Method, system, and computer-readable storage medium for adding new images and their related information to an image database

Abstract

According to an embodiment of the present invention, there is provided a method including the following steps: (a) by matching the stored images in the image database with the query image, search for an image similar to the query image in the image database; (b) ) If the search result is that there is no image similar to the query image, the query image is stored in the unrecognized image database; (c) Based on the similarity between the images stored in the unrecognized image database, the images that are related to each other are collected to form (d) If a specific image and its label information are input, a part of the images in the specific image set in the formed image set will be compared with the input specific image, and if it is judged to have a similarity above a predetermined threshold, then The image is automatically added to the image database along with the entered label 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