Image management method and device based on multi-task machine learning model

Abstract

The invention discloses an image management method and device based on a multi-task machine learning model, and relates to the machine learning technology of artificial intelligence. Image data is acquired; a target image is input into a shared feature expression network in a multi-task machine learning model to obtain task output features; the task output features are respectively input into a plurality of sub-task networks to obtain an identification result; and the image data is processed based on the identification result. Therefore, an image management process based on machine learning isrealized; since the shared feature expression network is used for extracting the features for executing a plurality of tasks, and the different sub-task networks are respectively used for executing the corresponding tasks, the execution process of the plurality of image management tasks can be realized through the multi-task machine learning model, and the efficiency of image management is improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to an image management method and device based on a multi-task machine learning model. Background technique [0002] With the popularization of smart phones and the increasing number of mobile phone photos, more and more people have the demand task of organizing mobile phone photos in real time. These demand tasks mainly have the following salient features. First of all, the task correlation is strong; the scene category of the photo has a great relationship with the main object in the photo, and various quality indicators of the photo, such as blur and exposure, are also related to the scene where the photo was taken. In addition, photo scene recognition, object detection, and photo quality assessment all rely on photo texture and contour light features. In addition, task processing requires high model size and computational complexity. Because the model needs to be d...

AI Technical Summary

Problems solved by technology

[0004] However, due to the large amount of tasks involved in the image sorting process, designing a separate machine learning model for each task takes up a lot of system resources, and the preprocessing time of multiple models in the design process is long and the process is complicated, which affects the image quality. management efficiency

Images