Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Face image acquisition system for data analysis

An image acquisition system and the technology of the acquisition system are applied to the acquisition of face image data and image data acquisition for artificial intelligence neural network, which can solve the problems of large device length, output error, and poor experience

Pending Publication Date: 2020-02-21
BEIJING MOMENTA TECH CO LTD
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the camera on the screen is used to shield this part of the light, without restoring the real scene, which will cause output errors after machine learning and affect the use effect
3) It is not easy to collect side images of faces (or large-angle images). If the person needs to turn his head nearly 90 degrees to collect side images, firstly, the experience is not good, and secondly, the gaze point of the human eyes needs to be far away from the side of the person, which will cause load The device length of the fixation point is very large

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 acquisition system for data analysis
  • Face image acquisition system for data analysis
  • Face image acquisition system for data analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, the image acquisition system of the present invention is used to collect the human eye image to obtain the three-dimensional coordinates of the eye, and the specific system is as follows:

[0041] The image acquisition system includes a test frame for a fixed camera provided for the convenience of placing the above-mentioned fixed camera. The test frame can be made of metal materials such as aluminum alloy, or light materials such as plastic. It should be noted that the test frame is not limited to the above-mentioned materials, and any material that can provide the camera with a fixed outdoor test can be used. Used to prepare the test rack.

[0042] The industrial camera is installed on the front of the aluminum alloy support frame.

[0043] For the convenience of description, this embodiment takes 9 industrial cameras as an example to describe the placement positions of the 9 industrial cameras on the fixed structure. The test stand is comp...

Embodiment 2

[0051] Such as figure 2 As shown, the image acquisition system adopted in the present invention includes a bracket 10 for fixing the camera 5 provided for the convenience of placing the above-mentioned fixed camera 5, the bracket 10 is composed of 3 horizontally parallel brackets 2 and 3 vertically aligned brackets 1, a number of bases 3 are arranged on each bracket, on which industrial cameras or light sources can be arranged as required.

[0052] The cross-section of each transverse support 2 and longitudinal support 1 is rectangular, and in the extension direction of each transverse support 2 and longitudinal support 1, on the four faces of the rectangle, bar-shaped grooves or bar-shaped protrusions are arranged. It is used as a guide rail for several bases; and several bases 3 have a shape matching the shape of the guide rail, such as protrusions or grooves.

[0053] In addition, the transverse support 2 and the longitudinal support 1 can also be equipped with threaded r...

Embodiment 3

[0059] The image acquisition system includes a bracket for fixing the camera provided for the convenience of placing the above-mentioned fixed camera. base, on which an industrial camera or light source can be set as required; in addition, each horizontal support and longitudinal support can also have a threaded rod parallel to the extension direction of the support and a motor driving the threaded rod; where the camera, light source, and motor are wired Or connect to the controller in a wireless manner, and the controller is also connected to the server.

[0060] Among them, the wired method is the signal line, and the wireless method is WIFI, Bluetooth, 2G, 3G, 4G and other network connection methods.

[0061] The controller controls the motor to move the camera and light source to the corresponding position, and then controls the camera and light source to cooperate with each other to complete the corresponding image acquisition operation. At the same time, the time of imag...

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 face image acquisition system, and belongs to the field of artificial intelligence. In the prior art, a camera or a camera on a display screen is often used for acquiring face image information, the accuracy of images is influenced or the actual environment cannot be reflected. The invention provides an image acquisition system. The system comprises a plurality of cameras and a support for fixing the plurality of cameras. The support comprises a transverse support body, a longitudinal support body and a plurality of bases arranged on the support. The base is used formounting a plurality of cameras. Natural light in the system can be completely transmitted from the back of the bracket, so that image data acquired by the camera is closer to an outdoor environment,and real training data is provided for face image recognition and human eye view field recognition in the driving field.

Description

technical field [0001] The invention relates to the field of image data collection for artificial intelligence neural networks. Specifically, it is the collection field of face image data involved. Background technique [0002] With the development of artificial intelligence, face recognition technology is playing an increasingly important role. With the improvement of image resolution, the application fields of face recognition are becoming wider and wider. By acquiring face images and deep learning neural networks, various information required by various application fields are output. For example, through the recognition of facial expressions, it is possible to judge the mental state of the person at the time; in addition, through the real-time tracking and recognition of facial expressions and human eye sight, human-computer interaction can be carried out. At this time, human-computer interaction does not need other auxiliary tools such as a mouse, or human gestures an...

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): G06K9/00G06N3/08G06T7/80
CPCG06T7/80G06N3/08G06T2207/10016G06V40/166G06V40/172
Inventor 侯喆
Owner BEIJING MOMENTA TECH CO LTD
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
Eureka Blog
Learn More
PatSnap group products