Method, system, device and readable storage medium for image feature extraction

Abstract

The application discloses a method for image feature extraction, including: obtaining an image matrix, a convolution kernel, and convolution characteristic parameters; dividing the convolution kernel and the image matrix into corresponding The convolution block and the image block; sequentially multiply the convolution block and the image block, and determine that the obtained multiplication result is the feature matrix of the image matrix. This application divides the convolution block and the image block, then sequentially multiplies the convolution block and the image block, and finally calculates the processing result of the image matrix according to the obtained multiplication result, so that the entire convolution calculation process eliminates unnecessary multiplication Operation reduces the demand for storage units, and through the multiplexing of parallel operation units, under the premise of using limited storage units, the improvement of high-speed operation is realized, which greatly improves the speed of image feature extraction. The present application also provides a system, device and readable storage medium for extracting image features, which have the above beneficial effects.

Description

technical field [0001] The present application relates to the field of image feature extraction, and in particular, to a method, system, device and readable storage medium for image feature extraction. Background technique [0002] With the development of science and technology, machine learning is involved in many fields. As the most cutting-edge branch of machine learning, deep learning has also developed rapidly in recent years. The convolutional neural network model is a widely used algorithm model in deep learning, and the convolutional neural network model is usually used as the backbone in the image feature extraction model. [0003] However, as the complexity of convolutional neural networks continues to increase, the amount of computation is also increasing, but there are limitations in computer resources, resulting in slow image feature extraction. [0004] Therefore, how to improve the speed of image feature extraction is a technical problem that needs to be solv...

AI Technical Summary

Problems solved by technology

[0003] However, as the complexity of the convolutional neural network continues to increase, the amount of calculation is also increasing, but there are limitations in computer resources, resulting in slow image feature extraction.

Images