Personnel management system identity recognition method, device and terminal equipment
By combining a facial recognition model with a local feature recognition model to obtain a comprehensive probability for identity determination, the problem of low recognition accuracy for people with similar facial contours is solved, and higher identity recognition accuracy is achieved.
CN113705366BActive Publication Date: 2025-12-12ZHONGKE HENGYUN CO LTD
Patent Information
- Application Number
- CN202110903287.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-08-06
- Publication Date
- 2025-12-12
- Estimated Expiration
- 2041-08-06
Smart Images

Figure CN113705366B_ABST
Abstract
The present application provides a kind of personnel management system identity recognition method, device and terminal equipment, the method comprises: obtaining the face data of target personnel, the face data is input into the preset face recognition model, obtain at least one candidate identity of target personnel, and the first probability corresponding to each candidate identity;Each candidate identity corresponding local feature recognition model is obtained, after the segmentation processing of the face data, the segmented face data is input into each candidate identity corresponding local feature recognition model, obtain the second probability corresponding to each candidate identity;Based on the first probability corresponding to each candidate identity, the second probability corresponding to each candidate identity determines the comprehensive probability of each candidate identity, and based on the comprehensive probability, the final identity of target personnel is determined.The personnel management system identity recognition method, device and terminal equipment provided by the present application can improve the accuracy of identity recognition.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Identity recognition method and device
CN111291645A