METHOD FOR LEARNING OF SEQUENTIAL BINARY CODE USING FEATURES AND APPARATUS FOR THE SAME

摘要

Disclosed are a method and apparatus for learning a sequential binary code using a plurality of features, capable of providing high accuracy when an image composed of multiple features is searched. The method includes the steps of obtaining an inquiry image; extracting the feature from the obtained inquiry image; learning a multi-view hashing algorithm by using the extracted feature; and searching an image with a binary code corresponding to the binary code generated through the learned multi-view algorithm. Therefore, high accuracy is provided when the image with the image composed of the features is searched. The present invention is successfully applied to a content-based image searching system.