Color correction through region matching leveraged by point correspondences

This paper addresses the problem of region-based color correction. Our solution begins with the image segmentation by marker-controlled watershed transformation, which is faster and produces more uniform regions with better adherence to object boundaries than the segmentation in previous works. Next, regions between two images are matched using point feature correspondences which are invariant to geometric transformation and illumination changes. Finally, the color-corrected image is generated from the color transfer functions of corresponding regions. We demonstrate the results of this approach using different sets of images.