Image classification method, device, electronic equipment and storage medium

Abstract

Embodiments of the present invention provide an image classification method, device, electronic equipment, and storage medium, wherein the image classification method includes: obtaining an image to be classified; inputting the image to be classified into a pre-trained convolutional neural network model to obtain the image to be classified The image is the confidence of each category; according to the relationship between the preset confidence threshold of each category and the confidence of the image to be classified as the category, the category of the image to be classified is determined, wherein the preset confidence threshold of each category makes: For each of the categories, the convolutional neural network model is used to predict the samples in the predetermined threshold adjustment sample set to obtain the confidence that the samples belong to the category, and when the confidence of the category is greater than the preset value of the category When the category of the sample with the confidence threshold is predicted as this category, the recall rate of this category is greater than the preset recall rate and / or the precision rate is greater than the preset precision rate. Through this solution, the detection rate of images of various categories can be improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image classification method, device, electronic equipment and storage medium. Background technique [0002] With the continuous development of Internet technology and multimedia technology, due to the advantages of intuitiveness and rich information, videos and images not only increase sharply in number, but also emerge in an endless stream. However, at the same time, images may be mixed with All kinds of pornographic and sensitive content seriously endanger the physical and mental health of people (especially minors). [0003] Therefore, it is necessary to classify and manage images to prevent the dissemination of illegal images. At present, with the continuous development of convolutional neural network technology, it has also been widely used in the image classification process. The image classification method based on convolutional neural network includes...

AI Technical Summary

Problems solved by technology

Using the above method for image classification detection can ensure that the number of correctly classified samples in the image samples meets certain requirements, but the detection accuracy of the illegal graphics to be detected cannot be guaranteed. For example: for a total of 100 image sample sets ( The number of image samples actually belonging to illegal images is 40; the number of image samples actually belonging to normal images is 60), through the above method, it can be ensured that the number of samples correctly classified meets the preset index (for example: the preset index is 80, That is, the correctness is 80%), but in the correctly classified samples, there may be 60 samples that actually belong to normal images, and only 20 samples that actually belong to illegal images. At this time, the samples that actually belong to illegal images The accuracy of classification is only 50%, that is, the detection rate of illegal images is low, and the ability to detect illegal images is weak

Images