Image classification method and device, computer equipment and storage medium

Abstract

The embodiment of the invention provides an image classification method and device, equipment and a storage medium, and is applied to the technical field of artificial intelligence, and the method comprises the steps: carrying out the preprocessing of each image in a first image set, and obtaining a second image set; performing gray level compression on each image included in the second image set to obtain a third image set; traversing each image in the third image set by using a preset domain structure to obtain a feature matrix corresponding to each image in the third image set; converting the feature matrix corresponding to each image in the third image set to obtain a texture feature corresponding to each image in the third image set; training the initial deep learning model by using the texture feature corresponding to each image in the third image set to obtain an image classification model; and performing image classification by using the image classification model. According to the invention, the image classification accuracy can be improved. The invention relates to block chain technology, such as obtaining a first image set from a block chain.

Description

technical field [0001] The present application relates to the technical field of image classification, and in particular, to an image classification method, apparatus, computer equipment, and storage medium. Background technique [0002] In the traditional image classification fields such as tile classification and wood classification, it is very difficult to collect a large number of samples, and there is no support for a lot of human and financial resources. In such a small sample and low-cost scenario, it is necessary to quickly and accurately obtain classification results. , then the traditional machine learning classification method becomes the first choice. At present, when using machine learning algorithms to classify images, such as classifying texture images, the most commonly used feature extraction methods include GLCM, LBP, HOG and other methods. However, the inventors have found through experiments that the accuracy of the features extracted by these algorithms...

AI Technical Summary

Problems solved by technology

However, the inventors have found through experiments that the accuracy of the features extracted by these algorithms is not very high, which leads to the low accuracy of image classification

Images