Evolutionary image vectorization with variable curve number
Open Access
- 14 July 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2083-2086
Abstract
Vector and raster graphics are the two main types of 2D graphics. Raster graphics operate images consisting of pixels (dots); vector images are created using mathematical objects such as lines, curves, and shapes. The main advantage of vector graphics is that it can be scaled without loss of quality, which is useful for advertising, design, frontend development, and other fields of application. At the moment, the issue of vectorization (conversion from raster to vector graphics) has not been fully resolved. Existing approaches are not able to work with a color gradient and they have other disadvantages, such as artifacts, inaccurate result correspondence to the original raster image, and extremely long processing time. To solve these problems, we propose an evolutionary algorithm for image vectorization. The main idea of our approach is to iteratively improve vector images using mutations and crossovers. The algorithm itself does not require any parameters, such as curve number, other than the original image, which makes it universal. The results of comparison with existing solutions show that our algorithm qualitatively and quickly vectorizes images, outperforms others in terms of pixel-by-pixel MSE by 15% and does not generate unnecessary shapes in the resulting vector image.Keywords
This publication has 13 references indexed in Scilit:
- Towards Layer-wise Image Vectorization2022
- P-clothACM Transactions on Graphics, 2020
- A differential evolution algorithm with intersect mutation operatorApplied Soft Computing, 2013
- High-performance software rasterization on GPUs2011
- Adaptive Fitness Function for Evolutionary Algorithm and Its Applications2008
- Scalable vector graphicsIEEE MultiMedia, 2003
- From Raster to Vectors: Extracting Visual Information from Line DrawingsPattern Analysis and Applications, 1999
- Sparse pixel vectorization: an algorithm and its performance evaluationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
- GENETIC ALGORITHM WITH ELITIST MODEL AND ITS CONVERGENCEInternational Journal of Pattern Recognition and Artificial Intelligence, 1996
- Adapting Crossover in Evolutionary Algorithms1995