Image recognition method and device, medium and confusion perception convolutional neural network

Abstract

The embodiment of the invention discloses an image recognition method, device and equipment, a computer readable storage medium and a confusion perception convolutional neural network. The confusion perception convolutional neural network comprises a prediction classifier, a confusion perception model, a correction classifier group and a probability average layer, and the prediction classifier, the confusion perception model, the correction classifier group and the probability average layer are trained by using a training sample set and are used as traditional convolutional neural network classifiers. The confusion perception model is constructed based on a confusion matrix obtained by cross validation of a prediction classifier on the training sample set. Each correction classifier is obtained by using a confusion perception model as a decision-making system and training confusion class sample data with fuzzy boundaries in the training sample set. The probability average layer outputsa classification result of the to-be-identified image according to the category probability output by the prediction classifier and the category probability output by the target correction classifier, and the target correction classifier is a correction classifier selected by the confusion perception model according to the prediction category of the prediction classifier. The accuracy of image recognition can be improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image classification and recognition, and in particular, to an image recognition method, apparatus, device, computer-readable storage medium, and a confusion-aware convolutional neural network. Background technique [0002] With the rapid development of computer vision technology, the requirements for image classification and recognition are getting higher and higher. Before the image is classified and recognized, the input image is generally subjected to preprocessing steps such as binarization and standardization. Compared with the traditional machine learning method of manual feature extraction and classifier classification, the convolutional neural network is used to automatically extract the features in the image. And the classification method should be more accurate and efficient. [0003] Convolutional Neural Networks (CNN) are a class of feedforward neural networks with deep...

AI Technical Summary

Problems solved by technology

[0006] Although the existing hierarchical classification method can improve the accuracy of classification to a certain extent, it faces the problem of error propagation, that is, the category misclassified by the upper-level classifier is propagated to the lower-level classifier, eventually leading to the inevitable Misclassification

Images