Ship security data recognition-based face picture compensation recognition method

A technology of data recognition and recognition method, which is applied in the field of face image compensation and recognition, can solve the problems of fat and thin face deformation, fat and thin faces cannot be recognized, etc., so as to reduce the impact, improve the accuracy, and improve the detection accuracy.

Active Publication Date: 2021-10-22
NANTONG HAIOU LIFE SAVING & PROTECTION EQUIP
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the difference in focal length when recognizing faces, the face will be fat and thin, and the face will not be recognized due to changes in the degree of fat and thin.

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
  • Ship security data recognition-based face picture compensation recognition method
  • Ship security data recognition-based face picture compensation recognition method
  • Ship security data recognition-based face picture compensation recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, this embodiment provides a face picture compensation recognition method based on ship security data recognition, including:

[0041] Partition the recognized face picture and the standard face picture respectively, obtain the feature points of the recognized face feature picture in different areas and match them with the standard picture, and obtain the deformation ratio according to the connection line of the feature points.

[0042] Such as figure 2 As shown, a schematic diagram of partitioning face pictures is given. First, control other variables to take a group of pictures with different focal lengths, and use 5mm as the focal length interval to change the focal length, and shoot a group of different focal lengths from 15mm-200mm For a portrait picture, use the pixel coordinates to find the center position of the picture, draw a circle with the center of the picture as the center, and take r as the radius interval until the largest circ...

Embodiment 2

[0090] Such as Figure 4 As shown, the present invention provides a kind of face recognition method, comprises the following contents:

[0091] In one embodiment, the face recognition is performed after compensating the feature points of the recognized face, including: obtaining the compensated feature points of the recognized face, quantifying it to obtain a measure of the degree of fatness and thinness of the face, and then calculating the The degree of fatness and thinness of the face is graded, and the label value of the degree of fatness and thinness of the face is obtained through DNN network training. According to the label value of the degree of fatness and thinness of the face, the weight value of the face contour feature is determined, so as to perform similarity comparison and complete face recognition.

[0092] Generally, the shooting parameter information of the picture is stored in the picture file captured by the camera, so the focal length information of the pi...

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 a ship security data recognition-based face picture compensation recognition method, which comprises the following steps of: respectively carrying out concentric circular ring partitioning on a recognized face picture and a standard face picture, and matching feature points of each region in the recognized face picture with feature points of corresponding regions in the standard picture; respectively obtaining the distance between two corresponding feature points in the recognized face picture and the standard picture, and obtaining a picture deformation proportion according to the distance between the two corresponding feature points; obtaining deformation strength data through the picture deformation proportion; obtaining the deformation quantity of the facial feature points through the deformation strength data; and compensating the feature points according to the deformation quantity. Through the technical method provided by the invention, the influence of the focal length on the fat and thin deformation of the face is reduced, so that the influence on the face recognition precision is reduced, and the detection precision is effectively improved.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a face picture compensation recognition method based on ship security data recognition. Background technique [0002] With the development of modernization, the scale of the ship industry has expanded, and the marine security system has become more and more diversified. At this stage, the face recognition methods used in the marine security system include geometric feature face recognition, line segment distance face recognition, Face recognition method based on deep neural network, etc. Among them, the face recognition method based on geometric features and the line segment distance face recognition method are more sensitive to changes in the face structure, and changes in the proportion of the face structure will affect the accuracy of face recognition. [0003] Face recognition methods at this stage usually compare the similarity between the existing face data pictures ...

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): G06K9/00G06K9/32G06K9/62G06N20/00
CPCG06N20/00G06F18/22
Inventor 曹伟
Owner NANTONG HAIOU LIFE SAVING & PROTECTION EQUIP
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