Unlock instant, AI-driven research and patent intelligence for your innovation.

A real-time face detection and recognition system based on miz702n

A face detection and recognition system technology, applied in the field of face detection and recognition, can solve the problems of high cost, unfavorable marketization, slow operation speed, etc., achieve the effect of low power consumption and meet real-time requirements

Active Publication Date: 2021-06-29
SOUTHEAST UNIV WUXI INST OF TECH INTEGRATED CIRCUITS +1
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the slow calculation speed on the PC and the high cost of using the GPU, it is not conducive to marketization

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
  • A real-time face detection and recognition system based on miz702n
  • A real-time face detection and recognition system based on miz702n

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Attached below figure 1 and figure 2 The present invention will be further described.

[0023] High-performance real-time face detection and recognition system framework construction:

[0024] There is MIPI interface on MiZ702N, which supports a variety of expandable devices. The OV5640 image sensor is connected with the MiZ702N through the MIPI interface. At the same time, the MiZ702N has a VGA interface, which can be used for video algorithm development. The architecture diagram of this system is shown in figure 1 shown.

[0025] System structure design:

[0026] The source of the data stream is the OV5640 image sensor. The RGB565 format data obtained by the image sensor is sent to the Sensor module, which processes the data to obtain 24-bit wide data. After that, the data is converted into a form that satisfies the AXI_Stream bus interface protocol through the Video in ToAXI-Stream module, and the data is sent to the AXI bus. Then the image data is sent to ...

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 real-time face detection and recognition system based on MiZ702N, which includes an image sensor, a MiZ702N development board, and a VGA display; the MiZ702N development board includes a video input module, a memory, a CPU, a neural network accelerator, and a video output module; the image sensor collects The video information is sent to the video input module, and then the single frame image is stored in the memory; the CPU obtains the image information from the memory, and after image preprocessing, the preprocessed image is stored in the memory; the neural network accelerator obtains the image information from the memory Obtain the preprocessed image for face detection and face recognition operations, and then return the operation results to the memory; the CPU processes the image according to the operation results; the video output module obtains the image processed by the CPU from the memory, and finally outputs the data to the VGA monitor. The invention has the advantages of fast internal bus data transmission speed, high neural network parallelism, and real-time and accurate detection and recognition of human faces.

Description

technical field [0001] The invention relates to the technical field of face detection and recognition, in particular to a real-time face detection and recognition system based on MiZ702N. Background technique [0002] As a main application direction of artificial intelligence, face detection and recognition has been widely used in many daily life fields such as home security, enterprise management, and social security, and plays an extremely important role. Especially in terms of social security, the face detection and recognition technology using neural networks can accurately analyze the image information in the monitoring, and extract the character information required by the public security personnel for comparison, which can effectively protect the public safety in the public environment, and at the same time. facilitate the arrest of suspects. [0003] Previous traditional face detection and recognition algorithms mostly used pattern recognition or statistical classif...

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): G06K9/00
CPCG06V40/161G06V40/172G06V10/955
Inventor 陆生礼李硕庞伟韩志周世豪沈志源
Owner SOUTHEAST UNIV WUXI INST OF TECH INTEGRATED CIRCUITS
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