Face detection method and device
A technology of face detection and detection frame, which is applied in the direction of instruments, character and pattern recognition, computer components, etc. Performance improvement, accurate classification and prediction
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0042] Example one
[0043] Reference figure 1 , A flowchart of a face detection method provided by an embodiment of the present invention is given.
[0044] Step 101: Use the pre-trained first convolutional neural network model to classify the image to be tested, determine the first face confidence of each input area in the image to be tested, and obtain the confidence of the first face according to the first face confidence. At least one candidate area is selected from the input area.
[0045] Among them, the first convolutional neural network includes m-layer convolutional layers.
[0046] Specifically, the first convolutional neural network is a deep convolutional neural network with deep learning capabilities, including one or more convolutional layers and pooling layers, which can realize deep learning. Compared with other deep learning structures, deep convolution Neural networks show more outstanding performance in image recognition.
[0047] Before detecting the face, you can...
Example Embodiment
[0057] Example two
[0058] Reference figure 2 On the basis of the foregoing embodiment, this embodiment further discusses the face detection method.
[0059] In an optional embodiment, before performing face detection on the image, it further includes training the first convolutional neural network model and the second convolutional neural network model.
[0060] The following are Figure 2 to Figure 4 The embodiment discusses the training process of the first convolutional neural network model and the second convolutional neural network model.
[0061] Reference figure 2 , A flowchart of training the first convolutional neural network model in a face detection method provided by an embodiment of the present invention is given:
[0062] In step 201, a face data set containing face annotations is selected as a training sample, and training images in the training sample are clipped.
[0063] Optionally, use the WIDER FACE data set as the training sample, where the WIDER FACE data set co...
Example Embodiment
[0125] Example three
[0126] On the basis of the foregoing embodiment, this embodiment also provides a face detection device, which is applied to an artificial intelligence terminal.
[0127] Reference Figure 13 A structural block diagram of a face detection apparatus provided by an embodiment of the present invention is given, which may specifically include the following modules:
[0128] The pre-classification module 1301 is configured to use the pre-trained first convolutional neural network model to classify the image to be tested, to determine the first face confidence of each input area in the image to be tested, and to determine the first face confidence level according to the first face The confidence level screens out at least one candidate region from the input region, and the first convolutional neural network includes m-layer convolutional layers.
[0129] The secondary classification module 1302 is configured to use a pre-trained second convolutional neural network mode...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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