Image feature description and memory method based on spiking neural network

Abstract

The present invention proposes an image feature description and memory method based on a spiking neural network, including: inputting M normalized images, determining the number of layers of the spiking neural network according to the size of the image, and preprocessing the image to obtain Gradient direction of , and discretize it into a preset value, according to the discretized gradient direction, determine one firing of every preset value of neurons in the first layer of the spiking neural network, according to the first layer of neurons The firing situation calculates the membrane potential of the neurons in the second layer to determine the firing situation of the neurons in the second layer, and obtains the firing situation of all layer neurons, according to the timing relationship of the firing of neurons in all layers and the pulse time-dependent synaptic plasticity STDP Regularly adjust the connection weights between the layers of the spiking neural network, and describe and memorize image features in the form of connection weights. The method of the invention can describe and memorize images of various categories, and can restore the images completely, and also has the function of image classification.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to an image feature description and memory method based on a pulse neural network. Background technique [0002] Computer vision is the use of computers and related equipment to simulate biological vision. Its ultimate research goal is to enable computers to observe and understand the world through vision like humans, and have the ability to adapt to the environment autonomously. At present, computer vision is widely used in industry, military and other fields. Specific applications include robot path planning, drone detection, autonomous combat, etc. However, to achieve the above applications, one of the most basic and important research contents is image classification and recognition in computer vision. The research idea is: first, design a description and memory method of image features; then, use this method to describe and memorize training images, and record the desc...

AI Technical Summary

Problems solved by technology

[0004] However, no matter whether the set method or the linear combination method is used to describe the combination of local features of the image, the relative position information between the features will be lost, resulting in the inability to restore the image from the memory. The description and memory are not complete enough

In addition, most of the above methods belong to the category of supervised learning, and the scale is not large. Although they can describe the characteristics of the images in the training sample set well after training, they usually cannot describe images of other categories outside the training sample set well. , need to retrain

Images