Inpainting by Modified Lattice Boltzmann Method and Exemplar Method for Object Removal in Colour Images

In this paper we use image inpainting technique in colour images. Inpainting is a technique in which, a
missing area or pixels are replaced by adequate neighbouring pixels so that the resultant image
obtained will look as no defect is there. In this paper we have removed an object from the colour
image and the vacant pixels are filled with the help of the surrounding neighbouring pixels. Two
techniques are used here for removing and inpainting an object from the still colour image, Modified
Lattice Boltzmann Method and Exemplar Method. Existing Exemplar Method of inpainting is used to
compare the results of Modified Lattice Boltzmann Method. The Lattice Boltzmann Equation from fluid
dynamics it modified to use for inpainting. Peak Signal to Noise Ratio, Self-SIMilarity Index and
execution time of the image is calculated for both inpainting techniques. From the objective analysis, it
is found that the proposed Modified Lattice Boltzmann method of inpainting gives a better inpainted
result.