Research on Image Segmentation Method Based on Consistency Theorem and Merging Criterion

This paper takes Hongze lake as an example to explore a novel image segmentation method. We use the regional consistency theorem and the merging criteria to merge discrete pixels of similar features into smaller regions. Thereby, the lake area can be represented by a number of pixels, and the area&#...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2018-09, Vol.1098 (1), p.12022
Main Authors: Lu, Jia-min, Li, Hao-fei, Yuan, Di, Miao, Ya-wen, Lei, Yi-fan
Format: Article
Language:English
Subjects:
Algorithms
Consistency
Image segmentation
Mathematical analysis
Pixels
Theorems
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper takes Hongze lake as an example to explore a novel image segmentation method. We use the regional consistency theorem and the merging criteria to merge discrete pixels of similar features into smaller regions. Thereby, the lake area can be represented by a number of pixels, and the area's change trend can be measured by simply counting the pixel numbers before and after. By using this algorithm, it is possible to skip the cumbersome steps of calculating the area and obtain the area change trends rapidly, as it avoids a large number of duplicate calculations and reduces the situation of missing extreme pixel points. In addition, it saves the required time on manual processing and increases the processing efficiency greatly. Finally, the validity of the proposed algorithm is verified by comparing the lake area data with the yearbook.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1098/1/012022