Dimensionality Reduction Based on Feature Points of Underwater Image Mosaic Algorithm

Image mosaic is a wide perspective to create high resolution for image processing, computer graphics and new field of interdisciplinary research. According to the fact that the real-time performance of Harris feature mosaic algorithm is poor, this paper proposes an improved Harris algorithm based on feature point mosaic of principal component analysis to reduce the dimensionality of the feature points. The algorithm constructs feature descriptors with the feature points, and then uses PCA to reduce the dimension of feature vector descriptor to improve the real-time of the algorithm. Experimental results show that the algorithm can realize the underwater image mosaic and improve the real-time performance of the algorithm.