Face identification method under shielding condition based on deep learning
A face recognition and deep learning technology, applied in the field of face recognition, can solve problems such as difficulty in implementation and increase in complexity of face recognition technology, and achieve the effect of improving effectiveness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0020] A face recognition method under occlusion conditions based on deep learning, the method includes the following steps: (1) face detection and feature point detection for a given face image with partial occlusion; (2) according to the detected (3) Based on the ubuntu16.04 operating system, under the GPU1080, build the CAFFE deep learning framework to obtain the face recognition model.
Embodiment 2
[0022] According to the face recognition method under the occlusion condition based on deep learning described in embodiment 1, the specific process of performing face detection and feature point detection on a given face image with partial occlusion is as follows:
[0023] (1) For the given face image data with partial occlusion, after three layers of convolutional layers, the obtained feature maps are respectively input into the first group of face classification layer, frame regression layer and facial feature point positioning layer to obtain Face candidate box and bounding box regression vector;
[0024] (2) Use the candidate frame as the input to continue the convolution operation, and then after three layers of convolution, the obtained feature map is input into the fully connected layer, and then input into the second group of face classification layer, border regression layer and facial feature point positioning layer to further improve the accuracy of the frame;
[...
Embodiment 3
[0027] According to the face recognition method under occlusion conditions based on deep learning described in Embodiment 1, the specific process of performing facial features partial map interception according to the positions of the detected feature points on the human face is as follows: according to the detected human face The location of the feature points, the original image is cut into three partial images including eyes, nose, and mouth, which are used for subsequent training.
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com