Method, system and computer-readable recording medium for adding new image and information on new image to image database

Abstract

According to one embodiment of the present invention, provided is a method comprising the following steps: (a) matching an image prestored in an image database with a query image so as to detect whether or not an image similar to the query image exists in the image database; (b) storing the query image in an unrecognized image database if an image similar to the query image does not exist; (c) collecting images related to each other based on the similarity between images stored in the unrecognized image database so as to construct an image group; and (d) comparing a portion of an image contained in a specific image group from among the constructed image groups with a specific input image when a specific image and tag information on the specific image are inputted, and, if it is determined that the portion of the image has a similarity that is higher than a preset threshold value, automatically adding the relevant image to the image database together with the input tag information.

Description

technical field [0001] The present invention relates to a method, system and computer-readable storage medium for adding new images and their related information to an image database. More specifically, the present invention relates to: when adding a new image and its related information in an image database, after searching an input query image in an image database for searching, additionally store and group unmatched unrecognized images, using A method, system, and computer-readable storage for easily adding the above-mentioned unrecognized image and its label information to an image database by verifying images (or images manually provided by users) and labels automatically obtained by methods such as web crawling medium. Background technique [0002] Recently, with the development of communication technology and the expansion of the use of the Internet, search methods have also been diversified. For example, when searching for the information that needs to be known, co...

AI Technical Summary

Problems solved by technology

First, in order to provide an image search system, an image database containing a sufficient amount of data is required. When the image database does not contain sufficient data, even if a query image is input, the search result information for the query image cannot be provided. The query image and the image database After matching the images stored in , the result is that the matching fails, that is, the unrecognized images cannot be reused and all are discarded

At this time, before the unrecognized images are manually reflected in the image database, even if the search is repeated repeatedly, the search result information for the existing unrecognized images cannot be provided.

Images