一种基于Zernike矩形状检索的新算法  

New Algorithm of Zernike Moments Features for Shape-base Image Retrieval

作　　者：郭丹[1] 闫德勤[1] 吴晓婷[1] 刘胜蓝[1] 

机构地区：[1]辽宁师范大学计算机与信息技术学院,大连116081

出　　处：《计算机科学》2010年第11期247-251,286,共6页Computer Science

基　　金：国家自然科学基金(60372071);中国科学院自动化研究所复杂系统与智能科学重点实验室开放课题基金(20070101);辽宁省教育厅高等学校科学研究基金(2008344)资助

摘　　要：高维Zernike矩作为图像检索的形状特征描述子,具有描述图像区域细节信息的能力,能够全面有效地表征图像的内容。但是高维的矩存在着"维数灾难"的问题,不仅使算法的复杂度增大,而且会增加不必要的信息,造成主要信息混淆,影响对图像的描述。提出了流行学习的方法来处理冗余的数据信息。在通过拉普拉斯图保持局部样本数据不变的情况下,引入了全局算法来保证样本的整体性。考虑到信息之间的相关性而影响投影的准确率,对其进行Schur特征值分解,得到正交基向量,从而使数据重构相对容易,并且Zernike矩的旋转不变性仍能保持下来,使检索得到的图像更加符合人眼视觉效果。该方法在检索性能上优于传统的局部保持投影方法,检索效果有明显的提高。As shape feature descriptors,high dimention zernike moments have the function of describing the detail information of image region,which exist＂dimension disaster＂.This will result to increase the complexity of the algorithm and unnecessary information which make major information confused,and will affect decribing the content of the image.A new algorithm based on Manifold method was proposed to realize dimension deduction in image data.Under the condition of Laplace figure keeping local sample data,overall algorithm was introduced to ensure the integrity of the sample.Considering the influence of the correlation between information on projection accuracy,schur eigenvalue decomposition was made to obtain the orthogonal vectors.This can make the data reconstruction relatively easier,and the rotation invariant of Zernike moment can still keep down,then making the image retrieval accords with the human visual effect.This method is superior than LPP in the retrieval performance,and retrieval results are significantly improved.

关 键 词：ZERNIKE矩 图像检索 主成分分析 局部保持投影 SCHUR分解 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]