Adjustment method and device of face recognition model and storage medium

A face recognition and model technology, applied in the field of communication, can solve the problems of long time, increase the complexity of the system, affect the recognition accuracy of most people, etc., and achieve the effect of improving the accuracy of face recognition

Active Publication Date: 2018-11-13
TENCENT TECH (SHENZHEN) CO LTD
View PDF6 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the process of research and practice of the prior art, the inventors of the present invention found that if a large number of minority population samples are re-collected to train the face recognition model, it will take a lot of time, and the training samples of the minority population A large increase may affect the recognition ac

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Adjustment method and device of face recognition model and storage medium
  • Adjustment method and device of face recognition model and storage medium
  • Adjustment method and device of face recognition model and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] This embodiment will be described from the perspective of an adjustment device for a face recognition model. Specifically, the adjustment device for a face recognition model may be integrated in a network device. The network device may be a terminal or a server, and the terminal may include Mobile phone, tablet computer, personal computer (PC, Personal Computer), etc.

[0042] An embodiment of the present invention provides a method for adjusting a face recognition model, including: obtaining an original sample set for training a preset face recognition model, and an adjustment sample set for adjusting the model, and using the face recognition model to respectively Calculate the crowd samples in the original sample set and the adjusted sample set to obtain the first vector group and the second vector group, determine the similarity distribution curve of the original sample set according to the first vector group, and determine the adjusted sample set according to the sec...

Embodiment 2

[0091] According to the methods described in the previous embodiments, examples will be given below for further detailed description.

[0092] In this embodiment, the adjustment device of the face recognition model will be specifically integrated in the network equipment, the original sample set includes a plurality of majority crowd samples, and the adjusted sample set includes a certain amount of minority crowd samples as an example.

[0093] like Figure 2a As shown, a face recognition model adjustment method, its specific process can be as follows:

[0094] 201. The network device acquires an original sample set for training a preset face recognition model, and an adjustment sample set for adjusting the model (ie, the face recognition model).

[0095] Wherein, the original sample set may include multiple majority population samples. For example, if most of the training samples originally used by the face recognition model are face images of people of "Mongolian race", the...

Embodiment 3

[0182] In order to better implement the above method, an embodiment of the present invention also provides an adjustment device for a face recognition model. The adjustment device for a face recognition model may specifically be integrated in a network device, which may be a terminal or a server, etc. .

[0183] For example, if Figure 3a As shown, the adjustment device of the face recognition model may include an acquisition unit 301, a calculation unit 302, a determination unit 303 and an adjustment unit 304, as follows:

[0184] (1) acquisition unit 301;

[0185] The acquiring unit 301 is configured to acquire an original sample set for training a preset face recognition model and an adjustment sample set for adjusting the model.

[0186] Among them, the original sample set includes a plurality of general population samples, these general population samples are the original training samples of the preset face recognition model, for example, it can be a majority of populat...

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

No PUM Login to view more

Abstract

The embodiment of the invention discloses an adjustment method and device of a face recognition model and a storage medium. The embodiment of the invention can obtain an original sample set used for training the face recognition model and an adjustment sample set (a minority population sample set) used for adjusting the model, respectively train the face recognition model according to the same, then determine a similarity distribution curve of the original sample set and a similarity distribution curve of the adjustment sample set, and then adjust the face recognition model through convergenceon the similarity distribution curve of the original sample set and the similarity distribution curve of the adjustment sample set. The scheme fine-tunes the face recognition model on the premise ofnot increasing face recognition system architecture complexity and not impacting majority population face recognition accuracy, and thus facilitates fast improvement of minority population face recognition accuracy.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a face recognition model adjustment method, device and storage medium. Background technique [0002] In recent years, face recognition technology has been greatly developed. However, for minority groups, such as Uighurs, the elderly, or blacks, most of the existing face recognition systems often have low recognition accuracy, which is specifically manifested in the system calculation. The facial feature similarity among the minority groups of different people is too high, resulting in too many false alarms, which seriously affects the use effect of the face recognition system in some scenarios. [0003] In response to the above problems, several methods have been proposed to improve the face recognition accuracy of minority groups to reduce the false alarm rate of minority groups. For example, retrain the face recognition model by increasing the sample proportion of minor...

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
no application Login to view more
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/16G06F18/22G06F18/214
Inventor 沈鹏程李绍欣
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap