An Image Processing Method of Coded Pulse Sequence

Abstract

The invention discloses an image processing method for encoding pulse sequences, which encodes multi-level information on images, and encodes information on different levels of the images into pulse sequences according to the time sequence; including: converting the image into a grayscale image and converting the image Standardize the gray value of the gray image; encode the shape, feature points, color, and texture of the gray image into pulses; then arrange the encoded pulses in a set order to form a series of pulse sequences. The invention effectively utilizes the information of various levels carried by the image, and reduces non-key information at the same time. For the spiking neural network, the information completeness of the spiking sequence input by the neural network is improved, the redundancy of information is reduced, and the information processing efficiency of the spiking neural network can be improved. For signal processing, the information capacity of the information source and the coding efficiency of information are improved.

Description

technical field [0001] The invention belongs to the technical fields of brain-inspired computing, pulse neural network, and image coding, in particular to a method for encoding an image into a pulse sequence, and in particular to an image processing method applied in the field of pulse neural network information processing. Background technique [0002] In recent years, the field of brain-inspired computing has gradually attracted the attention of many scholars. Researchers have carried out research in the fields of biological neurons, connection methods, and spiking neural networks, trying to model the brain from the microscopic to the macroscopic level, and further advance the current state of the art. The artificial intelligence process based on deep learning technology will eventually achieve the goal of general artificial intelligence. [0003] Spiking Neuron Networks (SNN, Spiking Neuron Networks) is known as the "third-generation neural network". The methods are more...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of serious information loss and low encoding efficiency in the process of encoding images into pulses in the current prior art, the present invention provides a new image pulse encoding method, which extracts the information of the original image at multiple levels , which greatly reduces the information loss caused by encoding the image into pulses, and the length of the pulse sequence generated by encoding is relatively short (generally within 10 pulse frames), which effectively improves the encoding efficiency

Images