Supercharge Your Innovation With Domain-Expert AI Agents!

MTCNN-based vehicle face alignment method

A vehicle face and vehicle technology, applied in the field of vehicle recognition, to achieve the effect of improving generalization ability and robustness, and improving accuracy

Active Publication Date: 2019-10-11
SHANDONG LINGNENG ELECTRONIC TECH CO LTD +2
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a vehicle face alignment method based on MTCNN, which solves the problem of vehicle face alignment in vehicle face recognition, and effectively improves the generalization ability and accuracy of vehicle recognition

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
  • MTCNN-based vehicle face alignment method
  • MTCNN-based vehicle face alignment method
  • MTCNN-based vehicle face alignment method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] A car face alignment method based on MTCNN, such as figure 1 shown, including the following steps:

[0045] (1) Divide the vehicle data set into a training set and a test set, and use the LabelImg tool to label the training data set;

[0046] Before step (1), it also includes preparing the vehicle data set. The vehicle data set here is a plurality of vehicle face images. It is necessary to ensure that the collected vehicle images contain vehicle faces and have changes in scale and scene, that is, the corresponding The scale and scene should be different, not all the same;

[0047] Step (1) is further:

[0048]Divide the vehicle data set into a training set and a test set, which can be randomly divided. The preferred division ratio is: the training set accounts for 90%, and the test set accounts for 10%. Download and install the LabelImg tool, and change the value in the category file to car. Consider According to the symmetry of the car face, select four feature poin...

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 MTCNN-based vehicle face alignment method, which belongs to the field of vehicle identification, and comprises the steps of dividing a vehicle data set into a training setand a test set, and marking the training data set by using a LabelImg tool; modifying an image reading file in the MTCNN algorithm model, and changing the number of feature points; training an MTCNN algorithm model; specifying a target picture and constructing an image pyramid; importing the image pyramid into the MTCNN algorithm model, and performing first level processing by P-Net; entering an output result of the P-Net into the R-Net for the second level processing; enabling output of R-Net to enter O-Net for third-level processing, identifying the face frames and feature points; and carrying out affine transformation of the output of an MTCNN algorithm model. According to the invention, the key problem of vehicle face alignment in vehicle identification is solved, and the generalization ability and accuracy of vehicle identification are effectively improved.

Description

technical field [0001] The invention relates to a vehicle face alignment method based on MTCNN, which belongs to the technical field of vehicle recognition. Background technique [0002] Vehicle identification has always been based on license plate recognition technology. When there is malicious defacement, covered license plate, fake license plate and bad weather, it is difficult for license plate recognition technology to achieve effective vehicle identification. At this time, a more intelligent vehicle recognition technology based on vehicle characteristics other than the license plate is needed, and the vehicle face can effectively express the appearance attributes of the vehicle, such as differences in brand, car series, model, style, color, and unique signs. Therefore, the vehicle face image can be used to identify the vehicle. The vehicle recognition technology based on vehicle face recognition can be applied to the rapid retrieval and deployment of public security o...

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): G06K9/62G06K9/46
CPCG06V10/462G06V2201/08G06F18/214Y02T10/40
Inventor 朱顺意范继辉李广立瞿明军刘雪健周莉巩志远陈建学杜来民邓国超白玥寅张松周雨晨
Owner SHANDONG LINGNENG ELECTRONIC TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com