Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Digital integration processing method based on CNN cellular neural network structure

A technology of network structure and processing method, applied in the field of digital integrated processing, can solve the problems of high power consumption of large image operation, lack of two-dimensional computing ability, controlled structure and data, etc., to reduce the probability of burrs, reduce power consumption, eliminate load effect

Pending Publication Date: 2021-06-15
北京微芯智通科技合伙企业(有限合伙)
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, to solve the problem of the weak parallel processing ability of the computing unit of the traditional architecture processor, the computing unit with large throughput is not strong in independent computing ability, and is limited by the structure and data. The problem of missing and high power consumption for large image operations is particularly important

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Digital integration processing method based on CNN cellular neural network structure
  • Digital integration processing method based on CNN cellular neural network structure
  • Digital integration processing method based on CNN cellular neural network structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to deepen the understanding of the present invention, the present invention will be further described below in conjunction with examples, which are only used to explain the present invention and do not constitute a limitation to the protection scope of the present invention.

[0035] The system structure block diagram of the CNN cellular neural network operation unit is as follows: figure 1 , figure 2 As shown, taking image processing as an example, after the image passes through the buffer unit, it is expanded on the cell circuit unit in units of pixels, and all the cell units in the cell unit circuit set simultaneously process all the corresponding pixels of the image and the pixels in the surrounding neighborhood. Points are calculated according to the connection relationship. Refine to each cell unit circuit, take a certain pixel in the image as the processing object, and the circuit transfers the pixel information of the object image, the operation surro...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a digital integrated processing method based on a CNN cellular neural network structure. According to the method, synchronous and efficient two-dimensional neighborhood matrix calculation is supported, synchronous block calculation is carried out on all points on an image pixel matrix, design of a special chip for efficient image processing is achieved, high efficiency and low power consumption factors are achieved, and the method has the advantage of being low in cost. Thus, various data structures and data precision are supported, and various mainstream protocols and neural network models are perfectly supported.

Description

technical field [0001] The invention relates to the technical field of digital integration processing, in particular to a digital integration processing method based on a CNN cellular neural network structure. Background technique [0002] At present, with the rise of the field of artificial intelligence, the status of image recognition is becoming more and more important. As an important part of the field of image recognition, the computing unit of image processing has also been developing. From general-purpose computing of CPUs to one-dimensional parallel computing of GPUs, proprietary computing integrated circuits are developing more and more rapidly. The computing unit of the existing processor has more or less its own disadvantages: CPU, the classic von Neumann system, is a general-purpose processor, which accesses memory and calls data through the control module addressing to process, and the control logic is complex. Its single computing unit is powerful, but computi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F15/16G06F7/50G06N3/04G06N3/063
CPCG06F15/161G06F7/50G06N3/063G06N3/045
Inventor 蔡群林周君临兰军彭杰展晓宇门爱东黄笑天
Owner 北京微芯智通科技合伙企业(有限合伙)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com