CN110751071A - Face recognition method and device, storage medium and computing equipment - Google Patents
Face recognition method and device, storage medium and computing equipment Download PDFInfo
- Publication number
- CN110751071A CN110751071A CN201910967124.XA CN201910967124A CN110751071A CN 110751071 A CN110751071 A CN 110751071A CN 201910967124 A CN201910967124 A CN 201910967124A CN 110751071 A CN110751071 A CN 110751071A
- Authority
- CN
- China
- Prior art keywords
- face picture
- face
- picture
- similarity
- feature vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Abstract
A face recognition method and device, a storage medium and a computing device are provided, wherein the face recognition method comprises the following steps: acquiring a first face picture and a second face picture; extracting the features of the first face picture and the second face picture based on a scale invariant feature transform algorithm to obtain the feature vectors of the first face picture and the second face picture respectively; judging the similarity of the first face picture and the second face picture according to the feature vector; and comparing the similarity with a preset threshold value to determine whether the first face picture and the second face picture are the same face picture. By the technical scheme provided by the invention, a more accurate face comparison result can be obtained.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a face recognition method and device, a storage medium and computing equipment.
Background
In the loan application link of the user, the identity authentication of the user is an essential link. For network lending, most financial institutions require users to upload a picture of a hand-held identification card.
In general, when the face comparison method is used to indicate that the face of the user in the photo is consistent with the face in the identity card, that is, the face comparison result passes, the next link of loan application is entered. However, in the face comparison process, there may be some cases where a lawless person uses image processing software to perform image processing so as to perform network fraud.
For example, a lawbreaker can process the face part of a user in a hand-held identity card in a photo, extract the face in the identity card stolen by the lawbreaker, and replace the real face of the hand-held user. If the lawbreaker adopts the fraud technique, the two faces are the same in height, so that the lawbreaker can easily pass through the face comparison algorithm adopted by the prior art, and the lawbreaker can successfully cheat.
Disclosure of Invention
The technical problem solved by the invention is how to obtain a face comparison result with higher precision.
In order to solve the above technical problem, an embodiment of the present invention provides a face recognition method, including: acquiring a first face picture and a second face picture; extracting the features of the first face picture and the second face picture based on a scale invariant feature transform algorithm to obtain the feature vectors of the first face picture and the second face picture respectively; judging the similarity of the first face picture and the second face picture according to the feature vector; and comparing the similarity with a preset threshold value to determine whether the first face picture and the second face picture are the same face picture.
Optionally, the acquiring the first face picture and the second face picture includes: and acquiring the first face picture and the second face picture based on a multi-task cascade convolution network face detection and alignment algorithm.
Optionally, the feature vector of the first face picture includes a plurality of first key point feature vectors, the feature vector of the second face picture includes a plurality of second key point feature vectors, and determining the similarity between the first face picture and the second face picture according to the feature vectors includes: traversing and calculating Euclidean distances between the first key point feature vectors and the second key point feature vectors for all the first key point feature vectors and all the second key point feature vectors to obtain a Euclidean distance set; and for each Euclidean distance in the Euclidean distance set, determining the number of Euclidean distances smaller than a preset Euclidean distance, and taking the number as the similarity.
Optionally, the step of calculating the euclidean distance between the first keypoint feature vector and the second keypoint feature vector in the traversal includes: and traversing and calculating the Euclidean distance between the first key point feature vector and the second key point feature vector by adopting a storm wind algorithm.
Optionally, the first face picture and the second face picture are located in the same picture, and the comparing the similarity with the preset threshold value to determine whether the first face picture and the second face picture are the same face includes: and when the similarity is larger than or equal to a preset threshold value, determining that the picture is a false picture, otherwise, determining that the picture is a real picture.
Optionally, the selecting the first face picture from an image, the selecting the second face picture from an image, and the comparing the similarity with a preset threshold to determine whether the first face picture and the second face picture are the same face picture includes: and when the similarity is larger than or equal to a preset threshold value, determining that the first face picture and the second face picture belong to the same person, otherwise, determining that the first face picture and the second face picture do not belong to the same person.
In order to solve the above technical problem, an embodiment of the present invention further provides a face recognition apparatus, including: the acquisition module is used for acquiring a first face picture and a second face picture; the extraction module is used for extracting the features of the first face picture and the second face picture based on a scale invariant feature transform algorithm so as to obtain the feature vectors of the first face picture and the second face picture respectively; the judging module is used for judging the similarity of the first face picture and the second face picture according to the feature vector; and the comparison module is used for comparing the similarity with a preset threshold value so as to determine whether the first face picture and the second face picture are the same face picture.
Optionally, the obtaining module includes: and the acquisition sub-module is used for carrying out face detection and alignment algorithm based on a multitask cascade convolution network to acquire the first face picture and the second face picture.
To solve the above technical problem, an embodiment of the present invention further provides a storage medium having stored thereon computer instructions, where the computer instructions execute the steps of the above method when executed.
In order to solve the above technical problem, an embodiment of the present invention further provides a computing device, including a memory and a processor, where the memory stores computer instructions executable on the processor, and the processor executes the computer instructions to perform the steps of the above method.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides a face determination method, which comprises the following steps: determining a first face picture and a second face picture; extracting the features of the first face picture and the second face picture based on a scale invariant feature transform algorithm to obtain the feature vectors of the first face picture and the second face picture respectively; judging the similarity of the first face picture and the second face picture according to the feature vector; and comparing the similarity with a preset threshold value to determine whether the first face picture and the second face picture are the same face picture. According to the embodiment of the invention, the scale invariant feature transformation algorithm is utilized, the local features of the human face can be extracted from the first human face picture and the second human face picture, and the feature vector extracted by the scale invariant feature transformation algorithm has high tolerance to light, noise, slight visual angle change and the like, so that whether the first human face picture and the second human face picture are the same human face picture can be determined more accurately, a human face comparison result with higher accuracy is obtained, whether the first human face picture and the second human face picture are pictures subjected to image processing is easier to identify, and the authenticity of the images and/or the pictures can be discriminated more accurately.
Further, the acquiring the first face picture and the second face picture includes: and acquiring the first face picture and the second face picture based on a multi-task cascade convolution network face detection and alignment algorithm. The embodiment of the invention adopts the multi-task cascade convolution network face detection and alignment algorithm, and can quickly and accurately find out the first face picture and the second face picture by utilizing the advantages of the algorithm.
Drawings
Fig. 1 is a schematic flow chart of a face recognition method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a face recognition apparatus according to an embodiment of the present invention.
Detailed Description
As will be appreciated by those skilled in the art, as background, existing mechanisms have deficiencies that tend to make it undesirable for a lawbreaker to use image processing methods to fraud.
The embodiment of the invention provides a face determination method, which comprises the following steps: determining a first face picture and a second face picture; extracting the features of the first face picture and the second face picture based on a scale invariant feature transform algorithm to obtain the feature vectors of the first face picture and the second face picture respectively; judging the similarity of the first face picture and the second face picture according to the feature vector; and comparing the similarity with a preset threshold value to determine whether the first face picture and the second face picture are the same face picture.
According to the embodiment of the invention, the scale invariant feature transformation algorithm is utilized, the local features of the human face can be extracted from the first human face picture and the second human face picture, and the feature vector extracted by the scale invariant feature transformation algorithm has high tolerance to light, noise, slight visual angle change and the like, so that whether the first human face picture and the second human face picture are the same human face picture can be determined more accurately, a human face comparison result with higher accuracy is obtained, whether the first human face picture and the second human face picture are pictures subjected to image processing is easier to identify, and the authenticity of the images and/or the pictures can be discriminated more accurately.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Fig. 1 is a schematic flow chart of a face recognition method according to an embodiment of the present invention. The face recognition method may be performed by a computing device, such as a server, a personal terminal, or the like.
Specifically, the face recognition method may include the steps of:
step S101, a first face picture and a second face picture are obtained;
step S102, extracting the features of the first face picture and the second face picture based on a scale invariant feature transform algorithm to obtain the feature vectors of the first face picture and the second face picture respectively;
step S103, judging the similarity of the first face picture and the second face picture according to the feature vector;
and step S104, comparing the similarity with a preset threshold value to determine whether the first face picture and the second face picture are the same face picture.
More specifically, in step S101, a first face picture and a second face picture may be acquired from a picture or an image.
In one embodiment, the first face picture and the second face picture may be located in the same picture. In practical applications, the first face picture and the second face picture may be in pictures taken by a mobile phone or a camera.
In another embodiment, the first face picture may be captured from an image, and the second face picture may be located in a picture, that is, the first face picture and the second face picture are from different sources. Alternatively, the first face picture may be located in a picture, and the second face picture may be captured from an image.
For example, the first face picture may be captured from an image captured by a camera, and the second face picture may be located in a photograph, for example, the second face picture may be taken from a photograph of an identification card.
In one embodiment, the first face picture and the second face picture may be obtained based on a Multi-task Cascaded convolutional network face Detection and Alignment using Multi-task Cascaded convolutional network (JDA-MTCNN).
In step S102, features of the first face picture and the second face picture may be extracted based on a Scale-invariant feature transform (Scale-invariant feature transform, referred to as SIFT for short) to obtain feature vectors of the first face picture and the second face picture, which are hereinafter referred to as a first SIFT feature vector and a second SIFT feature vector, respectively. The SIFT algorithm has scale invariance, can detect key points in an image and is a local feature descriptor.
The SIFT features corresponding to the SIFT feature vectors can represent local features of the image, the image keeps invariance to rotation, scale scaling and brightness change, and keeps high tolerance to view angle change, affine transformation and noise.
If the picture comprises the handheld identity card of the user and the identity card comprises the face image, when the picture is processed, even if the head portrait (face part) of the user in the picture is processed, the head portrait is amplified, pasted and subjected to color adjustment, and the local features of the face cannot be changed by the SIFT feature vector extracted by the SIFT algorithm in illumination adjustment.
In step S103, the similarity between the first face picture and the second face picture may be determined according to the first feature vector and the second feature vector.
Specifically, after SIFT feature vectors of two face pictures are obtained, the similarity of the two face pictures can be judged by using the euclidean distance of the feature vectors of the key points as a basis. In a specific implementation, the first SIFT feature vector comprises a plurality of first keypoint feature vectors, and the second SIFT feature vector of the second face picture comprises a plurality of second keypoint feature vectors.
For all the first keypoint feature vectors and all the second keypoint feature vectors, euclidean distances between any first keypoint feature vector and any second keypoint feature vector can be calculated, and each euclidean distance can form a set of euclidean distances. Then, the number of euclidean distances in the set of euclidean distances, each of which is smaller than a preset euclidean distance, may be determined, and the number may be used as the similarity.
In one embodiment, a storm Force (Brute Force) algorithm may be employed to calculate the euclidean distance between the first keypoint feature vector and the second keypoint feature vector. The effect of calculating the Euclidean distance by the storm algorithm is better.
As a variation, a first keypoint feature vector may be selected from the first SIFT feature vectors, the euclidean distance between the first keypoint feature vector and any one of the second keypoint feature vectors is calculated through a traversal method, two second keypoint feature vectors with the closest distance are selected, if the quotient of the closest distance divided by the next closest distance is smaller than a preset threshold, it is determined that the keypoint corresponding to the second keypoint feature vector and the keypoint corresponding to the selected first keypoint feature vector are a pair of matching points, otherwise, the determination result indicates that the two keypoints are not matching points. And selecting one key point feature vector from the residual key point feature vectors of the first SIFT feature vector, and repeating the process until all key point feature vectors of the first SIFT feature vector are traversed. And after the number of the matching points is determined, taking the number of the matching points as the value of the similarity.
In step S104, the first face picture and the second face picture are located in the same picture, and if the similarity is greater than or equal to a predetermined preset threshold, the picture may be determined to be a false picture. Otherwise, if the similarity is smaller than a predetermined preset threshold, the picture can be determined to be a real picture.
For example, the pictures uploaded by the user include a first face picture and a second face picture. The first face picture is a face picture in the identity card, and the second face picture is a face picture of a user holding the identity card. If the similarity between the face picture of the user and the face picture in the identity card is higher than the preset threshold value, the picture uploaded by the user can be judged to be a false picture generated by image processing. Embodiments of the present invention may be used in network lending institutions to identify real or fraudulent users.
In a variation, the first face picture is selected from an image, the second face picture is selected from the outside of the image, and if the similarity between the two face pictures is greater than or equal to a predetermined preset threshold, it may be determined that the first face picture and the second face picture belong to the same person. Otherwise, if the similarity is smaller than the preset threshold, it may be determined that the first face picture and the second face picture do not belong to the same person.
For example, the face of a person may be captured in an acquired video image and taken as a first face picture. The second face picture is a face picture in the identity card. If the similarity of the two face pictures is greater than or equal to a predetermined preset threshold value, it can be determined that the first face picture and the second face picture belong to the same person. Otherwise, it may be determined that the first face picture and the second face picture do not belong to the same person. The embodiment of the invention can be used for catching criminals escaping.
Therefore, the embodiment of the invention fully utilizes the high tolerance of the SIFT feature vectors to light, noise and slight visual angle changes, and screens the pictures and/or images by using the SIFT algorithm, so that a face comparison result with higher precision can be obtained. When similar human faces appear in the same picture or images, the authenticity of the images and the pictures can be quickly and efficiently identified. For example, photos that have been processed with fraudulent group pictures can be accurately and quickly found.
Fig. 2 is a schematic structural diagram of a face recognition apparatus according to an embodiment of the present invention. The face recognition apparatus 2 may implement the technical solution of the method shown in fig. 1, and is executed by a computing device.
Specifically, the face recognition apparatus 2 may include: the acquiring module 21 is configured to acquire a first face picture and a second face picture; the extraction module 22 is configured to extract features of the first face picture and the second face picture based on a scale invariant feature transform algorithm to obtain feature vectors of the first face picture and the second face picture; the judging module 23 is configured to judge a similarity between the first face picture and the second face picture according to the feature vector; and the comparison module 24 is configured to compare the similarity with a preset threshold value to determine whether the first face picture and the second face picture are the same face picture.
In a specific implementation, the obtaining module 21 may include an obtaining sub-module 211, which obtains the first face picture and the second face picture based on a multi-task cascaded convolutional network face detection and alignment algorithm.
In a specific implementation, the feature vector of the first face picture includes a plurality of first key point feature vectors, the feature vector of the second face picture includes a plurality of second key point feature vectors, and the determining module 23 may include: the traversal submodule 231 is configured to traverse and calculate a euclidean distance between the first keypoint feature vector and the second keypoint feature vector for all the first keypoint feature vectors and all the second keypoint feature vectors to obtain a euclidean distance set; the first determining submodule 232 determines, for each euclidean distance in the set of euclidean distances, a number of euclidean distances smaller than a preset euclidean distance, and takes the number as the similarity.
In a specific implementation, the traversal submodule 231 is adapted to traverse and calculate the euclidean distance between the first keypoint feature vector and the second keypoint feature vector by using a storm algorithm.
In one embodiment, the first face picture and the second face picture are located in the same picture, and the comparing module 24 may include: the second determining submodule 241 is configured to determine that the picture is a false picture when the similarity is greater than or equal to a preset threshold, and otherwise, determine that the picture is a real picture.
In another embodiment, the first facial picture is selected from an image, the second facial picture is selected from an image, and the comparing module 24 may include: and a third determining sub-module 242, configured to determine that the first face picture and the second face picture belong to the same person when the similarity is greater than or equal to a preset threshold, and otherwise, determine that the first face picture and the second face picture do not belong to the same person.
For more details of the working principle and the working mode of the face recognition apparatus 2, reference may be made to the related description in fig. 1, and details are not repeated here.
Further, the embodiment of the present invention further discloses a storage medium, on which computer instructions are stored, and when the computer instructions are executed, the technical solution of the method in the embodiment shown in fig. 1 is executed. Preferably, the storage medium may include a computer-readable storage medium such as a non-volatile (non-volatile) memory or a non-transitory (non-transient) memory. The storage medium may include ROM, RAM, magnetic or optical disks, etc.
Further, the embodiment of the present invention also discloses a computing device, which includes a memory and a processor, where the memory stores computer instructions capable of running on the processor, and when the processor runs the computer instructions, the computing device executes the technical solution of the method described in the embodiment shown in fig. 1.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A face recognition method, comprising:
acquiring a first face picture and a second face picture;
extracting the features of the first face picture and the second face picture based on a scale invariant feature transform algorithm to obtain the feature vectors of the first face picture and the second face picture respectively;
judging the similarity of the first face picture and the second face picture according to the feature vector;
and comparing the similarity with a preset threshold value to determine whether the first face picture and the second face picture are the same face picture.
2. The method according to claim 1, wherein the obtaining the first face picture and the second face picture comprises:
and acquiring the first face picture and the second face picture based on a multi-task cascade convolution network face detection and alignment algorithm.
3. The method according to claim 1, wherein the feature vector of the first face picture includes a plurality of first keypoint feature vectors, the feature vector of the second face picture includes a plurality of second keypoint feature vectors, and the determining the similarity between the first face picture and the second face picture according to the feature vectors includes:
traversing and calculating Euclidean distances between the first key point feature vectors and the second key point feature vectors for all the first key point feature vectors and all the second key point feature vectors to obtain a Euclidean distance set;
and for each Euclidean distance in the Euclidean distance set, determining the number of Euclidean distances smaller than a preset Euclidean distance, and taking the number as the similarity.
4. The method of claim 3, wherein the step of calculating the Euclidean distance between the first keypoint feature vector and the second keypoint feature vector comprises:
and traversing and calculating the Euclidean distance between the first key point feature vector and the second key point feature vector by adopting a storm wind algorithm.
5. The face recognition method according to any one of claims 1 to 4, wherein the first face picture and the second face picture are located in the same picture, and the comparing the similarity with a preset threshold to determine whether the first face picture and the second face picture are the same face comprises:
and when the similarity is larger than or equal to a preset threshold value, determining that the picture is a false picture, otherwise, determining that the picture is a real picture.
6. The method according to any one of claims 1 to 4, wherein the first face picture is selected from an image, the second face picture is selected from an image, and the comparing the similarity with a preset threshold to determine whether the first face picture and the second face picture are the same face picture comprises:
and when the similarity is larger than or equal to a preset threshold value, determining that the first face picture and the second face picture belong to the same person, otherwise, determining that the first face picture and the second face picture do not belong to the same person.
7. A face recognition apparatus, comprising:
the acquisition module is used for acquiring a first face picture and a second face picture;
the extraction module is used for extracting the features of the first face picture and the second face picture based on a scale invariant feature transform algorithm so as to obtain the feature vectors of the first face picture and the second face picture respectively;
the judging module is used for judging the similarity of the first face picture and the second face picture according to the feature vector;
and the comparison module is used for comparing the similarity with a preset threshold value so as to determine whether the first face picture and the second face picture are the same face picture.
8. The face recognition apparatus of claim 7, wherein the obtaining module comprises: and the acquisition sub-module is used for carrying out face detection and alignment algorithm based on a multitask cascade convolution network to acquire the first face picture and the second face picture.
9. A storage medium having stored thereon computer instructions, characterized in that the computer instructions are operative to perform the steps of the method of any one of claims 1 to 6.
10. A computing device comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, wherein the processor, when executing the computer instructions, performs the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910967124.XA CN110751071A (en) | 2019-10-12 | 2019-10-12 | Face recognition method and device, storage medium and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910967124.XA CN110751071A (en) | 2019-10-12 | 2019-10-12 | Face recognition method and device, storage medium and computing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110751071A true CN110751071A (en) | 2020-02-04 |
Family
ID=69278060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910967124.XA Pending CN110751071A (en) | 2019-10-12 | 2019-10-12 | Face recognition method and device, storage medium and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110751071A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652148A (en) * | 2020-06-04 | 2020-09-11 | 航天科工智慧产业发展有限公司 | Face recognition method and device and electronic equipment |
| CN111814697A (en) * | 2020-07-13 | 2020-10-23 | 伊沃人工智能技术（江苏）有限公司 | Real-time face recognition method and system and electronic equipment |
| CN113536844A (en) * | 2020-04-16 | 2021-10-22 | 中移(成都)信息通信科技有限公司 | Face comparison method, device, equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101510257A (en) * | 2009-03-31 | 2009-08-19 | 华为技术有限公司 | Human face similarity degree matching method and device |
| CN104036524A (en) * | 2014-06-18 | 2014-09-10 | 哈尔滨工程大学 | Fast target tracking method with improved SIFT algorithm |
| CN108268881A (en) * | 2016-12-30 | 2018-07-10 | 中兴通讯股份有限公司 | Electronic equipment, target image identification method and device |
| CN109063581A (en) * | 2017-10-20 | 2018-12-21 | 奥瞳系统科技有限公司 | Enhanced Face datection and face tracking method and system for limited resources embedded vision system |
| CN109934118A (en) * | 2019-02-19 | 2019-06-25 | 河北大学 | A kind of hand back vein personal identification method |
-
2019
- 2019-10-12 CN CN201910967124.XA patent/CN110751071A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101510257A (en) * | 2009-03-31 | 2009-08-19 | 华为技术有限公司 | Human face similarity degree matching method and device |
| CN104036524A (en) * | 2014-06-18 | 2014-09-10 | 哈尔滨工程大学 | Fast target tracking method with improved SIFT algorithm |
| CN108268881A (en) * | 2016-12-30 | 2018-07-10 | 中兴通讯股份有限公司 | Electronic equipment, target image identification method and device |
| CN109063581A (en) * | 2017-10-20 | 2018-12-21 | 奥瞳系统科技有限公司 | Enhanced Face datection and face tracking method and system for limited resources embedded vision system |
| CN109934118A (en) * | 2019-02-19 | 2019-06-25 | 河北大学 | A kind of hand back vein personal identification method |
Non-Patent Citations (3)
| Title |
|---|
| HIRDESH KUMAR ET AL.: ""Face Recognition using SIFT by varying Distance Calculation Matching Method"", 《INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS(0975-888)》 * |
| KAIPENG ZHANG ET AL.: ""Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks"", 《IEEE》 * |
| 闫家梅: ""基于SIFT特征的人脸识别"", 《科学技术与工程》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113536844A (en) * | 2020-04-16 | 2021-10-22 | 中移(成都)信息通信科技有限公司 | Face comparison method, device, equipment and medium |
| CN113536844B (en) * | 2020-04-16 | 2023-10-31 | 中移(成都)信息通信科技有限公司 | Face comparison method, device, equipment and medium |
| CN111652148A (en) * | 2020-06-04 | 2020-09-11 | 航天科工智慧产业发展有限公司 | Face recognition method and device and electronic equipment |
| CN111814697A (en) * | 2020-07-13 | 2020-10-23 | 伊沃人工智能技术（江苏）有限公司 | Real-time face recognition method and system and electronic equipment |
| CN111814697B (en) * | 2020-07-13 | 2024-02-13 | 伊沃人工智能技术（江苏）有限公司 | Real-time face recognition method and system and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bulatov et al. | Smart IDReader: Document recognition in video stream | |
| Priesnitz et al. | An overview of touchless 2D fingerprint recognition | |
| Garcia et al. | Face-spoofing 2D-detection based on Moiré-pattern analysis | |
| US8064653B2 (en) | Method and system of person identification by facial image | |
| Pang et al. | Classifying discriminative features for blur detection | |
| US9489566B2 (en) | Image recognition apparatus and image recognition method for identifying object | |
| Deepa et al. | Face recognition using spectrum-based feature extraction | |
| WO2019061658A1 (en) | Method and device for positioning eyeglass, and storage medium | |
| WO2016084072A1 (en) | Anti-spoofing system and methods useful in conjunction therewith | |
| CN110751071A (en) | Face recognition method and device, storage medium and computing equipment | |
| US11367310B2 (en) | Method and apparatus for identity verification, electronic device, computer program, and storage medium | |
| Hammudoglu et al. | Portable trust: biometric-based authentication and blockchain storage for self-sovereign identity systems | |
| CN110866466A (en) | Face recognition method, face recognition device, storage medium and server | |
| CN111079816A (en) | Image auditing method and device and server | |
| CN112200136A (en) | Certificate authenticity identification method and device, computer readable medium and electronic equipment | |
| CN110838119A (en) | Human face image quality evaluation method, computer device and computer readable storage medium | |
| Yeh et al. | Face liveness detection based on perceptual image quality assessment features with multi-scale analysis | |
| CN109815823B (en) | Data processing method and related product | |
| CN111783770A (en) | Image rectification method, device and computer readable storage medium | |
| CN111222452A (en) | Face matching method and device, electronic equipment and readable storage medium | |
| KR100777922B1 (en) | System For Personal Authentication and Electronic Signature Using Image Recognition And Method Thereof | |
| Yeh et al. | Face liveness detection with feature discrimination between sharpness and blurriness | |
| Chen et al. | Face deduplication in video surveillance | |
| Waris et al. | Analysis of textural features for face biometric anti-spoofing | |
| Liu et al. | Face liveness detection based on enhanced local binary patterns |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200204 |