EE 362 Final Project

Color Balancing:

The Battle of the Algorithms

Laura Diaz

 Jessica Heyman

Gustav Rydbeck

Background

Algorithms

Test Images

Testing Interface

Image Comparison
Methods

Results

Conclusion

Possible Extensions

References

Appendix I

Appendix II

Introduction

Color balancing is an important consideration in digital photography and imaging.  The process of color balancing includes trying to determine what the illuminant of a particular scene is and then adjusting the intensities of the red, green, and blue channel of the image in order to recover the original color characteristics of the scene.  Since for most images, we can not accurately determine the scene illuminant, we considered five basic algorithms and variants of those algorithms to color balance an image when the illuminant and scene information is unknown.  We color balanced a wide range of images using the algorithms to try to determine which algorithms performed best for various images types. We also tried to find the conditions under which the various algorithms failed.  To compare algorithm performance, we used both mathematical and subjective comparisons of the resulting color-balanced images.