Please use this identifier to cite or link to this item:
Title: Use of transformed reflectance functions for neural network color match prediction systems
Authors: Ameri, F
Moradian, S
Tehran, M Amani
Faez, K
Keywords: Color match prediction;Matrix R;Neural networks;Transformed reflectance functions;Wool
Issue Date: Sep-2006
Publisher: NISCAIR-CSIR, India
IPC Code: Int. Cl.8 G06N3/02
Abstract: Attempts have been made to use different transformed reflectance functions as input for a fixed genetically optimized neural network match prediction system. Two different sets of data depicting dyed samples of known recipes but metameric to each other were used to train and test the network. All the transformed and untransformed reflectance functions gave good recipe predictions when trained and tested by the same data sets (PF/4 being less than 4). However, the transformation based on matrix R of the decomposition theory showed promising results, since it gave very good colorant concentration predictions when trained by the first set of data dyed with one set of colorants while being tested by a completely different second set of data dyed with a different set of colorants (PF/4 always being less than 10).
Page(s): 439-443
ISSN: 0975-1025 (Online); 0971-0426 (Print)
Appears in Collections:IJFTR Vol.31(3) [September 2006]

Files in This Item:
File Description SizeFormat 
IJFTR 31(3) 439-443.pdf1.04 MBAdobe PDFView/Open

Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.