首页 | 本学科首页   官方微博 | 高级检索  
     

基于多特征的旋转不变纹理图像检索
引用本文:朱正礼,赵春霞,侯迎坤,范燕. 基于多特征的旋转不变纹理图像检索[J]. 南京理工大学学报(自然科学版), 2012, 36(3): 375-380
作者姓名:朱正礼  赵春霞  侯迎坤  范燕
作者单位:1. 南京理工大学计算机科学与技术学院,江苏南京210094;南京林业大学信息科学技术学院,江苏南京210037
2. 南京理工大学计算机科学与技术学院,江苏南京,210094
3. 南京理工大学计算机科学与技术学院,江苏南京210094;泰山学院信息科学技术学院,山东泰安271021
4. 江苏科技大学电子信息学院,江苏镇江,212003
基金项目:国家自然科学基金,山东省自然科学基金
摘    要:为了消除图像旋转对图像检索的影响,提出了一个基于非下采样轮廓波变换、灰度共生矩阵和新相似性度量的旋转不变纹理图像检索算法。非下采样轮廓波变换具有各向异性和平移不变性。灰度共生矩阵描述了图像的方向性、邻近空间关系和方差的变化范围。通过计算每个非下采样轮廓波变换尺度下的所有子带的平均能量和平均标准差,灰度共生矩阵的二阶矩角、惯性熵、惯性矩、反差分矩,惯性相关系数的均值、标准差,得到具有旋转不变性的纹理多特征。提出一种新的相似性度量以改进纹理图像检索性能。实验结果表明,对于1个含640幅图像的旋转纹理图像库,与基于双树复小波变换的方法相比,该文图像检索算法将旋转纹理图像检索准确率由73.28%提高至80.71%。

关 键 词:图像检索  旋转不变性  非下采样轮廓波变换  灰度共生矩阵  相似性度量

Rotation-invariant Texture Image Retrieval Based on Multi-feature
ZHU Zheng-li , ZHAO Chun-xia , HOU Ying-kun , FAN Yan. Rotation-invariant Texture Image Retrieval Based on Multi-feature[J]. Journal of Nanjing University of Science and Technology(Nature Science), 2012, 36(3): 375-380
Authors:ZHU Zheng-li    ZHAO Chun-xia    HOU Ying-kun    FAN Yan
Affiliation:1.School of Computer Science and Technology,NUST,Nanjing 210094,China; 2.College of Information Science and Technology,Nanjing Forestry University,Nanjing 210037,China; 3.School of Information Science and Technology,Taishan University,Taian 271021,China; 4.School of Electronics and Information,Jiangsu University of Science and Technology,Zhenjiang 212003,China)
Abstract:In order to eliminate the effect of image rotation on image retrieval,a novel rotation-invariant texture image retrieval algorithm is presented based on the nonsubsampled contourlet transform(NSCT),gray level concurrence matrix(GLCM)and novel similarity measurement.The NSCT has anisotropy and translation invariability.The GLCM reflects the direction,adjacency spacing relationship and range of variance change of the image.The rotation-invariant features are achieved by calculating the average energy and average standard deviation of all subbands at each NSCT scale,the mean and covariance of the second moment angle,inertia entropy,inertia moment,contrast points moment of the GLCM.A novel similarity measure is presented to improve the retrieval performance of texture images.Experimental results demonstrate that:compared with the dual tree-complex wavelet transform based approach,the image retrieval algorithm improves the retrieval accuracy from 73.28% to 80.71% for the rotated database of 640 images.
Keywords:image retrieval  rotational invariance  nonsubsampled contourtlet transform  gray level concurrence matrix  similarity measurement
本文献已被 CNKI 万方数据 等数据库收录!
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