Semi-automatic image labeling method based on semantic and content

Abstract

The invention discloses a semi-automatic image tagging method based on semantics and content. The tagging method comprises the following steps: a feedback image retrieval system based on semantics and content is established; a model of the system is expressed as (F, Q, R (fq, fd)) with a triple; a user submits an query based on keywords; the system converts a keyword sequence into a group of semantic characteristics vector Omega i', uses an arrangement function R (fq, fd)) for doing an query based on semantics for all the images in a database, and returns the query result to the user according to the arrangement; the user chooses relatively satisfactory images from the query result and feeds back to the system; the system again uses the arrangement function R (fq, fd)) for doing the query based on semantics or content or integrating the semantics and the content for all the images in a database, finds out all the images which are similar to the images that the user is satisfied with, and simultaneously adjusts the weight of the tagging information that each image corresponds to. The invention has the advantages of high efficiency, high accuracy, and friendly interactive way.

Description

technical field [0001] The invention relates to a computer image search and image labeling method, in particular to a semi-automatic image labeling method based on semantics and content. Background technique [0002] In the past ten years, with the rapid development of computer network technology, popularization and application, and a sharp decline in data storage costs, the use of multimedia databases has become more and more common. Multimedia information presented in the form of images, music, and video plays an increasingly important role in both business and entertainment. How to effectively manage and organize such a large amount of data, and search out the information that users need has become a very important issue. There has been a long history of research on browsing, searching and indexing technologies for multimedia data, especially image data. Today, the topic of image databases and visual information search has become the most active part of the research fie...

AI Technical Summary

Problems solved by technology

Human labeling has high accuracy but low efficiency; machine labeling has high efficiency but low accuracy

For a content-based image search system, it is generally difficult for users to define these descriptions, and it is also difficult for computer programs to understand these descriptions

In addition, even if the user provides a relatively good initial query, how to make the subsequent feedback information act on the system is also a big problem

[0004] Therefore, the three methods of semantic-based image search using manual annotation, semantic-based image search using machine annotation, and content-based image search have their own advantages and disadvantages. At present, there is no image annotation that can combine the advantages of the above three. indexing system

Images