Reducing texture details in images
A method generates an image with de-emphasized textures. Each pixel in the image is classified as either a silhouette edge pixel, a texture edge pixels, or a featureless pixel. A mask image M(x, y) is generated, wherein an intensity of a given pixel (x, y) in the mask image M(x, y) is zero if the pixel (x, y) is classified as the texture edge pixel, is d(x, y) if the pixel (x, y) is classified as the featureless pixel, and is one if the pixel (x, y) is classified as the silhouette edge pixel. An intensity gradient ∇I(x, y) is determined in the masked image, and the intensity gradients in the masked image are integrated according to G(x, y)=∇I(x, y). M(x, y). Then, an output image I′ is generated by minimizing |∇I′−G|, and normalizing the intensities in the output image I′.
1. A method for generating an image with de-emphasized textures, wherein each pixel in the image is classified as a silhouette edge pixel, a texture edge pixels, or a featureless pixel, comprising:
acquiring an image;
generating from the acquired image a mask image M(x, y), wherein an intensity of a given pixel (x, y) in the mask image M(x, y) is zero if the pixel (x, y) is classified as the texture edge pixel, is d(x, y) if the pixel (x, y) is classified as the featureless pixel, and is one if the pixel (x, y) is classified as the silhouette edge pixel;
determining intensity gradient ∇I(x, y) in the masked image;
integrating the intensity gradients in the masked image according to G(x, y)=∇I(x, y).M(x, y);
constructing an output image I′ by minimizing |∇I′−G|; and
normalizing intensities in the output image I′.
2. The method of claim 1 further comprising:
applying a Gaussian filter to boundary pixels of the output image to reduce image artifacts.
3. The method of claim 2 further comprising:
padding each boundary pixels by five pixels before applying the Gaussian filter; and
cropping the padded pixels after applying the Gaussian filter.
4. The method of claim 1 wherein the intensity gradients are integrated separately in each color channel.