Method and device for identifying target object, electronic equipment and storage medium

Abstract

The invention discloses a method and device for identifying a target object, electronic equipment and a storage medium, and relates to the field of information identification. The method comprises thesteps of obtaining feature information of a target object of a current time node; identifying the feature information through a pre-trained time feature information model, and performing similarity comparison with feature information of a target object pre-stored in a feature information base; when the similarity exceeds a preset threshold value, indicating the target object is successfully recognized, and automatically updating the feature information of the target object at the current time node to a feature information base; and automatically optimizing and retraining the pre-trained timefeature information model according to the updated feature information base. The feature information can be continuously identified and the feature information base can be updated based on the pre-trained time feature information model under the condition that the target object is not perceived. The identification precision is continuously improved, the requirement on the matching degree of a useris relatively low, and use experience is better.

Description

technical field [0001] The invention relates to the field of information identification, in particular to a method, device, electronic equipment and storage medium for identifying a target object. Background technique [0002] In the prior art, the target recognition technology is widely used in the fields of identity recognition and password unlocking. The usual method is to first extract the characteristics of the target object and establish a reliable model for the target object, and then model them separately; but these features will vary with time. Changes over time (such as gradual aging, beard changes, hair coverage, facial decoration changes, etc.), and these changes will lead to problems such as a decline in the target recognition pass rate and slow recognition speed; in order to maintain the target recognition rate and Recognition speed requires continuous perceptual and purposeful collection and updating of relevant samples and models, which requires a lot of time...

AI Technical Summary

Problems solved by technology

[0002] In the prior art, the target recognition technology is widely used in the fields of identity recognition and password unlocking. The usual method is to first extract the characteristics of the target object and establish a reliable model for the target object, and then model them separately; but these features will vary with time. Changes over time (such as gradual aging, beard changes, hair coverage, facial decoration changes, etc.), and these changes will lead to problems such as a decline in the target recognition pass rate and slow recognition speed; in order to maintain the target recognition rate and Recognition speed requires continuous perceptual and purposeful collection and updating of relevant samples and models, which requires a lot of time and effort, high cost, and poor experience

Images