Compensation

Several commercial programs equipped with toolboxes for image registration, correction, and retouching are available now (for example, Adobe Photoshop, Correl Draw, Paintshop Pro, and some others). However, retouching triple images from the particular collection by standard tools meets some difficulties condi-tioned by

1) the great number of images;

2) the variety of defect appearance;

3) standard tools do not use the peculiarities of the triple color images.

Two different classes of correcting techniques should be outlined. Techniques of the first class should be applied in case when restoration of lost fragments in one of the triplet images is possible using information from correspondent regions in other images of the triplet. Methods of the second class (image inpainting methods) are necessary in cases when the image fragments are lost in all of the images composing a triplet.

The following procedure for correction of local defects is developed.

1. The first object corresponding to defect region is found in the mask image obtained for one of the color components.

2. The mean grayscale value in the neighborhood of the defect region in the color component image is calculated.

3. Using the mask, the corresponding fragments in other color components are found. Grayscale values of reconstructed pixels in the damaged fragment are calculated taking into account the mean intensity value in the neighboring region.

4. The object corresponding to the restored region is removed from the mask.

5. The steps 1-4 are repeated till all of the detected defect regions are restored.

6. The next mask is taken, and steps 1-5 are repeated.

The flowchart of the detection procedure:

here, w is a correcting function (see References).