An image recognition method based on hierarchical feature extraction and multi-layer spiking neural network

Abstract

The invention discloses an image recognition method based on layered feature extraction and multi-layer pulse neural network. According to the visual information processing method of the visual cortex, the present invention introduces the sparse feature and feature autonomous learning method on the basis of the HMAX model, so that the hierarchical feature extraction results can reasonably retain effective information, and through multiple The layer spiking neural network model realizes the training and recognition of the extracted data. In addition, phase encoding is used as a bridge between hierarchical feature extraction and multi-layer spiking neural network, which effectively converts pixel information into time information and improves recognition accuracy. The image recognition method of the present invention not only satisfies biological characteristics but also has good classification performance; in the process of hierarchical feature extraction, manual features and autonomous learning features are combined to better meet different needs; at the same time, multi-layer pulse neural networks are used to perform Recognition and classification can effectively handle complex data.

Description

technical field [0001] The invention relates to the field of impulse neural networks, in particular to an image recognition method based on layered feature extraction and multi-layer impulse neural networks. Background technique [0002] At present, a series of computational models have been used to simulate the input-output relationship of visual information in the visual cortical area. These models focus on the representation of information, motion state, color texture, etc. or focus on specific functions, such as object recognition, boundary detection, action recognition, etc. While these models explain the underlying computational mechanisms of vision, they lack biologically grounded explanations. In order to simulate the high-efficiency and low-power characteristics of the visual information processing of the brain's visual cortex, the biological neural network is applied to the computer vision computing model. Based on the biological principles of the visual system, b...

AI Technical Summary

Problems solved by technology

Using probabilistic methods to solve the problem of discontinuous pulse firing in multi-layer spiking neural networks, which leads to difficult feedback

Images