摘要
针对SIFT算子进行图像匹配存在匹配特征点数少容易出现误匹配的缺点,将分数阶微分处理和SIFT算子结合起来,提出一种改进的SIFT的图像检测匹配算法。首先采用分数阶微分方法对图像的细节纹理部分进行加强从而提高图像的分辨率,之后采用SIFT算子对旋转缩放后的图像进行特征关键点提取和匹配,从而提高图像识别的准确率。实验结果表明,改进的SIFT算法提取图像的关键点和提高图像匹配的准确率达到94.59%,优于未改进的SIFT算法。
In view of the image matching SIFT operator is matching feature points less prone to shortcomings of mismatch,this paper combined fractional differential treatment and SIFT operator,an improved SIFT image matching algorithm is presented. First the fractional order differential method strengthens the part the detail of the image texture to improve the resolution of the images,after using SIFT operator to rotate the resized image feature point extraction and matching,so as to improve the accuracy of image recognition. The experimental results show that the improved SIFT algorithm to extract image point and improve the image matching accuracy reached 94. 59%,was better than the improved SIFT algorithm.
出处
《信息技术》
2017年第11期105-107,111,共4页
Information Technology
关键词
分数阶微分
SIFT
关键点
图像匹配
fractional order differentiation
SIFT
key points
image matching
