Convolution Optimized Density Clustering Algorithm for Image Segmentation

Abstract

In order to improve the usability of DBSCAN in the field of high-resolution image segmentation, according to the characteristics of digital images, an efficient DBSCAN based on three-dimensional convolution is proposed, and on this basis, a color image segmentation method is implemented. First, convolution is introduced into DBSCAN, three-dimensional convolution is used to obtain the core object, avoiding distance calculation and region retrieval, and reducing the time complexity of this step from the second order to a constant level. Then, the three-dimensional convolution is optimized based on dynamic programming, so that the convolution time is independent of the size of the convolution kernel. Finally, the neighborhood search range of the sample points is simplified according to the ordered core object set. Compared with the existing algorithms, the experimental results on the Berkeley BSD300 show that the algorithm is effective, the CH index and the time efficiency increase by 17% and 49% on average. The results of experiments using the remote sensing image set Mts-WH show that the computational efficiency of the algorithm is significantly improved. Compared with the DBSCAN optimized by the <italic>k</italic>D tree, the efficiency is increased by an average of 19 times, and the improvement effect is more obvious as the number of sample points increases. When the number of points exceeds 500 000, the efficiency is increased by 169 times.