Image structuring method and device

Abstract

The embodiment of the invention provides an image structuring method and device. The method comprises a step of extracting the characteristic of image based on a first neural network, wherein the characteristic is expressed by using a characteristic tensor, a step of determining an area with possible object of interest in the image according to the characteristic tensor based on a second neural network, a step of calculating the characteristic vector of the area with possible object of interest according to the characteristic tensor, and a step of identifying the object of interest in the area with possible object of interest according to the characteristic vector and determining the position of the object of interest and the attribute of the object of interest based on a third neural network. According to the method and device, the introduction of extra errors in the two links of detecting an object and determining an object attribute is avoided. In addition, the interference in analyzing the object of interest by a background is effectively avoided, and the accuracy of image structural analysis is improved.

Description

technical field [0001] The present invention relates to the field of image processing, and more particularly relates to an image structuring method and device. Background technique [0002] With the development of communication networks, data compression and mass storage technologies, more and more multimedia information exists on the Internet in computer-readable form. They include not only common text data, but also media information such as images and videos. They generally have no image structure and lack semantic information, and it is difficult for information retrieval systems to search them effectively. Only effective structuring of media data can help people find interesting content faster. [0003] Image structuring is an intelligent analysis process for image content information extraction. It organizes image content into text information that can be understood by computers and humans by using time-space segmentation, feature extraction, object recognition and ot...

AI Technical Summary

Problems solved by technology

In the above two independent links, additional errors may be introduced, causing the spread of errors to expand

Therefore, the existing image structuring methods and systems have low processing accuracy, and it is difficult to avoid the interference of the background in the image on the attributes of the object of interest.

Images