Answers are grounded in this paper and cite their sources.
We propose a non-photorealistic rendering method that converts photographic images into Yin-Yang-pattern-like images represented by smooth curved black and white areas. The proposed method applies two Gaussian filters with different parameter values (Difference of Gaussian: DoG) to photographic images, calculates the difference between the two smoothed images, and adds the difference to photographic images. By repeating the process, Yin-Yang-pattern-like images are generated. In order to verify the effectiveness of the proposed method, we performed an experiment using Lenna image, and visually confirmed the changes Yin-Yang-pattern-like images generated when the values of the various parameters were changed. In addition, we performed an experiment using various photographic images.
No takes yet. Share an insight, caveat, or question.
Toru Hiraoka (2021) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: