Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Memory assisting method and device based on face recognition technology

A face recognition and memory technology, applied in the field of image recognition, can solve problems such as being unable to carry around, memory pressure, large equipment, etc., and achieve the effect of strong scalability, complete functions, and wearable

Pending Publication Date: 2021-09-21
SHANGHAI INST OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the equipment is generally too large to be carried around, and the cost is relatively high
[0003] At this stage, many people need to memorize the information of many people, which puts pressure on the memory. For example, teachers need to memorize the information of every student, managers need to memorize the information of every employee, and patients with Alzheimer’s disease need to memorize the information of their family members. information
But in prior art, fail to have a kind of device that is portable and can assist memory

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
  • Memory assisting method and device based on face recognition technology
  • Memory assisting method and device based on face recognition technology
  • Memory assisting method and device based on face recognition technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] see figure 1 , this embodiment provides a memory assistance method based on face recognition technology. Preliminary work is required before face recognition is performed, a suitable development platform is built, and a face database and a voice database are constructed based on this. Specifically, in this implementation, it is first necessary to determine the hardware device to which this embodiment is applied, and select a suitable visual sensor. Since this embodiment needs to be applied to build small, wearable devices, the visual sensor also needs to be small, light and Low cost feature. So a low-cost, powerful Open MV camera is used. With the STM32F427CPU as the core, the OV7725 camera chip is integrated, and the core machine vision algorithm is efficiently implemented through software on a small hardware module. In addition, a Python programming interface will be opened on the machine vision module, which is conducive to the secondary development of developers. ...

Embodiment 2

[0074] see figure 2 , this embodiment provides a face recognition technology-based memory assistance device based on Embodiment 1, and the device adopts the face recognition technology-based memory assistance method as required in any one of Embodiment 1.

[0075] see image 3 , in this embodiment, a memory aid device based on face recognition technology, including: an image acquisition module, an image processing module and a voice module.

[0076] The image acquisition module is used to acquire the face images of the entry personnel and the personnel to be tested.

[0077] The image processing module is used to compare the face image with the images in the pre-stored face database to obtain the corresponding label information of the person to be tested in the face database.

[0078] Based on the face image, the LBP algorithm feature extraction is carried out to obtain the gray feature map of the face image. According to the comparison between the grayscale feature map an...

Embodiment 3

[0082] A computer device, comprising a memory and a processor, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the processor executes the memory based on face recognition technology as in any one of Embodiment 1 helper method.

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 memory assisting method based on a face recognition technology. The memory assisting method comprises the following steps: S1, acquiring a face image of a to-be-detected person; s21, performing LBP algorithm feature extraction to obtain a gray feature map; s22, comparing the gray feature map with a face database to obtain an error value; s23, accumulating and averaging the error values, obtaining the average difference value of each group, and obtaining the minimum difference value. S24, if the minimum difference value is smaller than a preset minimum similar threshold value, taking that the matching information is not found, and ending identification; and if the minimum difference value is greater than a preset minimum similarity threshold value, obtaining corresponding label information of the to-be-detected person in the face database. And S3, broadcasting based on the label information to realize memory assistance. The invention is high in expansibility, is more complete in function, and can accurately recognize a to-be-detected person. The invention is more suitable for the use habit of a user, and is easier to use through voice broadcast; the device constructed on the basis of the invention is more miniaturized, wearable and convenient to use, and effectively reminds a user of the information of the to-be-detected person.

Description

technical field [0001] The invention belongs to the field of image recognition, in particular to a memory assistance method and device based on face recognition technology. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. A series of related technologies that use a video camera or camera to collect images or video streams containing human faces, automatically detect and track human faces in the images, and then perform facial recognition on the detected faces, usually also called portrait recognition and facial recognition. . However, the equipment is generally large and cannot be carried around, and the cost is relatively high. [0003] At this stage, many people need to memorize the information of many people, which puts pressure on the memory. For example, teachers need to memorize the information of every student, managers need to memorize the information of every employee, and patien...

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
IPC IPC(8): G06K9/00
Inventor 牟通宋钰曹扬
Owner SHANGHAI INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products