Image recognition and neural network model training method, device and system

Abstract

The invention relates to an image recognition and neural network model training method, device and system and a readable storage medium. The method comprises the steps of obtaining a to-be-identifiedimage; inputting the to-be-identified image into a neural network model, and outputting a target image feature of the to-be-identified image, wherein the neural network model is trained based on eachsample image belonging to a plurality of training data sets, a difference value between data set characteristic distances corresponding to any two training data sets is smaller than a preset thresholdvalue, and the data set feature distance is an inter-data set class feature distance or an intra-data set class feature distance; and performing image recognition processing on the target image features according to a judgment threshold corresponding to the neural network model to obtain an image recognition result of the to-be-recognized image. For different data sets, the method can show relatively balanced image recognition performance.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to an image recognition and neural network model training method, device, system and readable storage medium. Background technique [0002] At present, face recognition tasks are divided into three categories, face verification (verifying whether multiple face images correspond to the same person), face search (finding the image most similar to the face image to be recognized in multiple face images in the bottom library) ) and face image clustering (classifying multiple face images to be recognized). At present, the popular method is to perform different types of face recognition tasks by training deep network models to convert face images into points in feature space (feature space). On this basis, the face recognition task is equivalent to training a good deep network model, converting the face image to be recognized into points in the feature space, that is, ...

AI Technical Summary

Problems solved by technology

In short, for different data sets, the traditional model has the problem of unbalanced performance

Images