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

IQ adjustment method and adjustment module based on AI face detection

A face detection and adjustment method technology, applied in the computer field, can solve problems such as global rough image adjustment, and achieve the effect of improving the detection and recognition rate

Inactive Publication Date: 2021-02-19
SENSLAB INC
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing image processing scheme uses the ISP that comes with the main chip to debug multiple sets of fixed values ​​to match the images acquired in different environments. It is a global and rough image adjustment. In addition, the ISP parameters of the product are set through The method of burning firmware is burned into the product, and the algorithm requirements cannot be changed with the environment change. When updating, it must be updated manually or online in the background.

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
  • IQ adjustment method and adjustment module based on AI face detection
  • IQ adjustment method and adjustment module based on AI face detection
  • IQ adjustment method and adjustment module based on AI face detection

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example ；

[0092] Such as figure 1 As shown, the present invention provides a kind of IQ adjustment method based on AI face detection, comprising the following steps:

[0093] S1, acquiring an image, the image is an image generated based on initial IQ parameters carried by the product firmware;

[0094] S2, acquiring the coordinates of the face position;

[0095] S3, draw a face frame according to the coordinates of the face position, and calculate and obtain an evaluation value of the face frame image;

[0096] S4, repeatedly adjusting the target exposure value of the face frame image according to the evaluation value until the evaluation value of the face frame image is greater than the evaluation threshold;

[0097] S5, adjusting gamma and contrast of the face frame image to predefined values;

[0098] S6, uniformizing the brightness of the face frame image;

[0099] S7, store the adjusted IQ parameters in the SD card, replace and cure the original parameters through the register ...

no. 2 example ；

[0102] Such as figure 2 As shown, the present invention provides a kind of IQ adjustment method based on AI face detection, comprising the following steps:

[0103] S1, acquiring an image, the image is an image generated based on initial IQ parameters carried by the product firmware;

[0104] S2, obtaining the coordinates of the face position, step S1 includes the following sub-steps;

[0105] S2.1, obtain the face position through the face detection algorithm;

[0106] S2.2, calculate the face boundary through the first-order differential operator and the second-order differential operator to obtain the position coordinates of the upper left corner and the lower right corner of the face frame; correspondingly, the face frame can completely pass the face detection in the prior art get;

[0107] S3, draw a face frame according to the coordinates of the face position, and calculate the gray mean value of the face frame image to obtain the mean value of the face, and the Mean...

no. 3 example ；

[0120] Such as image 3 As shown, the present invention provides a kind of IQ adjustment method based on AI face detection, comprising the following steps:

[0121] S1, acquiring an image, the image is an image generated based on initial IQ parameters carried by the product firmware;

[0122] S2, obtaining the coordinates of the face position, step S1 includes the following sub-steps;

[0123] S2.1, obtain the face position through the face detection algorithm;

[0124] S2.2, calculate the face boundary through the first-order differential operator and the second-order differential operator to obtain the position coordinates of the upper left corner and the lower right corner of the face frame;

[0125] S3, draw the face frame according to the coordinates of the face position, and count the gray value probability of the face frame image, the gray value calculation formula: Gray(i,j)=0.299*R(i,j)+0.587*G( i,j)+0.144*B(i,j), i,j represent the coordinates of the pixel;

[012...

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 IQ adjustment method based on AI face detection. The method comprises the steps: acquiring an image, acquiring face position coordinates, drawing a face frame according to the face position coordinates, calculating to obtain an evaluation value of a face frame image ,repeatedly adjusting the target exposure value of the face frame image according to the evaluation valueuntil the evaluation value of the face frame image is greater than an evaluation threshold, adjusting the gamma and the contrast of the face frame image to be predefined values, uniformizing the brightness of the face frame image, and outputting the adjusted picture for living body detection. The invention also discloses an IQ adjustment module based on AI face detection. According to the invention, after face detection is carried out on the blurred image, IQ adjustment can be carried out on the detected face frame image, and the detection and recognition rate of a face detection algorithm canbe improved.

Description

technical field [0001] The invention relates to the field of computers, in particular to an IQ adjustment method based on AI face detection. The invention also relates to an IQ adjustment module based on AI face detection. Background technique [0002] The research on Face Detection can be traced back to the 1960s, and its main goal is to determine whether there is a face in the image. Face detection is a biometric technology for identification based on human facial feature information. A series of related technologies that 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 are usually also called portrait recognition and facial recognition. The recent face detection algorithm adopts different methods according to the specific application, combining template matching, statistical learning, principal component analysis, skin color information, etc. to ach...

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): G06K9/00G06K9/32G06T5/00G06T7/13G06T7/62G06T7/90
CPCG06T7/13G06T7/90G06T7/62G06V40/161G06V10/25G06T5/90
Inventor 袁珊珊
Owner SENSLAB INC