Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (33): 195-197.DOI: 10.3778/j.issn.1002-8331.2010.33.055

• 图形、图像、模式识别 • Previous Articles     Next Articles

Research on modified two-dimensional Otsu of image segmentation algorithm

QIU Li-jun,HOU De-wen,WANG Yi-cai   

  1. College of Information Science and Engineering,Shandong Normal University,Jinan 250014,China
  • Received:2009-06-29 Revised:2009-08-17 Online:2010-11-21 Published:2010-11-21
  • Contact: QIU Li-jun

改进的二维Otsu图像分割方法的研究

邱丽君,侯德文,王依才   

  1. 山东师范大学 信息科学与工程学院,济南 250014
  • 通讯作者: 邱丽君

Abstract: In order to enhance the segmentation accuracy of traditional two-dimensional Otsu method,especially for the segmentation accuracy of small targets,an improved method is presented:Based on traditional two-dimensional Otsu method,the coordinate system of two-dimensional histogram is transformed and the traditional calculation formula is adjusted in order to improve the threshold segmentation method.The experimental results indicate that the identification capability and segmentation efficiency are enhanced,compared with the traditional method.

Key words: two-dimensional histogram, Otsu method, coordinate transformation, threshold segmentation

摘要: 为提高传统二维Otsu法的分割精度,尤其是对图像中小目标的分割精度,提出具体的改进方法:在传统二维Otsu法的基础上,对二维灰度直方图进行坐标变换,并将传统计算公式进行调整,改进阈值分割方法。实验结果表明,改进的阈值分割方法与传统算法相比较,提高了识别能力和分割效率。

关键词: 二维灰度直方图, Otsu法, 坐标变换, 阈值分割

CLC Number: