Face Recognition Based on Depth-Learning and Non-Collaborative Method
A face recognition and deep learning technology, applied in the field of non-cooperative face recognition based on deep learning, can solve the problems of poor recognition effect, non-standard image angle, easy to cause misunderstanding, etc., to overcome the non-standard recognition angle, The effect of high face recognition accuracy and speed improvement
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0048] The present invention will be further described below in conjunction with the accompanying drawings.
[0049] refer to figure 1 , the steps of the present invention are further described in detail.
[0050] Step 1, generate deep learning network training data set.
[0051]Collect at least 50,000 images, each of which has location information of all faces, and form the training set of the detection deep learning network with the collected images.
[0052] Collect at least 500,000 images, each of which has the identity information of all faces, and form the training set of the recognition deep learning network with the collected images.
[0053] Step 2, build the deep learning network for detection and the deep learning network for recognition respectively.
[0054] Build a detection deep learning network MTCNN composed of three sub-networks P, R, and O, and set the network parameters.
[0055] The structure of the detection deep learning network MTCNN that described ...
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