A MapReduce Approach for SIFT Feature Extraction
Wei Han, Yiding Kang, Chen Yang, Xueqing Zhang · 2013
SIFT feature extraction is a computationally intensive problem, for the large scale image, which will take a long time to extract SIFT feature. This paper presents a novel approach, based on MapReduce, to accelerate SIFT feature extraction. A MapReduce based SIFT feature extraction model is established, and the original SIFT feature extraction progress is reformed to fit the model. We have implemented the MapReduce based algorithm and evaluated it on a Hadoop cluster. The experimental results show that this approach can extract SIFT feature simultaneously on Hadoop cluster with a good speed up rate.