Research on image segmentation algorithm based on threshold

被引：7

作者：

Song, Shaozhong ^{[1
]}

Gao, Ting ^{[2
]}

机构：

[1] JiLin Engn Normal Univ, Sch Informat Engn, Changchun 130052, Peoples R China

[2] Jilin Business & Technol Coll, Coll Engn, Changchun, Peoples R China

来源：

2021 13TH INTERNATIONAL CONFERENCE ON MEASURING TECHNOLOGY AND MECHATRONICS AUTOMATION (ICMTMA 2021) | 2021年

关键词：

image segmentation; Threshold segmentation method; Histograms; Otsu algorithm;

D O I：

10.1109/ICMTMA52658.2021.00071

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Image segmentation technique is to segment an image into non-overlapping parts with similar features. It is the premise of image feature extraction and target recognition. The accuracy of different segmentation methods has a great impact on feature extraction and recognition. In order to verify the effect of different segmentation methods, this paper uses histogram threshold segmentation method and Otsu segmentation method to segment the same target image. The experimental results show that both methods can segment the target region and the background region, and the segmentation results of the Otsu segmentation method is better than the histogram threshold segmentation method, and the segmentation quality of the Otsu segmentation method is better.

引用

页码：306 / 308

页数：3