Method for achieving user authentication by utilizing camera

An identity verification and camera technology, applied in the fields of digital data authentication, character and pattern recognition, deception detection, etc., can solve the problems of loss, theft, easy forgetting, etc., to improve security, ensure picture quality, improve reliability and The effect of accuracy

Inactive Publication Date: 2014-03-26

湖北微模式科技发展有限公司

5 Cites 66 Cited by

AI-Extracted Technical Summary

Problems solved by technology

This verification method solves the above-mentioned problems of being easily forgotten, stolen or lost, but there are also some problems at the same time. For examp...

Abstract

The invention discloses a method for achieving user authentication by utilizing a camera. The method comprises the following steps: (1) pre-collecting and storing a facial image of a user, (2) performing vivo detection on a facial image of a current user through the camera in the field use process, executing the step (3) if the detection succeeds, and prompting that the detection fails if not, (3) performing field photographing on the current user through the camera and performing storing, (4) comparing the stored facial image of the user with the pre-collected facial image of the user to obtain the degree of similarity, and (5) comparing the degree of similarity and a preset threshold value and determining whether the two compared facial images belong to the same person, wherein it is determined that the two compared facial images belong to the same person if the degree of similarity is greater than or equal to the preset threshold value, and the authentication cannot be passed if the degree of similarity is smaller than the preset threshold value. According to the method for achieving the user authentication by utilizing the camera, because dual detection is performed through a facial recognition system and the vivo detection, the situation of easily invading the system can be effectively controlled, and the security of user data is promoted.

Application Domain

Digital data authenticationSpoof detection

Technology Topic

User authenticationFacial recognition system +3

Image

Examples

Experimental program(1)
Effect test(1)

Example Embodiment

[0035] Example 1

[0036] Such as figure 1 As shown, the method for implementing identity verification using a camera described in this embodiment includes the following steps:

[0037] S100: Collect the user's face image in advance.

[0038] There are two ways of image collection: one is to use the camera to take pictures on site, and the other is to use the system photo upload function to upload electronic photos with the user's front profile picture.

[0039] S200: Perform face image quality evaluation on the image collected in step S100.

[0040] The role of image quality evaluation is to judge the quality of face imaging. The quality of face images will directly affect the accuracy and reliability of the identity verification system. Therefore, it is necessary to check the scene before establishing the face image database for identity verification. The image quality of the face image obtained from the photo and the uploaded photo is judged, including the following judgment elements:

[0041] (1) The face area size is too small: If the face area size is too small for photos taken and uploaded on site, it will affect the accuracy of the subsequent authentication algorithm. Face detection is performed in the entire image through a face detection algorithm. If no face is detected, or the size of the detected face area is less than a preset threshold, it is determined that the face area size is too small.

[0042] (2) The image is too bright: If the photographed photo and the uploaded image have sufficient brightness but lack sufficient contrast, it is difficult to extract a face image from them. To this end, the average brightness and average contrast of the image are calculated and compared with the corresponding threshold: if the average brightness is greater than the maximum threshold of average brightness, or the average contrast is less than the minimum threshold of average contrast, the image is considered too bright.

[0043] (3) The image is too dark: similar to the above-mentioned judgment of the image being too bright, the image is too dark also makes it difficult to extract the face image from it. By calculating the average brightness value of the image, it is compared with the preset threshold. If it is less than the preset threshold, the image is considered too dark.

[0044] (4) Uneven image brightness: Uneven image brightness refers to the large changes in the brightness of different local areas in the image due to the different light intensity in different directions when taking pictures. For example, side light will cause one side of the image to be brighter and the other side to be darker. The uneven brightness of the image brings greater difficulty to subsequent identity verification. This embodiment adopts the following algorithm flow to judge the uneven brightness of the image: divide the image into multiple sub-blocks, count the average brightness value of each sub-block, and then calculate the variance of the average brightness value of all sub-blocks. If the variance is greater than the preset threshold, then The image brightness is considered uneven.

[0045] (5) The image is blurred: the image is blurred and the face image cannot be extracted from it. In this embodiment, the image focus score is calculated and compared with a preset threshold. If it is less than the preset threshold, the image is considered to be blurred.

[0046] (6) The face posture changes too much: the user does not face the camera when taking a photo or uploading a photo, which will cause the face posture to be changed too much, such as side face, head down, etc., which will bring about subsequent identity verification Great difficulty. Therefore, it is necessary to determine whether the posture of the customer's face image exceeds the tolerance range. This embodiment uses the following algorithm flow to determine the face pose: first, the face area is detected by the face detection algorithm, and then the detected face area is judged by the face pose estimation algorithm. If the returned result is "abnormal" , It is considered that the attitude has changed too much.

[0047] Through the evaluation of the above six elements, it can basically ensure that the quality of the face image of the user's face database used for subsequent identity verification is qualified, which will greatly improve the accuracy and reliability of subsequent identity verification.

[0048] S300: Establish a user face database.

[0049] The images that pass the quality evaluation are labeled with numbers or user names for storage, and a user face database is established.

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.

Classification and recommendation of technical efficacy words

Guaranteed picture quality
improve security

An image processing method and apparatus

ActiveCN109427047Aprevent image degradationGuaranteed picture quality

Owner:BOE TECH GRP CO LTD +1

Method for achieving user authentication by utilizing camera

AI-Extracted Technical Summary

Problems solved by technology

Abstract

Image

Examples

Example Embodiment

PUM

Description & Claims & Application Information

Similar technology patents

Foodstuff monitoring method and device

Cookie-based secure single sign-on method and unified authentication service system thereof

Method, device and system for carrying out service access control on third-party application

Multifunctional carry-on power supply

A method for WFII/3G router access authentication by using fingerprint

Classification and recommendation of technical efficacy words

An image processing method and apparatus

Low-temperature charge and heating system and method for power battery for all-electric vehicles

Block chain system, and data storage method and apparatus

Pesticide micro-capsule granules and preparation method thereof

Signing and decrypting method and system applied to cloud computing and based on SM2 algorithm

NFC (near field communication) mobile terminal and payment method