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

A method for two-dimensional grayscale image detection, recognition and classification

A grayscale image, recognition and classification technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve problems such as failure to obtain ideal classification results, time-consuming and labor-intensive, etc., to reduce manpower and material resources and improve accuracy. efficiency, reducing workload

Active Publication Date: 2022-06-28
GUILIN UNIV OF ELECTRONIC TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In many fields, traditional manual classification is time-consuming and laborious, and sometimes it may not be able to obtain ideal classification results after spending a lot of money

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 method for two-dimensional grayscale image detection, recognition and classification
  • A method for two-dimensional grayscale image detection, recognition and classification
  • A method for two-dimensional grayscale image detection, recognition and classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0056] refer to figure 1 , figure 2 , a method for detecting, identifying and classifying two-dimensional grayscale images, comprising the following steps:

[0057] 1) Obtain a two-dimensional grayscale image: obtain a two-dimensional grayscale image;

[0058] 2) Constructing a two-dimensional convolution block: adding an ELU activation function and a batch normalization layer after each two-layer two-dimensional convolutional neural network, and adding a two-dimensional maximum pooling layer after two iterations to form a two-dimensional convolution block;

[0059] 3) Feature extraction: input the two-dimensional grayscale image obtained in step 1) into a two-dimensional convolution block for preliminary feature extraction;

[0060] 4) Obtain feature map: the two-dimensional max pooling layer performs feature mapping after the convolution layer, extracts and obtains the feature map;

[0061] 5) Extracting time information: reshape and decompose the feature map obtained in...

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 discloses a method for detecting, identifying and classifying two-dimensional grayscale images, which is characterized in that it comprises the following steps: 1) obtaining a two-dimensional grayscale image; 2) constructing a two-dimensional convolution block; 3) extracting features; 4) Obtain the feature map; 5) Extract time information; 6) Retain and discard; 7) Selectively shield nodes; 8) Obtain the final classification result. This method is based on a model combining two-dimensional convolutional neural network and long-term short-term memory network to detect and classify images, which can improve the accuracy of classification.

Description

technical field [0001] The invention relates to the field of artificial intelligence deep learning, in particular to a method for detecting, identifying and classifying two-dimensional grayscale images based on a combined model of a two-dimensional convolutional neural network and a long-term and short-term memory network, in particular to a method for two-dimensional grayscale image detection, recognition and classification. A method for image detection, recognition and classification. Background technique [0002] Artificial intelligence is a discipline that studies how computers simulate or realize human learning behaviors to acquire new knowledge or skills, and to reorganize existing knowledge structures to continuously improve their performance. The detection, recognition and classification of image information has always been a hot topic and focus of research. In many fields, traditional manual classification is time-consuming and labor-intensive, and sometimes it may...

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): G06V10/774G06V10/764G06K9/62G06N3/04
CPCG06N3/044G06N3/045G06F18/214
Inventor 陈真诚郑震宇梁永波朱健铭韩国成魏子宁唐群峰
Owner GUILIN UNIV OF ELECTRONIC TECH