Drawing the real

In this paper we present an algorithm to automatically produce artistic drawings from stereo image pairs. The input to the algorithm is a natural scene, along with a user-defined set of parameters that define the tone and stylistic properties of the image to be produced. The stereo analysis yields a depth map that is used to preserve the perspective perception of the stylized image. In the next step, we perform a local image contrast enhancement, which is driven by the color segmentation result of the original image. We then draw each stroke in a direction determined by the stereoderived disparity layers, with the stroke density and distribution derived from a Poisson disc distribution. To outline important features in the image, we utilize the contour edges provided by an Edge Combination image. The output of the algorithm is a drawn-like form of the original scene, with objects highlighted by their dominant edges.

• Type: Conference
• Year: 2005
• Where: GRAPHITE
• Authors: Danijela Markovic, Margrit Gelautz
• Keywords: GRAPHITE 2005, Image, Image Contrast Enhancement, Stereo Image Pairs