Image processing method, equipment, computer storage medium and server

Abstract

An embodiment of the invention discloses an image processing method and equipment, a computer storage medium and system, wherein the method is applied to the cage. The method comprises the following steps of: The cage acquires M groups of image features of the image to be processed from the encoder, and acquires first image representation information corresponding to each group of image features in the M groups of image features. According to each group of image features and first image representation information corresponding to each group of image feature, M image representation informationsets are generated, wherein, a set image features corresponding to an image representation information set generated, and an image representation information set includes at least one second image representation information. The second image representation information included in the M image representation information sets is merged to acquire target image representation information, and the target image representation information is output to the decoder. According to the image processing method and equipment, the computer storage medium and system, it helps to improve the natural statement description accuracy of the image, and optimize the quality of the image content understanding service.

Description

technical field [0001] The present invention relates to the technical field of the Internet, in particular to the technical field of image processing, and in particular to an image processing method, an image processing device, a computer storage medium and a server. Background technique [0002] In order to facilitate and quickly understand the main content of the image, the image content understanding service came into being. The image content understanding service is a service that converts image content into a description using a natural sentence, so image content understanding can also be understood as image content description. In other words, image content understanding can be viewed as a translation problem, that is, translating image content into natural sentence descriptions. An important factor to measure the quality of the image content understanding service is the description accuracy of the natural sentences used to describe the image content. [0003] In the...

AI Technical Summary

Problems solved by technology

Although the image content understanding service is realized through the solution of the prior art, the existing art only obtains natural sentences used to describe the image content through the decoder and the decoder, and does not pay attention to describing the image from multiple angles, which cannot Guaranteeing the quality of image content understanding services

Images