An image segmentation method of a modified SPCNN based on human visual system in medical images

2019 ◽  
Vol 333 ◽  
pp. 292-306 ◽  
Author(s):  
Jing Lian ◽  
Zhen Yang ◽  
Wenhao Sun ◽  
Yanan Guo ◽  
Li Zheng ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Visual System ◽  
Human Visual System ◽  
Medical Images ◽  
Segmentation Method

Remote Sensing Image Segmentation Based on Human Visual System Region-Split and Graph Cut

2011 ◽  
Vol 55-57 ◽  
pp. 115-118 ◽  
Author(s):  
Hua Jiang ◽  
Jing Wen
Keyword(s):  
Remote Sensing ◽  
Image Segmentation ◽  
Visual System ◽  
Human Visual System ◽  
Spatial Location ◽  
Remote Sensing Image ◽  
Graph Cut ◽  
Split Method ◽  
Segmentation Quality ◽  
Image Segmentation Algorithm

Aiming at the problem of poor real-time ability of Normalized Cut (NC), this paper suggests a remote sensing image segmentation algorithm based on region-split and graph cut within human visual system (HVS). According to the features of HVS, the algorithm uses region-split method to segment the remote sensing image into a large number of small regions. By integrating gray feature and spatial location of each region, NC is used to segment the image among regions from global view, by which the final segmented image can be generated. Experimental results show that comparing with the traditional NC, operating speed is significantly improved as getting close segmentation quality, and this is a kind of effective method of image segmentation.

METHODS AND ALGORITHMS FOR IMAGE SEGMENTATION

2020 ◽  
Vol 2020 (2) ◽  
pp. 11-16
Author(s):  
Karina Jo ◽  
Olga Gerget
Keyword(s):  
Cluster Analysis ◽  
Image Segmentation ◽  
Brain Tumors ◽  
Medical Images ◽  
Region Growing ◽  
Segmentation Method ◽  
Segmentation Accuracy ◽  
Optimal Segmentation ◽  
The Brain

This study aim to find the optimal segmentation method for detecting brain tumors. For this purpose, the main methods from each group were selected: from stochastic-the method of cluster analysis of k-means, from structural-morphological, from mixed – region growing. The study was based on medical images of the brain, the sample includes 10 images. After segmenting the images, you need to find the best result. The result must be justified. As a result of the research, the method of region growing proved to be an effective method. The accuracy of the method is proved by statistical and variance analyses. The segmentation accuracy of the region growing is 89 %.

Sign in / Sign up

Export Citation Format

Share Document