Cascaded convolutional neural network based human face occlusion detection method
A technology of convolutional neural network and detection method, which is applied in biological neural network models, neural architectures, instruments, etc., can solve problems such as incomplete face data, random positions, and the inability of face recognition systems to extract face information, achieving The effect of high detection accuracy and strong occlusion robustness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0037] The present invention will be further described below in conjunction with the drawings.
[0038] Reference Figure 1 ~ Figure 4 , A face occlusion detection method based on cascaded convolutional neural network, including the following steps:
[0039] 1) Obtain the i-th frame image I in the continuous video from the camera i ;
[0040] 2) Convert the currently acquired video image I i Perform size normalization processing, and copy and save the normalized image as two copies, respectively with
[0041] 3) Such as figure 1 Shown in the image Head detection is carried out in the process, the specific process is as follows;
[0042] 3.1) Since the human head detection network is trained with grayscale images, the image is Perform grayscale processing to obtain grayscale images
[0043] 3.2) In order to enhance the robustness of the picture to external light changes during the shooting process, and effectively avoid the situation that the obtained image is too bright or too dark,...
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