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

An Image Classification Method Based on Layer Adaptive Convolutional Neural Network

A technology of convolutional neural network and classification method, applied in the field of image classification based on layer adaptive convolutional neural network, can solve the problem that all categories cannot be distinguished well

Active Publication Date: 2021-07-30
聚时科技(江苏)有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides an image classification method based on layer number self-adaptive convolutional neural network, which is used to solve the existing image classification method based on convolutional neural network. distinguish good questions

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
  • An Image Classification Method Based on Layer Adaptive Convolutional Neural Network
  • An Image Classification Method Based on Layer Adaptive Convolutional Neural Network
  • An Image Classification Method Based on Layer Adaptive Convolutional Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0033] In the description of the embodiments of the present invention, it should be noted that unless otherwise specified and limited, the terms "first", "second" and "third" are for the purpose of clearly explaining the numbering of product parts and do not represent any substantive gender distinction. The directions of "up", "down", "left"...

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 present invention relates to the technical field of computer vision, in particular to an image classification method based on a layer number self-adaptive convolutional neural network, including an input module, a basic network module, a layer number self-adaptive network module and an output module. It assigns labels, builds a neural network module based on layer number adaptation, sets training parameters, trains the neural network, and tests the neural network to obtain a layer number-based adaptive convolutional neural network. Share a small number of low-level features, and each has its own independent high-level structure classification network to achieve the purpose of using the same convolutional neural network to complete the classification of all image categories contained in the batch images generated in the actual application scene.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to an image classification method based on a layer number self-adaptive convolutional neural network. Background technique [0002] In recent years, with the continuous deepening of research on convolutional neural networks, image classification technology has also developed rapidly. Typical image classification techniques based on convolutional neural networks include: two-category image classification, multi-category image classification, multi-label image classification, image classification based on Few-Shot Learning and Zero-Shot Learning. image classification, etc. [0003] However, in practical application scenarios, some problems cannot be effectively solved by using the above-mentioned image classification technology, such as industrial inspection scenarios. In industrial quality inspection, the most important criteria for judging are the false negative rate and t...

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 Patents(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08
Inventor 罗长志李煜
Owner 聚时科技(江苏)有限公司