一种改进的SIFT—PCA算法在图像检索中的应用

摘要

针对SIFT算法（尺度不变特征）提取出的图像特征点向量维数较多造成计算量较大、检索效率低等问题，提出一种SIFT和改进的主成分分析（Principal Component Analysis，PCA）相结合的SIFT—PCA算法。该算法首先采用SIFT算法提取图像特征点向量，然后利用改进的PCA算法把特征点向量变换到另一个空间，得到最具有代表性的特征参数，实现对特征点向量的降维。此算法在保证原SIFT算法鲁棒性的同时减少了计算量，增强了实时性。实验结果说明了该算法具有尺度、平移、旋转、光照不变性，在图像检索中应用切实可行且效果良好。%The limitations of the scale-invariant feature points extraction algorithm were discussed at present, including larger amount of calculation, more complex matching, and lower retrieval rate. This paper proposes an improved algorithm SIFT with PCA that is SIFT-PCA. This algorithm utilizes SIFT algorithm to extract feature vectors of the image feature points, and then transforms the feature vector space to anoth- er by the improved PCA （Principal Component Analysis,PCA） algorithm, gains the most representative of the characteristic parameters to realize the feature point vector dimension reduction. The method guarantees the robustness of traditional SIFT algorithm, decreases the calculation amount, and enhances the realtime. Experiments show that the features are invariant to image scaling, translation, rotation, illumination. At the same time, it is quite applicable to image retrieval.