Unlock instant, AI-driven research and patent intelligence for your innovation.

Training method of convolutional neural network model for image processing

A convolutional neural network and image processing technology, applied in the field of image processing, can solve problems such as memory space shortage

Active Publication Date: 2022-03-25
HANGZHOU SUPERACME MICROELECTRONICS TECH CO LTD
View PDF15 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the memory space of smart devices is usually tight, so it is expected that only a small amount of memory space will be occupied when image processing is performed on the smart device side

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
  • Training method of convolutional neural network model for image processing
  • Training method of convolutional neural network model for image processing
  • Training method of convolutional neural network model for image processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Various exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be noted that relative arrangements of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

[0022] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way intended as any limitation of the disclosure, its application or uses. That is, the structures and methods herein are presented by way of example to illustrate various embodiments of the structures and methods of this disclosure. However, those skilled in the art will appreciate that they illustrate merely exemplary, and not exhaustive, ways in which the disclosure may be practiced. Furthermore, the figures are not necessarily to scale and some features may be exaggerated to show details of...

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 relates to a training method of a convolutional neural network model for image processing. A training method of a convolutional neural network model for image processing is characterized in that the method comprises the steps that a convolutional neural network model to be trained is constructed, and parameters of the convolutional neural network model comprise one or more original convolution kernels and one or more sets of convolution kernel generation parameters; training the one or more original convolution kernels and the one or more groups of convolution kernel generation parameters by using a training set image, during training, generating a derivative convolution kernel based on at least one part of the original convolution kernels by using each group of convolution kernel generation parameters, and generating one or more derivative convolution kernels based on at least one part of the derivative convolution kernels; and performing convolution processing on the image features of the training set image by using the one or more original convolution kernels and the generated one or more derivative convolution kernels.

Description

technical field [0001] The present disclosure relates to image processing on the smart device side. [0002] Specifically, it relates to a training method of a convolutional neural network model for image processing on the smart device side, using the image processing method of the convolutional neural network model trained in this way, and storing the computer storage medium of the above method on it to realize An image processing device according to the above method and an intelligent device including the image processing device. Background technique [0003] At present, in smart devices (such as mobile phones, tablet computers, smart cameras, smart gates, etc.), there is a wide demand for image processing technology. For example, in a smart camera, image processing is required to realize functions such as face recognition and beauty. [0004] The convolutional neural network model used in existing image processing methods is relatively large, requiring a large number of...

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): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 艾国杨作兴房汝明向志宏
Owner HANGZHOU SUPERACME MICROELECTRONICS TECH CO LTD