An Improved Algorithm of Parameter Kernel Cutting Based on Complex Fusion Image

DOI

10.2991/mbdasm-19.2019.4How to use a DOI?

Keywords

image segmentation; energy function; parameter kernel segmentation; edge detection

Abstract

Aiming at the problem that the color image with more detailed textures is not highly segmented in the image segmentation process, a PKGC image segmentation method based on improved edge detection difference ratio is proposed. The method first constructs an energy function by using a parametric kernel graph cutting algorithm. Then, the value of the three-channel RGB edge detection ratio of the color image is used to change the constant balance factor in the energy function to change the ratio of the data item and the boundary smoothing term in the energy function, so that the image segmentation effect is optimal. The segmentation results of different experimental show that the improved paper method has better segmentation precision and better segmentation of texture details for complex images.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yongxiang Zhang
AU  - Tiantian Meng
AU  - Zhuhong Shao
AU  - Liang Yan
PY  - 2019/10
DA  - 2019/10
TI  - An Improved Algorithm of Parameter Kernel Cutting Based on Complex Fusion Image
BT  - Proceedings of the 2019 International Conference on Mathematics, Big Data Analysis and Simulation and Modelling (MBDASM 2019)
PB  - Atlantis Press
SP  - 15
EP  - 19
SN  - 2352-538X
UR  - https://doi.org/10.2991/mbdasm-19.2019.4
DO  - 10.2991/mbdasm-19.2019.4
ID  - Zhang2019/10
ER  -