Research on Image Matching of Improved SIFT Algorithm Based on Stability Factor and Feature Descriptor Simplification

作者：Tang Liang, Shuhua Ma, Xianchun Ma, Hairong You · 发表于：Applied Sciences · 年份：2022 · DOI：10.3390/app12178448 · 被引用次数：30 · 研究领域：Advanced Image and Video Retrieval Techniques、Image Retrieval and Classification Techniques、Robotics and Sensor-Based Localization

In view of the problems of long matching time and the high-dimension and high-matching rate errors of traditional scale-invariant feature transformation (SIFT) feature descriptors, this paper proposes an improved SIFT algorithm with an added stability factor for image feature matching. First of all, the stability factor was increased during construction of the scale space to eliminate matching points of unstable points, speed up image processing and reduce the dimension and the amount of calculation. Finally, the algorithm was experimentally verified and showed excellent results in experiments on two data sets. Compared to other algorithms, the results showed that the algorithm proposed in this paper improved SIFT algorithm efficiency, shortened image-processing time, and reduced algorithm error.