Distributed image file system based on human cognition

摘要

Big Data era is characterized by the explosive increase of image files on the Internet, massive image files bring great challenges to storage. It is required not only the storage efficiency of massive image files but also the accuracy and robustness of massive image file management and retrieval. To meet these requirements, distributed image file storage system based on cognition is proposed. According to the human brain function, humans can correlate image files with thousands of distinct object and action categories and sorted store these files. Thus we proposed to sorted store image files according to different visual categories based on human cognition. The experimental results demonstrate that the proposed distributed image file system (DIFS) based on cognition performs better than Hadoop Distributed File System (HDFS).