•  
  •  
 

Abstract

It is a new digital process inspired by the pointillist technique of artist Georges Seurat and seeks to recreate Impressionist paintings in digital form in record time, as opposed to the long duration needed to create a painting by hand. The proposed algorithm breaks down the original image into the components of primary colors with the help of the Self-Organizing Maps algorithm. It's like how Seurat mixed his colours, which, when viewed from afar, creates a complete picture from small dots of color. The methodology has a number of technical improvements, such as a halo effect around the main components of the painting, Kirsch filters to determine the edges with the highest precision, the use of HSV color space to fine-tune the color gradations and the utilization of Gaussian functions to enhance the distribution of dots in space. The high efficiency of the proposed methodology was proved by experimental results in which PSNR values of 35.1, 33.0 and 32.4 dB were achieved with the help of the color palettes of 72, 24 and 16 colors, respectively. The processing time of the methodology was also significantly lower as compared to the conventional processes. Such a method opens new opportunities in digital art, providing viable solutions to the automation of the process of creating art at the same time as maintaining the aesthetic qualities of the products of handiwork. It might also benefit AI-driven image processing methods, especially in the area of preserving the artistic heritage and the creation of artistic content.

Keywords

Edge detection, Histogram equalization, Pointillism, PSNR, Self organizing map SOM, Unsupervised machine learning

Subject Area

Computer Science

Article Type

Article

First Page

1675

Last Page

1693

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download

Share

 
COinS