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

Face image automatic processing system based on monitoring system

A face image and monitoring system technology, applied in image data processing, image enhancement, image analysis, etc., can solve problems such as time-consuming and laborious, wrong recognition results, and poor face image recognition results

Inactive Publication Date: 2018-08-28
SHANGHAI MARITIME UNIVERSITY
View PDF7 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the field of security and monitoring, face recognition in video images has always been a time-consuming and laborious task. The traditional method of using people to monitor is time-consuming and labor-intensive; in recent years, various face image recognition algorithms have been proposed. These algorithms The recognition effect of face images taken in complex natural environments is not good, and there is usually a certain degree of wrong recognition.
However, when there are only one or two difficult-to-recognize face images for some criminal individuals, it is very easy to generate wrong recognition results for the recognition of difficult-to-recognize face images. When arresting, not only wasting police force, but also causing unnecessary trouble

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
  • Face image automatic processing system based on monitoring system
  • Face image automatic processing system based on monitoring system
  • Face image automatic processing system based on monitoring system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0103] This embodiment implements a process of parameter initialization of the automatic face image processing system based on the monitoring system.

[0104] 1. During the initialization process, the face image screening module receives a collection of gray-scale images of faces and non-faces under natural conditions. The dimensions of these sample pictures are unified into n×n dimensions, and then each sample picture P , construct the integral map PP corresponding to the picture P, then use all the integral maps to initialize the parameters of the cascade classifier, and finally save the trained cascade classifier for the detection process.

[0105] The process of constructing the integral graph PP corresponding to the picture P is as follows:

[0106] For the image P, we start to construct the integral image from the first row and the first column of the matrix, initially set s(1,1)=P(1,1), RR(1,1)=P(1,1) , the construction process is a two-layer loop:

[0107]

[0108...

Embodiment 2

[0157] This embodiment implements a detection process of a face image automatic processing system based on a monitoring system.

[0158] 1. During the detection process of the face image screening module, for each frame image of the video clip within each time interval t, where the value of t is input by the human-computer interaction module, firstly perform face detection on the first frame image , and then label the face detection frame corresponding to each detected face, and then we use the ORB feature-based tracking algorithm to perform multi-target tracking according to the coordinate interval of each face detection frame in the first frame. The tracking algorithm of the ORB feature has low system overhead and can track multiple targets in real time. Therefore, when tracking the second frame, the face detection frame of the second frame is obtained. Considering that the time interval is very short and the size of the face image changes relatively small, Therefore, the si...

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 present invention discloses a face image automatic processing system based on a monitoring system, and relates to a method for automatic identification and processing of a face image in a monitoring image. Aiming at the problems that manual processing of the monitoring image wastes time and labor and the face recognition method is easy to misjudge, the face images to be identified are assessed, two modules are employed to respectively perform processing of face images being easily recognized and being not easily recognized according to an assessment result, a classification result is obtained for the face images being easily recognized, and face images which are easy for human cognition are obtained for the face images being not easily recognized so as to allow each module to separately process one class of images, reduce the complexity degree of each module and improve the processing effects of the modules. The computer processing mode and the human processing mode are reasonablydivided to fully develop the maximum advantages of the two so as to avoid loss generated by wrong recognition of the face recognition algorithm on the premise of greatly reducing the human cost.

Description

technical field [0001] The invention relates to the technical field of computer vision monitoring, image processing and image reconstruction, and in particular to a method for automatically recognizing and processing human face images in monitoring images. Background technique [0002] In the field of security and monitoring, face recognition in video images has always been a time-consuming and laborious task. The traditional method of using people to monitor is time-consuming and labor-intensive; in recent years, various face image recognition algorithms have been proposed. These algorithms The recognition effect of facial images taken in complex natural environments is not good, and there is usually a certain degree of wrong recognition. However, when there are only one or two difficult-to-recognize face images for some criminal individuals, it is very easy to generate wrong recognition results for the recognition of difficult-to-recognize face images. When arresting, not...

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): G06K9/00G06K9/03G06K9/62G06T7/246
CPCG06T7/248G06T2207/30201G06T2207/10016G06V40/16G06V40/161G06V40/168G06V40/172G06V10/993G06F18/22G06F18/24
Inventor 刘昱昊
Owner SHANGHAI MARITIME UNIVERSITY
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com