SSD face detection method based on deep learning

A technology of face detection and deep learning, applied in the field of face detection, can solve the problems of inability to achieve real-time detection and slow detection speed, and achieve the effect of enhancing generalization ability and robustness, increasing diversity, and balancing category distribution

Active Publication Date: 2021-01-05
GUANGXI UNIVERSITY OF TECHNOLOGY
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the inherent defects of the detection mechanism of the R-CNN series of algorithms, the huge amount of parameters and calculations of the convolutional n

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
  • SSD face detection method based on deep learning
  • SSD face detection method based on deep learning
  • SSD face detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0043]Example 1

[0044]ReferenceFigure 1 ~ Figure 7 , Is the first embodiment of the present invention, and this embodiment provides a deep learning-based SSD face detection method, including:

[0045]S1: Perform candidate frame extraction, target detection and bounding box regression tasks based on the deep convolutional neural network for the face data to be tested. It should be noted that the deep convolutional neural network includes a convolutional layer, a pooling layer and a fully connected layer.

[0046]S2: Use the SSD strategy to discretize the output space of the target Bounding Box regression task into a priori box, and set a priori box of various aspect ratios and sizes corresponding to each position in each detection layer. What needs to be explained in this step is that the SSD strategy adopts the SSD network, which includes:

[0047]Use VGG16 as BackBone (pillar), and replace the sixth fully connected layer and seventh fully connected layer of VGG16 with the convolutional layer...

Example Embodiment

[0083]Example 2

[0084]The SSD network can detect multi-scale faces. The so-called multi-scale detection is to use different feature maps for face detection, and in each detected feature map, a priori box is set according to certain rules for multi-scale face matching. Generally speaking, The front feature map of the convolutional neural network is larger, and the receptive field corresponding to the feature unit is smaller. The convolutional layer at the back reduces the feature map through convolution and pooling to reduce the feature map, but it has a larger receptive field; therefore, The SSD algorithm sets default boxes of different scales to match the effective receptive fields of feature units of different feature maps, sets a small-scale prior box in the larger feature map in the front for small face detection, and sets a large in the smaller feature map in the back. Large face detection is performed on the priori box of the scale.

[0085]In layman's terms, the SSD300 algorithm ...

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 SSD face detection method based on deep learning, and the method comprises the steps: carrying out the candidate box extraction, target detection and bounding box regressionof to-be-detected face data based on a deep convolutional neural network; discretizing an output space of the target Bounding Box regression task into a priori box by utilizing an SSD strategy, and respectively setting priori boxes with various aspect ratios and sizes corresponding to each position in each detection layer; wherein the deep convolutional neural network generates a confidence coefficient of the to-be-measured face according to the priori frame, and corrects the position of the priori frame; and in combination with an SSD strategy, carrying out detection of a plurality of feature maps with different resolutions on the corrected position to obtain a final detection result. According to the SSD strategy provided by the invention, the difference between detection layer data isincreased, the generalization ability and robustness of the model are improved through data enhancement, the problem of difficult negative sample mining is solved, the purpose of balancing training set category distribution is achieved, and the precision and efficiency of small face detection are improved.

Description

technical field [0001] The invention relates to the technical field of face detection, in particular to an SSD face detection method based on deep learning. Background technique [0002] Traditional face detection algorithms such as VJ based on sliding windows use the strategy of cascading AdaBoost for face region screening and face detection. Since this type of model has fewer parameters and features and simple calculation, it can meet the requirements of real-time detection. However, due to the shortcomings of poor stability and few features in the artificially designed features used in the traditional model, the traditional algorithm cannot detect the diversity of faces, and it is difficult to detect blurred and occluded faces. Therefore, the detection accuracy of the traditional algorithm is not ideal. The R-CNN series of algorithms are two-stage general object detection algorithms based on convolutional neural networks. These algorithms use self-learning CNNs for image ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/161G06V40/168G06V40/172G06N3/045G06F18/214G06F18/241
Inventor 王智文安晓宁王宇航
Owner GUANGXI UNIVERSITY OF TECHNOLOGY
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap