Face recognition methods, devices, systems, and storage media based on element detection.

By combining deep learning neural networks for encoding and decoding with predictive feature neural networks and IOU modules, the problem of low efficiency in face occlusion recognition in multi-face scenarios is solved, achieving efficient and accurate multi-face occlusion recognition and improving user experience.

CN116189270BActive Publication Date: 2026-05-26CHINA GUANGFA BANK
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA GUANGFA BANK
Filing Date
2023-03-29
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing technologies are ineffective in recognizing face occlusion types in situations with multiple faces, and are inefficient and provide a poor user experience.

Method used

By combining deep learning neural networks for encoding and decoding with predictive feature neural networks, along with an IOU module, a candidate box classification module, and a logical judgment module, facial elements are identified and classified through high-level and low-level feature fusion, and redundant information is filtered out, enabling simultaneous recognition of multiple occluded faces.

Benefits of technology

It supports simultaneous recognition of multiple faces with occlusion, improving recognition efficiency and accuracy, meeting the needs of real-time video review, and providing a better user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116189270B_ABST
    Figure CN116189270B_ABST
Patent Text Reader

Abstract

This invention provides a face recognition method, device, system, and storage medium based on feature detection. The method includes: acquiring image data; inputting the image data into a face recognition model to identify several facial feature information; the face recognition model includes an encoding / decoding deep learning neural network and a predictive feature neural network; filtering identical facial feature information through an IOU module; classifying target features through a candidate box classification module, aggregating each facial feature information element and its related target elements into a feature set and assigning a unique code to each feature set; filtering each feature set through the IOU module; inputting each feature set into a logic judgment module for occlusion judgment, obtaining a mapping between the code and the occlusion judgment result; and outputting the face recognition result. This invention supports simultaneous recognition of multiple faces occluded in a single image, meets the real-time requirements of face recognition, and offers high accuracy and stronger robustness.
Need to check novelty before this filing date? Find Prior Art