Title: Modelling and generating abstract images of Paul Klee style

Authors: Hanqing Zhao; Kang Zhang

Addresses: School of Computer Software, Tianjin University, Tianjin 300072, China ' Department of Computer Science, The University of Texas at Dallas, Richardson, TX 75080, USA

Abstract: This paper presents our recent work on automatically generating Paul Klee style of abstract paintings. Based on Klee's Pedagogical Sketchbook and our own understanding and observation, we analyse Klee's paintings made in his final few years. The generation process is described in details and sample generated images styled on two of Paul Klee's paintings are also demonstrated. Having analysed the colour and composition of Klee's paintings, we can randomly adjust the parameters to present results with unique compositions and palettes. We also propose a workflow of generating abstract paintings. This framework helps developing a paradigm for abstract image generation process. Our approach is also highly scalable.

Keywords: abstract painting; generative art; new media art.

DOI: 10.1504/IJART.2019.103490

International Journal of Arts and Technology, 2019 Vol.11 No.4, pp.380 - 392

Received: 30 Nov 2018
Accepted: 12 Jun 2019
Published online: 06 Nov 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article