Bridge crack image segmentation based on improved watershed algorithm

2018 ◽  
Author(s):  
Liang Zhang ◽  
Wenguang Luo ◽  
Yani Xu
Keyword(s):  
Image Segmentation ◽  
Watershed Algorithm

Image of Monolithic Circuit Segmentation Based on Watershed Algorithm

2013 ◽  
Vol 303-306 ◽  
pp. 1109-1113
Author(s):  
Zhu Lin Wang ◽  
Bin Fang ◽  
Xi Wei Guo
Keyword(s):  
Image Segmentation ◽  
Processing Method ◽  
Morphological Processing ◽  
Watershed Algorithm ◽  
Single Object ◽  
Watershed Transform ◽  
Key Technology ◽  
Processing Function ◽  
Important Position

Abstract. Image segmentation is a key technology in image engineering, it occupy an important position. This paper introduces the watershed transform to Image of monolithic circuit processing method, and then introduced the watershed transform to Image of monolithic circuit segmentation and sample. The results show that, by using the watershed algorithm and morphological processing function, which is connected with a plurality of object images are segmented into a plurality of single object, to achieve the image segmentation, and as far as possible to reduce or eliminate the phenomenon of over-segmentation. Finally it points out the further direction of research.

Improved watershed algorithm for color image segmentation

2009 ◽  
Author(s):  
Hong-bo Tan ◽  
Zhi-qiang Hou ◽  
Xiao-chun Li ◽  
Rong Liu ◽  
Wei-wu Guo
Keyword(s):  
Image Segmentation ◽  
Color Image ◽  
Color Image Segmentation ◽  
Watershed Algorithm

Image Segmentation Algorithm Combined with Regularized P-M De-Noising Model and Improved Watershed Algorithm

2020 ◽  
Vol 10 (2) ◽  
pp. 515-521 ◽  
Author(s):  
Guorui Chen
Keyword(s):  
Image Segmentation ◽  
Brain Mri ◽  
Small Region ◽  
Watershed Algorithm ◽  
Segmentation Method ◽  
Segmentation Algorithms ◽  
Segmentation Image ◽  
The Brain ◽  
Image Segmentation Algorithm ◽  
Mri Image

Aiming at the problems of noise sensitivity and unclear contour in existing MRI image segmentation algorithms, a segmentation method combining regularized P-M de-noising model and improved watershed algorithm is proposed. First, the brain MRI image is pre-processed to obtain a brain nuclear image. Then, the brain nuclear image is de-noised by a regularized P-M model. After that, the image is preliminarily segmented by the traditional watershed algorithm to extract the features of each small region. Finally, the small regions are merged by Fuzzy Clustering with Spatial Pattern (FCSP) to obtain the segmentation image with smooth edges. The experimental results show that the algorithm can accurately segment the gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) regions. The average AOM and ME of the segmentation results on the BrainWeb dataset reached 0.93 and 0.04, respectively.

Sign in / Sign up

Export Citation Format

Share Document