Notice of RetractionApplication of Approximate Vector Indexing Method in Medical Image Retrieval Platform

Notice of Retraction

After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.

We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.

In content-based multimedia information retrieval, image and video information are usually described by high-dimensional vector, if using a linear scanning approach to search for those feature vectors will undoubtedly increase the cost of calculating, so the approximate vector indexing method and clustering method are used in conjunction in this article to make use of high-dimensional indexing techniques in medical image retrieval platform. When creating an index file, transform the original vector into approximate vector, and use k-means clustering algorithm to divide the approximate vector, and then the index vectors of different clustering are stored in the respective sub-file. Experimental results show that a clustered index has higher efficiency than simple approximate vector method in querying feature vector. This paper also proposes an architecture design method based on search strategies, according the search strategy system could flexibly choose the method to use for feature extraction or matching calculation, and this makes it flexible and Convenient to publish an algorithm or Evaluation an algorithm.