Study Of The Extraction Of Line Drawings And Style Conversion Method

With the rapid development of computer graphics, the graphics with the goal of non-photorealistic rendering is coming to attach more and more importance. Non-photorealistic rendering technique is a brand new and an animate branch of computer graphics. As an effective tool for abstract shape visualization, line drawing falls squarely within the scope of non photorealistic rendering. For its special performance and abstraction used in art creation, cartoon making and advertisement Line drawing is a simple yet effective means of visual communication and also a mean to express the Subjective feelings of the author. A good piece of line art, sketch, or technical illustration typically consists of a small number of lines, describing the identifying characteristics of objects, that is, shapes. Line drawing is a simple yet effective means of visual communication. This enables quick recognition and appreciation of the subject with little distraction from relatively unimportant contents. Also, line-based object representation can provide significant gain, both in terms of time and storage space, in subsequent processing of the data.To accomplish non-photorealistic pictures, researchers have studied and found many effective methods. Line drawings abstraction and style transformation have been a hotspot in NPR area. This paper focus on how to abstract, scalable and style translation of line drawing from 2D images. As the multiplicity and complexity of art forms, we could easily solve the reusing and adjusting the style problem if we have a reasonable model to represent the style numerically.In this paper, we present an automatic 2D line-drawing generation framework. Our overall framework consists of three modules: line extraction, line rendering and style transform. In the first part, we proposed two methods to get the contents of the input image: one is based on morphology thinning, in which we give an accelerated algorithm for morphology thinning. The other one is based on edge detection information. In second part, it assembles the discrete pixels into stroke paths. Then considers the feature scale with which the level-of-detail of lines is controlled in the rendering. In the last part, the new method of style transformation for line drawings based on planar shape evolution. With the formally representation of the line drawings, it presents a more flexible technique to adjust the styles of line drawings. It generates exaggerated-style line drawings. Experimental results show that our technique can generate vivid line drawings from images.This paper we try to solve how to get scalable line drawings from 2D image. Based on these work, we can research the style translation and customization for line drawings from example learning and also can research the model and method of other art forms. To further implement the transformation from realistic photos to NPR pictures.