Image recognition method of motor vehicle and driver file based on convolutional neural network

A convolutional neural network and image recognition technology, applied in the field of deep learning, can solve problems such as classification errors, difficult classification errors, and labor-intensive problems, achieving high accuracy, avoiding human identification, and fast execution speed

Active Publication Date: 2021-12-07
HANGZHOU TRUSTWAY TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are many categories of motor vehicle and driver file images, and due to the existence of a large amount of historical data, images of the same category also have the characteristics of huge differences in style. For these reasons, based on past experience, when uploading images through manual identification, it is inevitable that Classification errors and other phenomena, and there is a large amount of unclassified historical data, if manually verified and compared one by one for reclassification, it will consume a lot of labor, and it is difficult to ensure that there will be no reclassification errors during the reclassification process

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
  • Image recognition method of motor vehicle and driver file based on convolutional neural network
  • Image recognition method of motor vehicle and driver file based on convolutional neural network
  • Image recognition method of motor vehicle and driver file based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with accompanying drawing. Such as figure 1 Shown, the present invention comprises the steps:

[0020] Step (1). Data preparation: collect data according to the categories of motor vehicle and driver profile images, collect enough data for each category, and place them in the same folder, and the folders are named according to the category name.

[0021] Step (2). Data segmentation: According to the preset ratio ratio, the vehicle and driver profile image data set is divided into a training set and a test set, and data segmentation for each category is performed according to the ratio ratio.

[0022] Step (3). Data preprocessing: uniformly convert the images in the training set and test set to the specified size: width*height*3, where width is the width of the image, and height is the height of the image. Then convert the image pixel value tensor x and its label of uniform size into an input data for...

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 recognizing images of motor vehicle and driver files based on convolutional neural networks; The convolutional neural network trained by the file images of bullet trains and drivers has a high recognition accuracy. The invention realizes automatic identification and classification of motor vehicles and driver file images, and has the characteristics of fast execution speed, high accuracy, high efficiency and the like. Avoid a lot of manual identification and classification work.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and in particular relates to a method for recognizing images of motor vehicle and driver files based on a convolutional neural network. Background technique [0002] With the development of economy and society, the penetration rate of the Internet is getting higher and higher, and a large number of image resources are generated, transmitted and received on the Internet at all times. Image resources contain a lot of information that is beneficial to the economy and society. With such a large number of image resources, manual recognition will consume a lot of labor and costs, so it is particularly important to use computers to complete image recognition tasks. [0003] With the introduction of "Internet +", a large number of image resources in various fields will be uploaded to the Internet. With the gradual increase of urban population and the rapid growth of car ownership, the data volume ...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/214G06F18/24
Inventor 黄冬发陈教王天然李万清
Owner HANGZHOU TRUSTWAY TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap