Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Facial data processing method, memory and processor

A data processing and face technology, applied in the field of image recognition, can solve problems such as reducing the false recognition rate, achieve the effects of reducing the false recognition rate, improving the face alignment method, and reducing the consumption of computing resources

Pending Publication Date: 2020-12-18
KUANG CHI INST OF ADVANCED TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is to provide a face data processing method, memory and processor, which can reduce the false recognition rate to a large extent by filtering non-human faces, blurred faces, side faces and light-colored faces. , and the face alignment method can be improved. Without increasing the calculation, the face alignment is realized, and the side face filtering is completed, thereby reducing the consumption of computing resources and reducing the misrecognition rate of face recognition. And reduce the consumption of system computing resources, it can be generally applied to the field of portrait recognition

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
  • Facial data processing method, memory and processor
  • Facial data processing method, memory and processor
  • Facial data processing method, memory and processor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] figure 1 It is a flow chart of a face data processing method of the present invention. Such as figure 1 Shown, a kind of facial data processing method comprises steps:

[0039] S11. Input a facial picture, and detect feature data of the facial picture;

[0040] S12, according to the characteristic data of described facial picture filter unaligned face facial picture;

[0041] S13. Save the face picture of the aligned face.

[0042] The feature data of the face picture includes: left eye coordinate value x L_eye , right eye coordinate value x R_eye , nose tip coordinate value x nose , mouth left coordinate point x L_mouth , the right coordinate point x of the mouth corner R_mouth , the angle α of the face. Filtering non-aligned face facial images according to the feature data of the facial images comprises the steps of:

[0043] S121, judging whether it is a side face according to the characteristic data of the facial picture, if not, then execute S122;

[004...

Embodiment 2

[0051] figure 2 It is a flow chart of a preferred embodiment of a face data processing method of the present invention. Such as figure 2 As shown, if a large number of face pictures include the function of filtering non-face, blurred face, side face and light-colored face pictures, and saving the aligned face pictures, the introduction of each functional module is as follows:

[0052] S10: Input image is the input picture data of the system, and it is a picture prepared for face recognition. The number of faces contained in the picture ranges from [0,200], and the format can be jpg, png, jpeg, tiff, etc., and the range of the length and width of the picture Both are [64,4000].

[0053] S20: It refers to "MTCNN detects the key points of all faces". The input is the Input image, and then MTCNN performs face detection on this image, and outputs the coordinates of the face area and five key points.

[0054] S30: Indicates judging whether there is an unaligned face, if yes, ex...

Embodiment 3

[0091] An embodiment of the present invention also provides a storage medium, the storage medium includes a stored program, wherein, when the above program is running, it executes the flow of the above facial data processing method.

[0092] Optionally, in this embodiment, the above-mentioned storage medium may be configured to store program codes for performing the following facial data processing method flow:

[0093] S11. Input a facial picture, and detect feature data of the facial picture;

[0094] S12. Filter the facial pictures of non-aligned faces according to the feature data of the facial pictures;

[0095] S13. Save the facial picture of the aligned face.

[0096]Optionally, in this embodiment, the above-mentioned storage medium may include but not limited to: U disk, read-only memory (Read-Only Memory, ROM for short), random access memory (Random Access Memory, RAM for short), Various media that can store program codes such as removable hard disks, magnetic disks...

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 invention provides a face data processing method, a memory and a processor. The method is characterized by comprising the following steps: S11, inputting a face picture, and detecting feature dataof the face picture; S12, filtering a non-aligned face picture according to the feature data of the face picture; and S13, storing the aligned face picture. By filtering non-human faces, fuzzy humanfaces, side faces and light-colored human faces, the false recognition rate can be reduced to a large extent, the human face alignment method can be improved, human face alignment is achieved and sideface filtering is completed under the condition that operation is not increased, and therefore consumption of computing resources is reduced. The face recognition error recognition rate is reduced, the consumption of system computing resources is reduced, and the invention can be universally applied to the field of face recognition.

Description

【Technical field】 [0001] The invention relates to the technical field of image recognition, in particular to a face data processing method, memory and processor. 【Background technique】 [0002] In recent years, the amazing performance of deep learning in many fields has attracted a lot of attention. Academically, the research of face recognition has always been a hot field that cannot go back. New algorithms are constantly emerging, and the accuracy records are constantly being refreshed. [0003] The way of ranking in academia is just to compare the performance and accuracy of the algorithms, or even to compare the accuracy, directly extracting features from each face image in the test set, and purely comparing whether the algorithm itself can distinguish the features of faces. In industry applications, not only the performance and accuracy of the algorithm itself must be paid attention to, but also facial data processing, that is, in actual recognition, under the condition...

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): G06K9/00
CPCG06V40/171G06V40/161
Inventor 刘若鹏栾琳季春霖钟凯宇
Owner KUANG CHI INST OF ADVANCED TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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