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

A kind of image recognition method and device including surrounding environment

A surrounding environment and image recognition technology, applied in the information field, can solve problems that do not involve image recognition

Active Publication Date: 2022-07-01
上海日观芯设自动化有限公司
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the patent describes a method and device for image enhancement, which does not involve image recognition, or it is an image enhancement method after distinguishing the foreground and background through other image recognition devices

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
  • A kind of image recognition method and device including surrounding environment
  • A kind of image recognition method and device including surrounding environment
  • A kind of image recognition method and device including surrounding environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] In the prior art, the core convolution layer used in the residual network is pre-added with padding to the image. The input and output matrices of this convolution layer are of the same size, and the residual operation is performed F(x)=H(x)- x. Among them, F(X) is the residual function, which refers to the difference between the output of the module and the output, H(X) refers to the output matrix of the module, and X refers to the input matrix (image matrix) of the module.

[0060] In the prior art, only Chinese patent CN102694961B mentions the technical solution of "edge reduction", but the "edge reduction" in this patent refers to directly removing the pixels at the edge of the image after image processing. This is completely different from the definition of the narrow edge of the present invention, and the purpose of use is also irrelevant. The shrinking edge of the present invention refers to removing the characteristic elements of the matrix edge in the neuron n...

Embodiment 2

[0093] This embodiment is a further supplement and description to the foregoing embodiment, and repeated content will not be repeated.

[0094] This embodiment provides an image recognition device including a surrounding environment, characterized in that the device at least includes:

[0095] Convolution module for extracting image matrix based on convolution layer;

[0096] A shrinking unit, which is used to perform at least one shrinking process on the image matrix;

[0097] The residual unit is used to perform at least one non-reduced residual processing on the image matrix after the edge reduction processing;

[0098] The fully connected layer module is used to output the recognized image data based on the fully connected layer. Wherein, the edge reduction unit is arranged between the convolution module and the residual unit. That is, the convolution module is arranged at the data input end and connected to the edge reduction unit, so as to input the image matrix extra...

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 an image recognition method and device including surrounding environment. The method at least includes the following steps: extracting an image matrix based on a convolution layer; performing edge reduction processing on the image matrix at least once; and processing the image after edge reduction processing. The matrix undergoes at least one non-shrinking residual processing; the recognized image data is output based on the fully connected layer. Among them, the edge reduction module includes a basic edge reduction module and a bottleneck edge reduction module. The edge reduction methods of the basic edge reduction module include: G(x)=conv_2(σ(conv_1(x)))+r(x). Among them, conv_1(x), conv_2(x) represents the convolution transformation without padding on the image matrix x; σ(x) represents the non-linear transformation of the image matrix x; r(x) represents the edge reduction of the image matrix x . Establishing a neural network through the edge shrinking module can better identify images including the surrounding environment and reduce the amount of calculation.

Description

Technical field [0001] The present invention relates to the field of information technology, and in particular to an image recognition method and device including surrounding environment. Background technique [0002] Image recognition through deep learning is the hottest development direction and most successful application direction of artificial intelligence today. Using deep learning to recognize images has great value in aspects such as identity authentication, security, autonomous driving, and even integrated circuit design and garbage classification. [0003] The specific method of using deep learning for image recognition is to construct a convolutional neuron network; collect massive images (data) and their classification labels; use these data and labels to train the convolutional neuron network and establish corresponding models; In practical applications, the established model is used to recognize input images. [0004] In recent years, with the improvement and...

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): G06V10/26G06V10/44G06V10/46G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V10/44G06V10/26G06V10/764G06V10/82
Inventor 杜宇
Owner 上海日观芯设自动化有限公司