关键词: 并行化, 图像聚类

Abstract: As technology advances, image data is rapidly growing including images and videos on Internet. How to effectively manage the image data is a great challenge. Image clustering is an important image data managing solution. This paper proposes a solution of MapReduce parallelization about the SIFT image feature extraction and K-means clustering method on Hadoop platform. It achieves good results.

Key words: parallelization, image clustering