首页 | 本学科首页   官方微博 | 高级检索  
     

视觉显著性纹理—色彩特征融合的图像目标分类
引用本文:韩辰希,刘惠义,商国中.视觉显著性纹理—色彩特征融合的图像目标分类[J].电子测量技术,2017,40(11):94-98.
作者姓名:韩辰希  刘惠义  商国中
作者单位:河海大学计算机与信息学院 南京 210000,河海大学计算机与信息学院 南京 210000,河海大学计算机与信息学院 南京 210000
摘    要:针对图像目标分类,提出了一种显著性纹理特征.考虑到显著目标图像在纹理特征表征上的优势,在目标显著性图像提取的基础上进一步提取视觉显著性纹理特征.进而将该视觉显著性纹理特征同HSV色彩特征进行融合,形成图像目标融合特征,输入至后端分类器中进行分类.多类别的交叉实验证明,基于该融合特征的目标分类方法能够较为准确的对图像目标进行分类,在SIMPLIcity图像数据集上平均分类正确率达到84.84%,在Corel图像集上平均分类正确率为85.05%,优于基于单一分类特征的图像分类方法.

关 键 词:图像目标分类  显著图  特征融合  纹理特征  色彩特征

Vision saliency texture color feature fusion basedobject classification
Han Chenxi,Liu Huiyi and Shang Guozhong.Vision saliency texture color feature fusion basedobject classification[J].Electronic Measurement Technology,2017,40(11):94-98.
Authors:Han Chenxi  Liu Huiyi and Shang Guozhong
Affiliation:College of Computer and Information, HoHaiUniversity , Nanjing 210000,China,College of Computer and Information, HoHaiUniversity , Nanjing 210000,China and College of Computer and Information, HoHaiUniversity , Nanjing 210000,China
Abstract:In order to improve the performance of the image classification,a novel saliency texture feature is proposed.Considering the advantage of the saliency map for representing the texture information,the saliency texture feature is extracted based on the saliency map.This feature is further fused with the HSV color feature,generating a fused image feature which is inputted into the classifier.Results of cross-over experiments demonstrate that the fused feature works better than the compared counterpart and has the ability to correctly recognize the image objects.The imageclassification precision rates of the proposed method in SIMPLIcity and Corel5k databases achieved 84.84 % and 85.05%,respectively.
Keywords:image classification  saliency map  feature fusion  texture feature  color feature
本文献已被 万方数据 等数据库收录!
点击此处可从《电子测量技术》浏览原始摘要信息
点击此处可从《电子测量技术》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号