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

Face detection method of main sample attention mechanism

A technology of face detection and attention, applied in the field of face detection, to achieve the effect of reducing false detection, increasing detection performance, and improving performance

Active Publication Date: 2021-03-16
成都东方天呈智能科技有限公司
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] To sum up, there are two problems in the existing face detection methods: 1) Separate classification and positioning; 2) Treat all samples equally and independently, ignoring the influence relationship between samples

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 detection method of main sample attention mechanism
  • Face detection method of main sample attention mechanism
  • Face detection method of main sample attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] A face detection method of a primary sample attention, including the following steps:

[0064] Step S100: Collect the image data containing the face in the natural scene, constitutes a training set;

[0065] Step S200: Using the network model to extract the feature map information of the training image, then by the anchor frame filter module to generate a predicted anchor frame set using the predicted coordinate value offset, and divide the prediction anchor frame into candidate Positive samples and candidate negative samples, sorting candidate positive samples and candidate negative samples, respectively;

[0066] Step S300: Finally, the loss function is used to calculate the loss value. The loss function is divided into a category classification loss function and the position regression loss function, and gives a different degree of loss value weights depending on the candidate positive sample and the ranking of candidate negative samples. The sample attention mechanism w...

Embodiment 2

[0079] This embodiment is optimized on the basis of the first embodiment, and the class classification loss function uses a binary cross entropy loss function, and the loss value weight is set according to the sample in the set of samples, which is different importance. The loss weight of the sample assignment, the calculation formula is as follows:

[0080]

[0081] among them:

[0082] It is sorted after normalization.

[0083] The maximum value ranked in the collection;

[0084] Ranking for predicting the anchor box in the collection;

[0085] To convert the weight value of the collections;

[0086] β and γ are parameters of setting adjustment weight values, respectively;

[0087] will Normalize ,

[0088] Tags for real categories,

[0089] To predict the probability value of a certain type,

[0090] Equation (4) i For the positive sample, j For negative samples,

[0091] If the ratio between the predictive anchor frame and the real boundary box is greater than ...

Embodiment 3

[0094] This embodiment is optimized based on the basis of Example 1 or 2, and the position regression loss function uses a classified sensible regression loss function, and the classification and positioning regression is positively correlated, and the classification and position regression branches are optimized, and the prediction anchor frame is calculated. The loss value between the coordinate offset and the real coordinate offset, the calculation formula is as follows:

[0095]

[0096] among them:

[0097] For universal smooth L1 loss functions,

[0098] The category probability value after the adjustment factor is calculated.

[0099] n To the category probability The total number of samples,

[0100] For the returns loss weight value obtained after normalization according to the category probability value,

[0101] For real coordinate offset,

[0102] To predict the coordinate offset;

[0103] The category probability value of the anchor frame,

[0104] b wi...

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 face detection method of a main sample attention mechanism, which comprises the following steps: extracting feature map information of a training image by using a network model, generating a prediction anchor frame set on each feature point of a feature map by using a prediction coordinate value offset by using an anchor frame screening module, and dividing a prediction anchor frame into candidate positive samples and candidate negative samples; sorting the candidate positive samples and the candidate negative samples respectively; and calculating a loss value by using a loss function, dividing the loss function into a category classification loss function and a position regression loss function, endowing loss value weights with different importance degrees according to ranking results of the candidate positive samples and the candidate negative samples, and deflecting the weights to the main samples by using the main sample attention mechanism. According to the method, the importance of the main sample is emphasized in the model training process, and the influence of unimportant samples on model learning is suppressed, so that the performance of the modelis improved, and the method has relatively good practicability.

Description

Technical field [0001] The present invention belongs to the technical field of face detection, and more particularly to a human face detection method of primary sample attention. Background technique [0002] Face detection technology is one of important research in the field of target detection, is the basis for face verification, expression identification, age identification, intelligent monitoring. Face detection technology is divided into single-stage algorithm and two-stage algorithm. The main idea of ​​the former is to set a fixed-size anchor frame to generate a candidate area, and then classify, position regression, and sliding window mechanisms, and model training is more stable. The positioning accuracy is higher, and the representative algorithm has R-CNN, FASTER R-CNN, while the latter removes the calculation of the candidate area part, directly returning to the target, which is faster, and the representative algorithm has YOLOV3. SSD. However, the single-stage or two-...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06V40/161G06V40/172G06N3/045G06F18/23213G06F18/214
Inventor 闫超黄俊洁韩强
Owner 成都东方天呈智能科技有限公司