| Paper: | IMDSP-P8.6 | ||
| Session: | Image and Multidimensional Signal Processing: Applications I | ||
| Time: | Thursday, May 20, 09:30 - 11:30 | ||
| Presentation: | Poster | ||
| Topic: | Image and Multidimensional Signal Processing: Image Scanning, Display, and Printing | ||
| Title: | BLIND PRIMARY COLORANT SPECTRAL SEPARATION COMBINING ICA AND POCS NON-NEGATIVE MATRIX FACTORIZATION | ||
| Authors: | Chunghui Kuo; NexPress Solutions LLC | ||
| Abstract: | Traditional printing technologies use metamerism to match colorbetween original objects and reproduced images under certainlighting constraints. These techniques become unsatisfactory forapplications demanding high color accuracy where lightingconditions are subject to change, for example, artworkreproduction. Therefore, it is desirable to reproduce the imageusing colorants whose spectrum is closest to the original print.To estimate the original object primary colorant spectrum, wepropose a blind spectral separation algorithm by combiningIndependent Component Analysis, ICA, and Non-NegativeMatrix Factorization, NNMF. Our experimental resultsshow a satisfactory match between the original and the estimatedprimaries' spectrums. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops