Color image quantization using flower pollination algorithm
- PDF / 6,660,966 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 60 Downloads / 240 Views
Color image quantization using flower pollination algorithm Mengyi Lei 1,2 & Yongquan Zhou 1,2 & Qifang Luo 1,2 Received: 4 October 2019 / Revised: 13 August 2020 / Accepted: 20 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Flower pollination algorithm (FPA) is a swarm-based optimization technique that has attracted the attention of many researchers in several optimization fields due to its impressive characteristics. This paper proposes a new application for FPA in the field of image processing to solve the color quantization problem, which is use the mean square error is selected as the objective function of the optimization color quantization problem to be solved. By comparing with the K-means and other swarm intelligence techniques, the proposed FPA for Color Image Quantization algorithm is verified. Computational results show that the proposed method can generate a quantized image with low computational cost. Moreover, the quality of the image generated is better than that of the images obtained by six well-known color quantization methods. Keywords Flower pollination algorithm . Color image quantization . Metaheuristic algorithm
1 Introduction With the rapid development of computer hardware and software, high-quality images can be easily displayed and stored. Electronic documents include many images that must be stored, transmitted and displayed. Current devices can display high quality images with many colors. Nevertheless, the quality of the image is a disadvantage for its storage and transmission, since more colors means more quality, but also implies more storage space and slower speed of transmission. Reducing the colors of an image not only allows it to be displayed on low-end devices, but also reduces the size of the image and this allows it to be stored and transmitted more efficiently. However, these high-quality images may contain a large amount of
* Yongquan Zhou [email protected]
1
College of Artificial Intelligence, Guangxi University for Nationalities, Nanning 530006, China
2
Key Laboratories of Guangxi High Schools Complex System and Computational Intelligence, Nanning 530006 Guangxi, China
Multimedia Tools and Applications
information, which leads to problems such as increased transmission time and increased storage space requirements. In order to avoid these problems, we should try to eliminate some unnecessary information in the image before transferring the image. Color image color quantization is one of the common image processing techniques, which is a process of reducing the number of colors in color images and reducing distortion [7, 25, 29]. The main purpose of color quantization is to reduce the number of image colors while retaining important information and reducing the image transmission time [2, 3, 8, 9, 31]. Color image quantization generally consists of two stages. The first stage is a palette design, which selecting the appropriate number of colors, usually 8–256 colors [32, 34]; the second stage is pixel mapping, which
Data Loading...
