A Novel Pencil Drawing Algorithm Based on Non-Symmetry and Anti-Packing Pattern Representation Model

The artistic stylization transformation of images is an important part in the research of Non-Photorealistic Rendering (NPR). This kind of non-realistic stylized research has a very strong realistic romantic temperament and it can express the artistic pursuit of researchers very well. It is a good example of practical application combining computer science and art. In the technology of image style conversion, the simulation of the realistic art style includes mainly cartoon style, oil painting style, ink painting style and pencil drawing style. Previously, some researchers proposed a style conversion method based on the prior knowledge that there might be crosses at the junction of two lines where the tone distribution has a certain rule. However, in this paper, we have focused on the use of an edge extraction algorithm based on Non-symmetry and Anti-packing pattern representation Model (NAM) to enhance the pencil strokes and highlight the details of the image. Then, by combining the line pencil strokes with the tone drawing, we can transform the image into an image with pencil sketch style. Finally, compared with the most important previous methods, the experimental results presented in this paper showed that our proposed method showed more clearly the scene and the content and more details of the image than the previous methods. We also verified our method and calculated Structural Similarity (SSIM) and Peak Signal-to-Noise Ratio (PSNR) of original images and color pencil drawings with different algorithms on the 7 nature images and the BSDS500 data set.