Camera face recognition aggregation optimization method
An optimization method and face recognition technology, applied in the field of face recognition, can solve the problems of low accuracy, face misrecognition, camera misrecognition and recognition accuracy, and achieve high recognition accuracy and accurate recognition
Pending Publication Date: 2021-12-10
HANGZHOU VISION INSIGHT TECH CO LTD
View PDF2 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] With the continuous popularization of security cameras and the continuous improvement of their intelligence, face recognition is used more and more in this type of product. However, due to the influence of some factors such as light and angle, false recognition often occurs in the camera. As well as problems such as low recognition accuracy, the existing solutions on the market cannot deal with this misidentification problem very well. An optimization solution is needed to ensure the accuracy and user experience of the camera for face recognition. This solution discloses a A method for aggregating and managing recognized face information in face recognition to solve the problem of face misrecognition in security cameras
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0019] see Figure 1-2 , the present invention provides a technical solution: a camera face recognition aggregation optimization method, comprising the following steps;
[0020] Step 1. The camera uploads the video code stream to the server, and the server extracts frames from the video code stream, performs face detection on the pictures obtained by the frame extraction, and obtains top3 pictures through detection scores;
[0021] When the camera performs fa...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a camera face recognition aggregation optimization method. The method comprises the following steps that: the step 1, a camera uploads a video code stream to a server, and the server performs frame extraction on the video code stream, performs face monitoring on a picture obtained by frame extraction, and obtains a top3 picture through detection score; the step 2, the server compares each picture in the top3 with a face in an existing face library one by one, and a corresponding group of scores is written through a specific face algorithm; the step 3, the highest score and the face in the face library corresponding to the highest score are extracted, and two different thresholds on the platform are configured to control the processing result of the face picture; and the step 4, the face picture score is compared with a configured threshold value, if the score is higher than the threshold value 1, the face picture is classified to a corresponding face, if the score is lower than the threshold value 2, the face picture is registered to a new face, and if the score is lower than the threshold value 2, the face picture is discarded. According to the method, the recognition precision is higher, and the recognition result can be actively corrected when the same person is less recognized as a plurality of persons, so that the subsequent recognition is more accurate.
Description
technical field [0001] The invention relates to the technical field of face recognition, in particular to a camera face recognition aggregation optimization method. Background technique [0002] With the continuous popularization of security cameras and the continuous improvement of their intelligence, face recognition is used more and more in this type of product. However, due to the influence of some factors such as light and angle, false recognition often occurs in the camera. As well as problems such as low recognition accuracy, the existing solutions on the market cannot deal with this misidentification problem very well. An optimization solution is needed to ensure the accuracy and user experience of the camera for face recognition. This solution discloses a A method for aggregated and managed face information in face recognition is provided to solve the problem of face misrecognition in security cameras. Contents of the invention [0003] The purpose of the present...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F16/55G06F16/51G06K9/00
CPCG06F16/55G06F16/51
Inventor 徐庆庆张彪
Owner HANGZHOU VISION INSIGHT TECH CO LTD