the results show that the proposed hierarchical structure of neural networks is superior over the conventional neural network classifier in color detection. © 2011 IEEE.eninfo:eu-repo/semantics/closedAccessColor DetectionNeural NetworkSegmentationConference Object15415810.1109/INISTA.2011.59460882-s2.0-79961205068N/A