摘要
提出一种鲁棒的图像局部仿射不变特征提取方法.该方法首先对图像进行M进制小波变换,根据M进制小波变换系数的能量性质来检测图像特征点.然后以检测到的稳定特征点为中心,根据特征点周围的局部图像信息,以矩的形式构造仿射不变特征描述子.实验结果证明该方法对图像的旋转变化、尺度变化、视点变化、平移等所有仿射变换均具有较好的不变性.
A robust affine invariant local image features extraction method is proposed. Firstly, the image is transformed with M band wavelet. The feature points of the image are detected according to the energy of the M band wavelet transform coefficients. Then, every detected feature point is set to be a center. According to the local image information around the center, affine invariant feature is eonstructed with a moment structure. The experiments prove the invariant efficiency of the proposed method in image rotation, shift, scaling and viewpoint change etc.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2013年第3期276-281,共6页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.61175006,61175015)
湖南省研究生科研创新项目(No.CX2010B024)
国防科学技术大学优秀博士生创新项目(No.B100504)资助
关键词
仿射不变
图像特征
小波
Affine Invariant, Image Feature, Wavelet