Image description method and device

Abstract

The invention provides an image description method and device, and the method comprises the steps: carrying out the feature extraction of a target image through employing a plurality of first featureextraction models, and obtaining the image features generated by each first feature extraction model; performing fusion processing on the image features generated by the plurality of first feature extraction models to generate global image features corresponding to the target image; performing feature extraction on the target image by using a second feature extraction model to obtain a target detection feature corresponding to the target image; inputting the global image feature and the target detection feature corresponding to the target image into a translation model, and using the generatedtranslation statement as a description statement of the target image, so that in the subsequent process of inputting the global image characteristics corresponding to the target image and the targetdetection characteristics into the translation model to generate the translation statement, the global image characteristics of the image information are richer as a reference, and the output translation statement is more accurate.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular, to a method and apparatus for image description, a computing device, and a computer-readable storage medium. Background technique [0002] Image description is to automatically generate a descriptive text based on the image, similar to "seeing the picture and talking". Image captioning is simple and natural for humans, but challenging for machines. The reason is that the machine not only needs to be able to detect the objects in the image, but also to understand the relationship between the objects, and finally to express it in a reasonable language. [0003] In the prior art, the process of image description requires a machine to extract local information and global information from the target image, input the global information and local information to the translation model, and use the sentence output by the translation model as the description informatio...

AI Technical Summary

Problems solved by technology

In this case, the extraction of global information by the feature extraction model depends on the performance of the feature extraction model itself. Some feature extraction models will pay attention to one type of information in the image, and some feature extraction models will pay attention to another type of information in the image. One type of information, which will cause the translation model to often fail to use the complete global information corresponding to the image as a reference in the subsequent process, resulting in deviations in the output sentences

Images