Image classification method and device based on pulse neural network

Abstract

The invention discloses an image classification method based on a pulse neural network. The method comprises a step of encoding an externally input image analog quantity into a pulse time series, a step of adding time delay information to the pulse time series and storing the pulse time sequence with the added time delay information into an FIFO memory for buffering, a step of inputting the pulsetime sequence with the currently added time delay information into an IF pulse neuron model to generate a neuron membrane voltage signal, wherein a pipeline architecture is adopted by the IF pulse neuron model and a neuron model calculation method is optimized, and a step of generating a neural pulse sequence based on a Poisson distribution by comparing the membrane voltage signal and a thresholdand carrying out classification and judgment on the membrane voltage signal. According to the image classification method, the pulse neural network has powerful computing power and can simulate various neuron signals and arbitrary continuous functions, the operation efficiency is high, and so the pulse neural network has a hardware realization value.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to an image classification method and device based on a pulse neural network. Background technique [0002] Image classification technology is a very challenging basic problem in the field of image processing and computer vision. Traditional image classification methods use color features, morphological features or texture information to calculate image features, which are all implemented based on pixels, mainly using The spectral characteristics of the image, so the information that can be obtained is limited. [0003] The traditional artificial neural network, that is, the first generation and the second generation neural network, encodes the pulse firing frequency of biological neurons. The output of neurons is generally a simulation of a given interval, and its computing power and biological reality are weaker than that of pulses. Neural Networks. However, at present, ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a kind of image classification method based on the pulse neural network, thereby overcome the disadvantages that the prior art cannot make full use of the characteristics of high parallelism of the neural network, slow processing speed, and high power consumption

Images