Contrast Preserving Decolorization

Cewu Lu          Li Xu           Jiaya Jia

Abstract

Converting color images into grayscale ones suffer from information loss. In the meantime, it is one fundamental tool indispensable for single channel image processing, digital printing, and monotone e-ink display given color inputs. In this paper, we propose an optimization framework aiming at maximally preserving color contrast. Our main contribution is threefold. First, we propose a novel framework employing a bimodal objective function to alleviate the restrictive order constraint for color mapping. Second, we develop an efficient solver that allows for automatic selection of suitable grayscales based on global contrast constraints. Third, we advocate a perceptual-based metric to measure contrast loss, as well as content preservation, in the produced grayscale images. It is among the first attempts in this field to quantitatively evaluate decolorization results.


 

Downloads

Snapshot for paper "Contrast Preserving Decolorization with Perception-Based Quality Metrics"
Cewu Lu, Li Xu, Jiaya Jia
International Journal of Computer Vision (IJCV), 2014

   [Paper (pdf, 5MB)]

  [Metric Code (CCPR, CCFR and E-score)]

  [COLOR250 Dataset (181MB)]

Snapshot for paper "Contrast Preserving Decolorization"
Cewu Lu, Li Xu, Jiaya Jia
IEEE International Conference on Computational Photography (ICCP), 2012

   [Paper (pdf, 4.9MB)]

  [Matlab Code (zip, 500k)] (upon request)

  [Presentation Slides]


 

Printing Effect

Input Picture

HP Printed Picture

Printed picture using our technique

 

Kindle Display Effect

Input Picture

Kindle display

Kindle display using our technique

 

More Examples and Comparisons

Input Picture

Photoshop CS5

IrfanView

Ours

Input Picture

Photoshop CS5

IrfanView

Ours

Input Picture

Photoshop CS5

IrfanView

Ours

Input Picture

Photoshop CS5

IrfanView

Ours

Input Picture

Photoshop CS5

IrfanView

Ours

Input Picture

Photoshop CS5

IrfanView

Ours

Input Picture

Photoshop CS5

IrfanView

Ours



Related Projects