基于颜色和几何特征的图像特征点匹配算法

Color and Shape-Based Algorithm for Feature Correspondence

提出一种基于颜色和几何特征的图像特征点匹配算法。首先提取两幅图像特征点集邻域色调的局部累加直方图,然后结合图像特征点的几何特征构造亲近矩阵,再对亲近矩阵进行奇异值分解(SVD),利用分解的结果构造出一个反应特征点之间匹配程度的关系矩阵,最后根据关系矩阵实现两幅图像的特征点匹配。实验结果显示,这种图像特征点匹配算法对真实图像的平面旋转和立体旋转都具有较高的匹配精确度。

A novel method for performing point - feature correspondence based on the color and shape description is proposed in this paper, First of all, partial accumulation histogram of the hue of the matching features of images is quantified into one matrix. Mix the matrix and geometric characteristic into a correspondence strength matrix. Then, the correspondence strength matrix is decomposed by the singular value decomposion （SVD）, a relation matrix that denotes the matching degree among feature points is constructed by the result of the decomposition. Finally, the matching feature points of the two images are obtained according to the relation matrix. Experimental results indicate that the algorithm in the paper has the higher precision both of planar matching and stereo matching for real images.