Flow-guided sketch and accentuated-tone adjusting for pencil drawing generation

Ruirui Li; Lei Yang; Wei Hu

doi:10.1117/12.2282827

21 July 2017 Flow-guided sketch and accentuated-tone adjusting for pencil drawing generation

Ruirui Li, Lei Yang, Wei Hu

Proceedings Volume 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017); 104204E (2017) https://doi.org/10.1117/12.2282827
Event: Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, Hong Kong, China

Abstract

Pencil drawing is an important artistic style which is widely used in draft sketch and finished rendering. It is non-trivial if we can automatically generate the pencil drawing more precisely in order to ease the human efforts. In this paper, we propose flow-guided sketch and accentuated-tone adjusting techniques to transform the pencil drawing from natural images. This work is extended from the existing pencil drawing framework where authors combine sketch and tone together for penciling purpose. Through an edge tangent flow guided classification and convolution, we can obtain more coherent and smooth strokes, especially for portraits. In addition, we also introduce a hierarchical approach to generate strokes. According to saliency map, we can adjust the tone of images automatically. The experimental results indicate the generated toned pencil drawings by our approach are of fewer artifacts and could even solve the images with dark background

Citation Download Citation

Ruirui Li, Lei Yang, and Wei Hu "Flow-guided sketch and accentuated-tone adjusting for pencil drawing generation", Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104204E (21 July 2017); https://doi.org/10.1117/12.2282827

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available