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

Association identification method and equipment based on generative adversarial network

A recognition method and generative technology, applied in the field of target recognition, can solve problems such as restricting the practical process and application scenarios of target recognition technology, increasing system complexity, affecting recognition speed, etc., and shortening the time for data collection and processing.

Pending Publication Date: 2021-08-17
XI AN JIAOTONG UNIV
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, this method virtually increases the complexity of the system and affects the recognition speed, which restricts the practical process and application scenarios of target recognition technology

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
  • Association identification method and equipment based on generative adversarial network
  • Association identification method and equipment based on generative adversarial network
  • Association identification method and equipment based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0036] see figure 1 , the present invention uses the handwritten picture corresponding to the letter ABCDEFGHIJ and the number 0123456789 as the target object, and defines the category label corresponding to the target ABCDEFGHIJ and 0123456789 as 0123456789. After the GAN network training is completed, the test data is input and the corresponding category label is output.

[0037] see figure 2 , the present invention is based on the association recognition method of generative confrontation network, mainly comprises the following steps:

[0038] S1. Taking the category of the object to be recognized as the target of network training, and applying a set of random speckle sequences to objects of the same type and different shapes as the object to be recognized, including the following steps: using a set of known sequences of random speckles i...

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 correlation recognition method and device based on a generative adversarial network, and the method comprises the following steps: taking the type of a to-be-recognized object as a network training target, enabling a random speckle sequence to act with objects of the same type and different shapes of the to-be-recognized object, and forming a barrel detection signal array of the objects through multiple times of sampling. Different objects correspond to different barrel detection signal arrays, the barrel detection signal arrays serve as samples of network training, and a generative adversarial network is used for training; after training is completed, a random speckle sequence used in the training process is used for detecting a target object, corresponding bucket detection signals are collected, and a corresponding bucket detection signal array is formed after multiple times of sampling is completed; and the bucket detection signal array is input into the trained generative adversarial network, and the category of the target object is output. According to the invention, the method achieves the recognition without depending on the target image information, and can greatly shorten the data collection and processing time.

Description

technical field [0001] The invention belongs to the field of target recognition, and relates to an association recognition method and equipment based on a generative confrontation network. Background technique [0002] Target recognition has always been an important and difficult problem in the fields of national economy and military warfare. At present, the recognition technology based on target image information greatly depends on the quality of target image information acquisition, as well as the quality of processing and analysis of acquired images. At the same time, this method virtually increases the complexity of the system and affects the recognition speed, which restricts the practical process and application scenarios of target recognition technology. Correlation imaging, also known as quantum imaging or ghost imaging, is a new imaging technology developed on the basis of quantum entanglement. In 1995, it was completed for the first time by Chinese scientists Shi...

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): G06K9/62G06N3/04
CPCG06N3/048G06F18/2132G06F18/2415G06F18/214
Inventor 贺雨晨陈薏冰陈辉郑淮斌徐卓
Owner XI AN JIAOTONG UNIV