Image updating process and apparatus based on human face recognition

A face image and image update technology, which is applied in the field of information security, can solve problems that affect the accuracy of face recognition, face recognition processing hardware requirements are high, and ordinary users are difficult to use, so as to reduce requirements and increase accuracy.

Active Publication Date: 2009-07-08
HUAWEI DEVICE CO LTD
0 Cites 35 Cited by

AI-Extracted Technical Summary

Problems solved by technology

[0003] However, the existing face recognition technology needs to use high-speed processors to calculate a large number of training samples, so it is mainly used on PCs or large systems, making it difficult for ordinary users to use
[0004] In the process of realizing the present invention, the inventor has found that there are at least the following problems in the prior art: the image of the hum...
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

Method used

The beneficial effect of this embodiment is: by keeping the update of user's face image, reduced the impact of facial shape change on recognition, increased the accuracy rate of recognition, and make face recognition technology can be applied in daily life , such as providing image updates to the company's access control system, operating authentication restrictions, etc.
The beneficial effect of this embodiment is: by keeping the update of user's face image, reduced the impact of facial shape change on recognition, increased the accuracy rate of recognition, can only use less facial image as training simultaneously The sample reduces the requirements for hardware, so that face recognition technology can be applied to daily life; it provides a list of candidate face images, which is more convenient for users to use.
The beneficial effect of this embodiment is: by keeping the update of user's facial image, reduced the impact of facial shape change on identification, increased...
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

Abstract

The invention provides a method for updating face recognition images and a device. The method comprises the following steps: acquiring a first face image; comparing the consistency between the first face image and a second face image stored; if the first face image and the second face image are identical with each other, the first face image is stored, and the second face image is updated by the first face image. By keeping updating the face images of users, the method ensures that impacts of changes of face outlines on recognition are reduced, and the recognition accuracy is improved.

Application Domain

Technology Topic

Image

  • Image updating process and apparatus based on human face recognition
  • Image updating process and apparatus based on human face recognition
  • Image updating process and apparatus based on human face recognition

Examples

  • Experimental program(1)

Example Embodiment

[0024] For example, in the above-mentioned embodiment, the mobile phone contact update picture function can also be automatically selected by the mobile phone without selecting the contact. The implementation method is as follows:
[0025] In step 201, the user's face is photographed, and the face photographed image is obtained, for example, the contact in the mobile phone is photographed through the mobile phone camera.
[0026] In step 202, the feature data of the face photographed image is extracted. The image is stored in a pixel matrix in the mobile phone, which is actually an integer matrix. Perform mathematical singular value calculation on the integer matrix to obtain the feature data and store it in the mobile phone. .
[0027] In step 203, the feature data of the face photographed image is compared with the stored feature data of multiple user face images to obtain the most similar user face image, for example, the singular value feature of the face photographed image The data and the saved singular value feature data are compared and judged by Euclidean distance, and the image with the smallest threshold value is selected.
[0028] In step 204, the feature data of the photographed face image is compared with the most similar facial image of the user, and when the comparison result matches a set value, it is determined that the user authentication is passed, and the face is used. The partial captured image replaces the most similar user face image. For example, the judgment threshold is set to 0.0001. When the calculation result is less than 0.0001, it is judged as the same person, and the contact image is allowed to be replaced.
[0029] In addition, users can also be allowed or restricted to perform corresponding operations based on the authentication results, such as making calls, deleting messages, and other functions.
[0030] The beneficial effects of this embodiment are: by keeping the user's facial image updated, the impact of face shape changes on recognition is reduced, the accuracy of recognition is increased, and the face recognition technology can be applied to daily life, such as providing Updates to mobile phone contact images, restrictions on operation authentication, etc.
[0031] Such as image 3 As shown, it is a flowchart of an image update method based on face recognition provided by another embodiment of the present invention.
[0032] As with the mobile phone contact updating picture function in the above embodiment, the mobile phone can also list the user's face images whose similarity meets the condition for the user to choose.
[0033] In step 301, a face image is taken.
[0034] In step 302, the feature data of the captured face image is extracted.
[0035] In step 303, the feature data of the captured face image is compared with the feature data of the stored face image for consistency, and a face image whose comparison result meets a set value is output, and the face image is compared with all the face images. The comparison result of the captured facial images is a list of the similarity between the user's facial image and the captured facial image.
[0036] In step 304, according to the user's selection instruction, a stored face image is determined from the similarity list, and the selected stored face image is replaced with the captured face image.
[0037] The beneficial effects of this embodiment are: by keeping the user's facial image updated, the impact of face shape changes on recognition is reduced, and the accuracy of recognition is increased. At the same time, fewer facial images can be used as training samples, which reduces In addition to the hardware requirements, face recognition technology can be applied to daily life.
[0038] Such as Figure 4 Shown is a structural diagram of a face recognition image updating device provided by an embodiment of the present invention, and the device includes:
[0039] The camera unit 401 is used to capture a first face image;
[0040] The image comparison unit 402 is configured to compare the first face image with the stored second face image for consistency;
[0041] The image update unit 403 is configured to store the first face image when the consistency comparison result of the image comparison unit is that the first face image is consistent with the second face image The first face image updates the second face image.
[0042] The beneficial effect of this embodiment is that by keeping the face image of the user updated, the influence of the change of the face shape on the recognition is reduced, and the accuracy of the recognition is increased.
[0043] In an embodiment of the present invention, the face recognition image update device provided by the present invention can be applied to a company's access control system, and the device includes a storage unit storing employee face images, such as Figure 5 As shown, the device also includes:
[0044] The camera unit 501 is used to take a picture of the user's face and obtain a face photographed image;
[0045] The feature extraction unit 502 is used to extract the feature data of the photographed face image; generally, the face recognition system includes image capture, face positioning, image preprocessing, and face recognition (identity confirmation or identity search) . The input of the system is generally one or a series of face images with undetermined identities, and several face images with known identities in the face database or corresponding codes, and the output is a series of similarity scores, indicating The identity of the face to be recognized.
[0046]In image processing, the processing of facial images can be regarded as a vector whose component is the luminance of each pixel. The dimension of the vector space is the number of pixels. The eigenvectors of the covariance matrix of a large data set of a standardized facial image are called eigenfaces. They are very useful for expressing any facial image as a linear combination of them. Eigenfaces provide a way of data compression for recognition purposes. In this application, generally only the eigenface corresponding to the largest eigenvalue is selected.
[0047] The comparing unit 504 is configured to compare the characteristic data of the photographed face image with the characteristic data of multiple stored facial images of users for consistency, and obtain the most similar facial image of the user;
[0048] The judging unit 505 is configured to judge the face shot when the comparison result of the comparing unit 504 is that the face shot image is consistent with the most similar user face image and the comparison result meets a set value. The user corresponding to the image passes user authentication. The image update unit 503 is configured to store the photographed face image when the user passes the user authentication, and update the most similar facial image of the user with the photographed face image.
[0049] The authentication restriction unit 506 is configured to allow the user to perform corresponding operations when the determination unit determines that the user corresponding to the facial image is authenticated; the determination unit determines the user corresponding to the facial image When the user fails to pass the authentication, the user is restricted from performing corresponding operations.
[0050] The beneficial effects of this embodiment are: by keeping the user's facial image updated, the impact of face shape changes on recognition is reduced, the recognition accuracy is increased, and the face recognition technology can be applied to daily life, such as providing Image update and operation authentication restrictions on the company's access control system.
[0051] Such as Figure 6 As shown, it is a structural diagram of a face recognition image updating device provided by another embodiment of the present invention, in the device:
[0052] The camera unit 601 is used to capture the first face image, such as a company employee access control system to take photos of employees.
[0053] The image comparison unit 602 is configured to compare the first face image with multiple stored face images for consistency.
[0054] The image and comparison result output unit 604 is configured to output candidate face images whose comparison results for consistency comparison with the first face image meet a set value among the plurality of face images, and each of the candidates The comparison result of the face image and the captured face image; for example, a list of employee images that meet the set value is displayed on the screen of the access control system for the user to select.
[0055] The image update unit 603 is configured to store the first face image according to the instruction after receiving an instruction from the user to select the candidate face image based on the image and the result output by the comparison result output unit, and use the The first face image updates the selected candidate face image.
[0056] The beneficial effects of this embodiment are: by keeping the user's facial image updated, the impact of face shape changes on recognition is reduced, and the accuracy of recognition is increased. At the same time, fewer facial images can be used as training samples, which reduces In addition to the hardware requirements, the face recognition technology can be applied to daily life; it provides a list of candidate face images, which is more convenient for users to use.
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

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
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

Similar technology patents

Classification and recommendation of technical efficacy words

  • Lower requirement
  • Improve accuracy

LTE channel measurement and feedback method

InactiveCN102546113ALower requirementReduce computational workloadError preventionTransmission path multiple useSignal-to-noise ratio (imaging)Transmission point
Owner:沈阳市联盛科技有限公司

Cassette-based dialysis medical fluid therapy systems, apparatuses and methods

InactiveUS20050209563A1Improvement for dialysisImprove accuracyMedical devicesPeritoneal dialysisAccuracy improvementDialysis
Owner:BAXTER INT INC +1
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