XDoG: An eXtended difference-of-Gaussians compendium including advanced image stylization

Abstract

Recent extensions to the standard difference-of-Gaussians (DoG) edge detection operator have rendered it less susceptible to noise and increased its aesthetic appeal. Despite these advances, the technical subtleties and stylistic potential of the DoG operator are often overlooked. This paper offers a detailed review of the DoG operator and its extensions, highlighting useful relationships to other image processing techniques. It also presents many new results spanning a variety of styles, including pencil-shading, pastel, hatching, and woodcut. Additionally, we demonstrate a range of subtle artistic effects, such as ghosting, speed-lines, negative edges, indication, and abstraction, all of which are obtained using an extended DoG formulation, or slight modifications thereof. In all cases, the visual quality achieved by the extended DoG operator is comparable to or better than those of systems dedicated to a single style.

User-guided line abstraction using coherence and structure analysis

“…Parametric image filters such as the Canny edge detector [1] and the difference-of-Gaussians filter [2][3][4] are widely used in image abstraction for generating line drawing images. However, the quality of output may vary significantly when adjusting the associated control parameters, leading to either excessive or insufficient details.…”

An Improved Fractional Differential Edge Detection Algorithm

“…Where ( ) v v > , to get more precise edges, the fractional differential mask is twice employed to enhance edge and texture with order 1 v and 2 v respectively, and the subtractive result of the two enhanced image is the edge of the image, and the process can be expressed as the following formula.…”

“…Edge detection is not only the basic problem of image processing, but also an important part of computer recognition and understanding. It plays an important role in human and computer vision [1] [2].…”

“…The difference of Gaussians (DoG) operator with strong robustness for noise is mentioned by Lowe has been shown to yield aesthetically pleasing edge lines without postprocessing [3]. The XDoG(eXtended Difference of Gaussians) operator presented by Winnem¨oller Obtains a range of subtle artistic effects, such as ghosting, speed-lines, negative edges, indication, and abstraction [1] [4]. SUSAN (Small Univalue Segment Assimilating Nucleus) operator based on local gray level difference with strong robustness for noise is an acronym standing for smallest univalue segment assimilating nucleus.…”

Special section on the 2011 joint symposium on computational aesthetics (CAe), non-photorealistic animation and rendering (NPAR), and sketch-based interfaces and modeling (SBIM)

“…The first paper "XDoG: An eXtended Difference-of-Gaussians Compendium including Advanced Image Stylization" [6] responds to the growing volume of the NPR literature adopting edge enhancing filtering operators to emphasize and stylize edges to create a variety of artistic effects in images. For the first time, the paper draws together the many works in this area to present both a comprehensive overview of these techniques, and a new formulation of edge enhancing filtering-the extended Difference of Gaussian (XDoG).…”