期刊文献+

基于感兴趣区域的图像自动标注算法研究

Automatic image annotation algorithm based on the region of interest of the image
下载PDF
导出
摘要 提出一种基于感兴趣区域(ROI)的图像自动标注算法.首先利用JPEG 2000中的Maxshift算法提取出图像的感兴趣区域,建立感兴趣图像库;之后对图像库中的图像利用SIFT算法提取图像的特征向量;并利用支持向量机对图像进行标注;最后应用Corel图像数据库进行自动标注仿真试验,结果表明,所设计算法有较好的效果. For improving the accuracy of image automatic annotation, the paper submits a new automatic annota- tion algorithm based on the region of interest (ROI) of the image. First, it extracts the region of interest of the image by using the Maxshift algorithm of JPEG 2000, thereby establishing a ROI library, and then extracts the feature vector by using SIFT algorithm in the image library, and SVM is adopted to classify and annotate images automatically. Experimental results on images from Corel database show that this algorithm can improve the anno- tation accuracy.
出处 《云南民族大学学报(自然科学版)》 CAS 2013年第2期136-139,共4页 Journal of Yunnan Minzu University:Natural Sciences Edition
基金 云南民族大学研究生创新基金(2012YCX11) 云南省教育厅科学研究基金(2012Y315) 云南民族大学青年基金(11QN08)
关键词 图像自动标注 Maxshift算法 SIFT变换 K-MEANS聚类 支持向量机 automatic image annotation Maxshift algorithm SIFT k - Means cluster SVM
  • 相关文献

参考文献14

  • 1WATANABE O, KIYA H. Roi - base scalability for pro- gressive transmission in JPEG 2000 coding [ J ]. IEEE, 2003: 2(2): 416 - 419.
  • 2FUKUMA S, IKUTA S, ITO M, et al. An ROI image cod- ing based on swithing wavelet transform[ J]. IEEE, 2003, 2(2) :420 -423.
  • 3LIU Li-jie, GUO Liang-fan. A new method for JPEG 2000 region- of- interest image coding: most significant bit- planes shift[J]. IEEE, 2002,2(2) : 176 - 179.
  • 4唐俊华,阎保平.基于用户定义感兴趣区域的图像检索算法[J].计算机应用,2002,22(11):20-22. 被引量:6
  • 5阙大顺,李占,高勇.基于EZW与ROI混合编码的身份照片压缩算法研究[J].武汉理工大学学报(交通科学与工程版),2005,29(3):429-431. 被引量:3
  • 6刘海林,李灿平,王绪本.ROI技术在车牌识别系统中图像存储方面的应用研究[J].物探化探计算技术,2002,24(4):362-366. 被引量:4
  • 7尹文杰,韩军伟,郭雷,贺胜,许明.基于显著区域的图像自动标注[J].计算机应用研究,2011,28(10):3925-3928. 被引量:3
  • 8LOWED C. Distinctive image features from scale -invari- ant key points [ J ]. International Journal of Computer Vi- sion, 2004,60(2) :91 - 110.
  • 9LOWED G. Distinctive image features from scale - invari- ant interest points [ J ]. International Journal of Computer Vision, 2004, 60 (2), 91 - 110.
  • 10MACKAY D J C. Information theory, inference and learning algorithms [ M ]. Cambridge : Cambridge Univer- sity, 2003 : 284 - 292.

二级参考文献36

  • 1ZHANG Shao-ting, HUANG Jun-zhou, HUANG Yu-chi,et al. Auto- matic image annotation using group sparsity[ C ]//Proc of IEEE Con- ference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010:3312-3319.
  • 2MEI Tao, WANG Yong, HUA Xian-sheng, et al. Coherent image annotation by learning semantic distance [ C ]//Proc of IEEE Confer- ence on Computer Vision and Pattern Recognition. [ S. l. ] : IEEE, 2008:1-8.
  • 3WANG Chang-hu, YAN Shui-cheng, ZHANG Lei, et al. Multi-label sparse coding for automatic image annotation [ C ]//Proc of IEEE Con- ference on Computer Vision and Pattern Recognition. [ S. l. ] : IEEE, 2009 : 1643-1650.
  • 4JEON J, LAVRENKO V, MANMATHA R. Automatic image annotation and retrieval using cross-media relevance models [ C ]//Proc of ACM SIGIR. [ S. l. ] :ACM ,2003 : 119-126.
  • 5XIANG Yu, ZHOU Xiang-dong, LIU Zuo-tao, et al. Semantic context modeling with maximal margin conditional random fields for automatic image annotation[ C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010:3368-3375.
  • 6PUTTHIVIDHYA D, ATTIAS H T, NAGARAJAN S S. Topic regres- sion multi-modal latent Dirichlet allocation for image annotation [ C ]// Proc of IEEE Conference on Computer Vision and Pattern Recogni- tion. San Francisco : IEEE ,2010:3408-3415.
  • 7CHANG E, GOH K, SYCHAY G, et al. CBSA : content-based soft an- notation for multimodal image retrieval using Bayes point machines [ J]. IEEE Trans on Circuits and Systems for Video Technolo- gy,2003,13( 1 ) :26-38.
  • 8GAO Yu-li, FAN Jian-ping, XUE Xiang-yang, et al. Automatic image annotation by incorporating feature hierarchy and boosting to scale up SVM classifiers[ C ]//Proc of ACM International Conference on Multi- media. [ S. l. ] :ACM, 2006:901-910.
  • 9CLAUDIO C, GIANLUIGI C, RAIMONDO S. Image annotation using SVM [ C ]//Proc of SPIE, vol 5304. 2004:330- 338.
  • 10YANG C B, DONG M. Region-based image annotation using asymmet- rical support vector machine-based multiple-instance learning [ C ]// Proc of IEEE Conference on Computer Vision and Pattern Recogni- tion. New York : IEEE, 2006:2057-2063.

共引文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部