J4

• 计算机科学 • 上一篇    下一篇

基于贝叶斯分类器的图像分类

董立岩1, 苑森淼1, 刘光远2, 贾书洪3   

  1. 1. 吉林大学 计算机科学与技术学院, 长春 130012; 2. 吉林大学 通信工程学院, 长春 130022;3. 空军航空大学 基础部, 长春 130022
  • 收稿日期:2006-10-14 修回日期:1900-01-01 出版日期:2007-03-26 发布日期:2007-03-26
  • 通讯作者: 苑森淼

Image Classification Based on Bayesian Classifier

DONG Liyan1, YUAN Senmiao1, LIU Guangyuan2, JIA Shu hong3   

  1. 1. College of Computer Science and Technology, Jilin University, Changchun 130012, China;2. College of Communication Engineering, Jilin University, Changchun 130022, China;3. Department of Foundation, Aviation University of Air Force, Changchun 130022, China
  • Received:2006-10-14 Revised:1900-01-01 Online:2007-03-26 Published:2007-03-26
  • Contact: YUAN Senmiao

摘要: 通过对朴素贝叶斯分类器的讨论, 提出将贝叶斯方法应用于医学图像分割后的图像分类思想. 给出一种基于朴素贝叶斯分类器的图像分类方法, 对从尿沉渣图像中识别出的微粒进行正确分割及特征提取与选择, 并利用朴素贝叶斯分类器进行分类. 实验结果表明, 所提出的方法用于解决图像分类有效.

关键词: 贝叶斯分类器, 图像分类, 特征提取, 特征选择

Abstract: Naive Bayesian classifier was discussed. Naive Bayesian approach was used in image classification. The new method improves the accuracy of image recognition. An image classification method based on naive Bayesian classifier was introduced. After distinguishing the visible compositions, feature extraction and feature selection were processed. In the end, naive Bayesian classifier was used in classifying of object entities. Experiment result shows that the new method is suitable for image classification.

Key words: Bayesian classifier, image classification, feature ext raction, feature selection

中图分类号: 

  • TP18