Impulsive neural network-based image feature describing and memorizing method

Abstract

The invention provides an impulsive neural network-based image feature describing and memorizing method. the method comprises steps: M normalized images are inputted, the layer number of the impulsive neural network is determined according to the size of the image, a gradient direction at each pixel point is acquired when pretreatment is carried out on the images, the gradient direction is discretized into a preset individual value, distribution of one of each preset value number of neurons in the first layer in the impulsive neural network is determined according to the discretized gradient direction, membrane potential of neurons in the second layer and the distribution condition of the neurons in the second layer are calculated according to the distribution condition of the neurons in the first layer, the distribution conditions of the neurons in all layers are obtained, a connection weight of each layer of the impulsive neural network is adjusted according to a timing relationship for distribution of neurons in all layers and a STDP (Spike Timing-dependent Plasticity) rule, and the image features are described and memorized in a connection weight form. The method of the invention can describe and memorize images of various kinds, can completely restore an image, and also has an image classification function.

Description

Technical field [0001] The present invention relates to the technical field of computer vision, in particular to an image feature description and memory method based on a spiking 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 independently. At present, computer vision is widely used in industry, military and other fields, and specific applications include robot path planning, UAV reconnaissance, and autonomous combat. However, to realize 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 rec...

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