Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (25): 40-42.

• 学术探讨 • Previous Articles     Next Articles

Algorithm and implementation of image classification based on SVM

ZHANG Shu-ya,ZHAO Yi-ming,LI Jun-li   

  1. Institute of DSP and Software Techniques,Ningbo University,Ningbo,Zhejiang 315211,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-09-01 Published:2007-09-01
  • Contact: ZHANG Shu-ya

基于SVM的图像分类算法与实现

张淑雅,赵一鸣,李均利   

  1. 宁波大学 数字技术与应用软件研究所,浙江 宁波 315211
  • 通讯作者: 张淑雅

Abstract: This paper presents an algorithm to classify old black-and-white photographs and color photographs.The basic idea of the algorithm is that,first defines some indexes according to the different characteristics between them,then uses these indexes to find out images with obvious characteristics by advance classification,at last,classifies other images by SVM to finish the work of image classification,and the indexes above are used as learning parameters.The experimental results show that the definition of indexes is reasonable and the effect is satisfying.

Key words: old black-and-white photographs, color photographs, SVM, image classification

摘要: 提出了一种对人类视觉中的黑白老照片和彩色照片进行分类的方法,其基本思想是,首先在分析两者各自特点的基础上,定义了一些指标特征;其次利用这些指标对图像进行预分类,找出其中特征明显的图像;然后使用支持向量机(SVM)的算法对这些指标进行学习来区分剩余图像,最终达到对图像分类的效果。实验结果表明指标定义是合理的,效果也较满意。

关键词: 黑白老照片, 彩色照片, SVM, 图像分类