Ear recognition and tracking method based on convolutional neural network

A convolutional neural network and ear recognition technology, applied in the fields of image processing and computer vision, can solve problems such as difficulty in labeling, achieve the effect of small network structure parameters, compressed network size, and easy convergence of training

Active Publication Date: 2022-07-12
SOUTHEAST UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The ears are too small relative to the size of the face, and the features are densely concentrated in a specific area, so it is extremely difficult to label

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
  • Ear recognition and tracking method based on convolutional neural network
  • Ear recognition and tracking method based on convolutional neural network
  • Ear recognition and tracking method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The technical solutions provided by the present invention will be described in detail below with reference to specific embodiments. It should be understood that the following specific embodiments are only used to illustrate the present invention and not to limit the scope of the present invention.

[0041] The present invention provides a three-layer network structure, and the complete processing process is as follows: figure 1 shown. There are three stages in total. The first stage performs face detection and box correction to include the ear area. The second stage performs ear detection on the local area of ​​the head in the first stage to obtain a more accurate ear position. In the third stage, ear feature points are annotated in the ear region. The three stages contain multiple supervised learning processes. Specifically, the ear recognition and tracking method based on convolutional neural network provided by the present invention includes the following steps: ...

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 an ear recognition and tracking method based on a convolutional neural network. Detect to obtain a face image including the ear area; build a second layered neural network for the ear data set and the ear labeling box label, and detect the ear area in the output image in step 1 through training; for the ear data set and ear feature points The label builds a third layered neural network, and automatically labels the ear feature points in the output image in step 2 through training. The present invention adopts a three-level cascaded architecture, which can effectively solve the problems of detection and feature point labeling when the existing ear data set is relatively small. Moreover, the multi-layer network can significantly compress the network size, the network structure parameters are relatively small, and the requirements for video memory in the training stage are not high, the training is easier to converge, and the performance is better under complex conditions.

Description

technical field [0001] The invention belongs to the technical fields of computer vision and image processing, relates to an object detection and feature point location technology, and more specifically relates to an ear recognition and tracking method based on a convolutional neural network. Background technique [0002] Ear recognition and modeling have a very important impact on the realistic rendering of virtual objects. In the field of biometrics, automatic identification from ear images represents an active area of ​​research. The ability to covertly capture images of the ear from long distances makes this technology an attractive option in surveillance and security applications, among other fields of application. Compared with traditional biometric modalities, such as fingerprint, face and iris recognition technology, the ear has its unique advantages: the ear has a stable and rich structure that does not change much with age and is not affected by facial expressions....

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): G06V40/16G06V10/82G06N3/04
CPCG06V40/161G06V40/171G06N3/045
Inventor 林云智王雁刚
Owner SOUTHEAST UNIV
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