I want to use color information for using traffic sign recognation. But the color effected from illumination for example red color looks like black color. I think maybe color normalization help me. what can ı do?
Illumination is quite a common problem in image processing. Images will almost always be taken under different lightning. The most common solution is to use a different color model that includes a dimension for lightning like HSL.
http://en.wikipedia.org/wiki/HSL_and_HSV
Your question is not very clearly formulated. However, you need to consider both the illumination of the signs as as well as the way they are presented to your test subjects. Is it on a screen? Is the screen calibrated? Are the signs retro-reflecting? Then the illumination needs to be directed from a place near the observer/camera.
If I'm reading your question right, you're interested in what color different signs appear when illuminated using illuminants which have vastly different colors; the example is that a red stop sign will appear dark when illuminated using a source which is predominantly blue.
The traditional way to transform between different illuminations is to use the von Kries transform. It models the way human eyes respond to different illuminations. It's not perfect (human vision is complicated, and color spaces usually use three values to approximate the spectrum!), but it will get you close. [Hint: when you're transforming the colors, remember to convert your pixel values from sRGB to linear RGB first.]
Bruce Lindbloom (linked below) has great information about the von Kries transform and color adaptation when viewing scenes under different illuminations.
https://en.wikipedia.org/wiki/Von_Kries_Coefficient_Law
http://www.brucelindbloom.com/index.html?Eqn_ChromAdapt.html
- Badges
- Science topic