CN110070017B - Method and device for generating human face artificial eye image - Google Patents
Method and device for generating human face artificial eye image Download PDFInfo
- Publication number
- CN110070017B CN110070017B CN201910295861.XA CN201910295861A CN110070017B CN 110070017 B CN110070017 B CN 110070017B CN 201910295861 A CN201910295861 A CN 201910295861A CN 110070017 B CN110070017 B CN 110070017B
- Authority
- CN
- China
- Prior art keywords
- image
- eye
- shielding
- human
- gray
- 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.)
- Active
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
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of human eye shielding data generation and identification, in particular to a human face artificial eye image generation method and a human face artificial eye image generation device. The human face artificial eye image generation method comprises the following steps: acquiring human eye key points, namely acquiring human eye key points through a human face image, wherein the human eye key points comprise a left eye key point and a right eye key point; a step of creating a shielding template, wherein the shielding template for shielding the eye is created and comprises a gray level image, the center of the gray level image is provided with a gray point, and the gray point is higher than the gray level value of the rest part of the gray level image; generating an eye shielding image, namely generating the eye shielding image according to the key points of human eyes and a shielding template; and affine step, affine the eye shielding image to the eye position of the human face image to generate a human face artificial eye image. By using the method, a large amount of face image data does not need to be acquired, and under the premise of not influencing other functions of the face recognition system, the problem of eye shielding attack can be effectively solved, and the cost is saved.
Description
Technical Field
The present invention relates generally to the field of face recognition technology, and in particular, to a method and an apparatus for generating a face pseudoeye image.
Background
With the progress of computer graphics and image processing technologies, face recognition has received a great deal of attention. As the most common biological identification technology, the biological identification technology is widely applied to criminal identification systems, customs and bank monitoring systems, automatic entrance guard systems for daily life, office attendance systems, mobile phone security systems and the like. In most scenes, the recognition result is easily interfered by information loss caused by local shielding of the face. Shielding the face can bring huge potential safety hazards.
In practical application, a malicious attack often occurs to shield the eye information, so that the acquisition of the eye information is incomplete. Face recognition systems fail to prevent such attacks and result in face recognition passing.
The human face image shielding data is collected through amplification, the problem of human face image eye information shielding is solved, the cost is easily overhigh, the covered data distribution is narrow, and the effect is not obvious if the collected data is small in total data amount.
Disclosure of Invention
In order to solve the above problems in the prior art, the present invention provides a method and an apparatus for generating a human face artificial eye image.
In a first aspect, an embodiment of the present invention provides a method for generating an image of a human face with an artificial eye, including: acquiring human eye key points, namely acquiring human eye key points through a human face image, wherein the human eye key points comprise a left eye key point and a right eye key point; a step of creating a shielding template, wherein the shielding template for shielding the eye is created and comprises a gray level image, the center of the gray level image is provided with a gray point, and the gray point is higher than the gray level value of the rest part of the gray level image; generating an eye shielding image, namely generating the eye shielding image according to the key points of human eyes and a shielding template; affine step, affine the eye shielding image to the eye position of the human face image to generate the human face artificial eye image
In one embodiment, the step of generating an eye-blocking image further comprises: the image transformation step, carrying out random transformation on the shape of the shielding template to obtain a transformed shielding template, wherein the random transformation comprises the transformation of the size, the height-width ratio and the horizontal angle of the shielding template; and generating an eye shielding image based on the combination of the transformed shielding template and the key points of the human eyes.
In one embodiment, the image transforming step further comprises: and randomly transforming the gray value of the gray map to obtain a transformed gray map, wherein the transformed gray points are higher than the gray value of the rest part of the gray map.
In another embodiment, in the step of creating an occlusion template, the occlusion template further includes a binary image, the binary image has the same shape as the gray-scale image, an ellipse is embedded in the binary image, an inner pixel value of the ellipse is 1, and an outer pixel value of the ellipse is 0.
In another embodiment, the step of generating an eye occlusion image further comprises: acquiring a human eye local image, namely acquiring the human eye local image with the same size as the gray image according to human eye key points and the gray image; and a generation step of generating an eye-shielding image having the same elliptical shape from the partial image of the human eye, the gray-scale image, and the binary image.
In one embodiment, the step of obtaining the key points of the human eyes further comprises: a plurality of eye key points are obtained through the face image, and eye key points corresponding to the left eye and the right eye are respectively selected as the eye key points.
In a second aspect, an embodiment of the present invention provides a training method for an artificial eye shielding model, where the artificial eye shielding model is trained by training sample data, and the training sample data is generated by a human face artificial eye image generation method.
In a third aspect, an embodiment of the present invention provides a device for generating an image of a human face with artificial eyes, where the device includes: the human eye key point acquisition module is used for acquiring human eye key points through a human face image; and the shielding template creating module is used for creating a rectangular two-dimensional gray scale map as a shielding template, wherein the shielding template comprises: the gray-scale image and the binary image are formed, wherein the size of the gray-scale image is the same as that of the binary image; the eye shielding image generating module is used for generating an eye shielding image according to the key points of the human eyes and the shielding template; and the affine module is used for affine matching the eye shielding image to the eye position of the human face image to generate a human face pseudoeye image.
In a fourth aspect, an embodiment of the present invention provides a training device for an artificial eye shielding model, configured to train the artificial eye shielding model through training sample data, where the training sample data is generated by a human face artificial eye image generation method.
In a fifth aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes: a memory to store instructions; and a processor for calling the instructions stored in the memory to execute the texture image generation method.
In a sixth aspect, embodiments of the present invention provide a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions that, when executed by a processor, perform a method for generating an image of a human facial prosthesis.
According to the method and the device for generating the face pseudoeye image, a large amount of face image data does not need to be acquired, and the problem of eye shielding attack can be effectively solved on the premise that other functions of a face recognition system are not influenced, so that the cost is saved.
Drawings
The above and other objects, features and advantages of embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
fig. 1 is a schematic diagram illustrating an eye occlusion data generation method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating another eye occlusion data generation method according to an embodiment of the invention;
FIG. 3 is a schematic diagram illustrating another eye occlusion data generation method according to an embodiment of the invention;
FIG. 4 is a schematic diagram illustrating another eye occlusion data generation method according to an embodiment of the invention;
FIG. 5 is a schematic diagram illustrating an apparatus for generating an image of a human face with artificial eyes according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of an electronic device provided by an embodiment of the invention;
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Detailed Description
The principles and spirit of the present invention will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the invention, and are not intended to limit the scope of the invention in any way.
It should be noted that although the expressions "first", "second", etc. are used herein to describe different modules, steps, data, etc. of the embodiments of the present invention, the expressions "first", "second", etc. are merely used to distinguish between different modules, steps, data, etc. and do not indicate a particular order or degree of importance. Indeed, the terms "first," "second," and the like are fully interchangeable.
Fig. 1 is a flowchart illustrating an embodiment of a method 10 for generating an image of a human face and an artificial eye. As shown in fig. 1, the method of this embodiment includes: the method comprises the steps of acquiring human eye key points 110, creating an occlusion template 120, generating an eye occlusion image 130 and affine processing 140. The respective steps in fig. 1 are explained in detail below.
Acquiring human eye key points 110, acquiring human eye key points through a human face image, wherein the human eye key points comprise a left eye key point and a right eye key point.
In this embodiment, key points of human eyes are obtained through a face image, and one key point is obtained for each of the left and right eyes. In one example, the human eye key points are obtained through human face key point model detection; in another example, the key points of the human eyes are identified through manual marking, and the key points of the human eyes are obtained. The face image used may be a grayscale image or a color image. The face image can be acquired by image acquisition equipment, such as: the mobile phone camera and the computer camera can be called from a local database or a cloud.
Creating a blocking template step 120, creating a blocking template for blocking the eye, wherein the blocking template comprises a gray scale map, the center of the gray scale map is provided with a gray point, and the gray point is higher than the gray value of the rest part of the gray scale map.
In the embodiment, the gray-scale map is created to be used for shielding the eye image to be shielded in the face image. The creation center is provided with a gray map having a gray point higher than the gray value of the rest of the gray map. In one example, the gradation value of the gradation map is a fixed value. In another example, the gray scale value in the gray scale map is a random value, for example, the color of the gray scale map is normalized to change the value range (0, 255) of the original color to (0, 1), which is convenient for adjusting the pixel color. The color span of the grayscale image ground color is between (0.1, 0.4), the color span of the center point is between (0.7, 1.0), and the position of the white point is between one and five pixels in the center of the grayscale image. The image pixels of the used grayscale image are randomly generated within the respective value range interval.
And a step 130 of generating an eye shielding image, namely generating the eye shielding image according to the key points of human eyes and the shielding template.
In this embodiment, the positions of the human eyes in the face image are determined by the human eye key points, and an eye shielding image with the same size as the shielding template is generated according to the combination of the shielding template and the human eye key points.
And an affine step 140 of affine the eye shielding image to the eye position of the human face image to generate a human face pseudoeye image.
In this embodiment, through affine transformation, the generated eye blocking image is affine-matched to the eyes in the face image to cover the eye image in the original face image, and a human face pseudoeye image is generated.
Fig. 2 is a flowchart illustrating another embodiment of the method 10 for generating an image of a human face and an artificial eye. As shown in fig. 2, the method of this embodiment includes: an image transformation step 131. Fig. 2 is explained in detail below.
An image transformation step 131, randomly transforming the shape of the shielding template to obtain a transformed shielding template, wherein the random transformation includes transforming the size, the aspect ratio and the horizontal angle of the shielding template; and generating an eye shielding image based on the combination of the transformed shielding template and the key points of the human eyes. In one example, the size, the aspect ratio, or the horizontal angle of the shielding template may be randomly transformed within a certain threshold, for example, the shielding template only transforms the image size, and the random transformation is performed within a certain threshold, for example, the size changes in a (0.7, 1.0) value range, and other image attributes do not change; or only carrying out random conversion on the aspect ratio of the shielding template within a certain threshold value. In another example, the size, the aspect ratio and the horizontal angle of the shielding template are simultaneously transformed within a certain threshold value to generate various shielding templates, and the various shielding templates are combined with key points of human eyes to generate various eye shielding images, so that a face recognition model can learn human eye shielding data.
In one embodiment, the image transforming step 131 further comprises: and randomly transforming the gray values of the gray map to obtain a transformed gray map, wherein the transformed gray points are higher than the gray values of the rest parts of the gray map, and a plurality of gray maps are generated. The method is used for combining with human eye key points to generate various eye shielding images, and is beneficial to a human face recognition model to learn human eye shielding data. For example, the color span of the grayscale image ground color is between (0.1, 0.4), the color span of the center point is between (0.7, 1.0), and the position of the white point is between one and five pixels in the center of the grayscale image. The image pixels of the used gray level images are randomly changed in the respective value range intervals to generate various gray level images with different gray level values, which is beneficial to training the false eye shielding model.
In another embodiment, in the step 120 of creating an occlusion template, the occlusion template further includes a binary image, the binary image has the same shape as the gray-scale image, an ellipse is embedded in the binary image, an inner pixel value of the ellipse is 1, and an outer pixel value of the ellipse is 0. The interior of the binary image ellipse is used for reserving image pixels left by multiplying the gray image and the binary image, and the exterior of the ellipse is used for reserving image pixels of the face image. The larger the ellipse embedded in the binary image, the larger the range of pixels that remain multiplied by it.
Fig. 3 and 4 are flow diagrams illustrating further embodiments of a method 10 for generating an image of a human face prosthesis. As shown in fig. 3 and 4, the method of this embodiment includes: a step 132 of acquiring a partial image of human eyes and a step 133 of generating. The respective steps in fig. 3 and 4 are explained in detail below.
And a step 132 of acquiring a local image of the human eye, wherein the local image of the human eye with the same size as the gray image is acquired according to the key points and the gray image of the human eye.
In an embodiment, according to the obtained key points of the human eyes, the local images of the human eyes with the same size as the gray-scale image are obtained by taking the key points of the human eyes as the center, so that the generated eye shielding images have the same size as the obtained local images of the human eyes.
A generating step 133 generates an eye-shielding image having the same elliptical shape from the partial image of the human eye, the gray-scale image, and the binary image.
And multiplying the human eye local image by the inverse binary image to obtain a human eye local edge image with a middle pixel value of 0 in the human eye local image, wherein the size of the area with the middle pixel value of 0 is the same as the size and the position of the ellipse embedded in the binary image, and the pixels outside the ellipse are unchanged. The inverse binary image pixel assignment is opposite to that of the binary image, the ellipse inner pixel value is 0, and the ellipse outer pixel value is 1. And multiplying the binary image by the gray image, and reserving the elliptical image of which the center of the gray image is the same as the size of the ellipse embedded in the binary image. And combining the generated human eye local edge image with the elliptical image to generate an eye shielding image which has the same size as the acquired human eye local image but is an elliptical gray scale image inside the image. And affine the generated eye shielding image to the eyes in the face image to cover the eye image in the original face image and generate a human face artificial eye image.
In one embodiment, the step 110 of obtaining the human eye key points further comprises: a plurality of eye key points are obtained through the face image, and eye key points corresponding to the left eye and the right eye are respectively selected as the eye key points. By selecting eye key points corresponding to the left and right eyes, the human face artificial eye images with the same left and right eye shielding positions can be generated. In another embodiment, any key point of the left and right eyes can be randomly acquired to generate the artificial eye images of the human face with different occlusion positions of the left and right eyes.
The embodiment of the invention also provides a training method of the artificial eye shielding model, the artificial eye shielding model is trained through training sample data, and the training sample data is generated through the human face artificial eye image generation method of any one of the embodiments. The method for generating the human face artificial eye image is suitable for training an eye blocking model. By using the generated various human face artificial eye images as model learning materials, the artificial eye shielding model can learn data shielded by human eyes under various conditions, the accuracy rate of human eye shielding identification is improved, and eye shielding attack is prevented.
Fig. 5 is a schematic structural diagram of an embodiment of the image generating apparatus 20 for artificial eye of a human face. As shown in fig. 5, the face pseudoeye image generating apparatus includes: a human eye key point obtaining module 210, configured to obtain human eye key points through a face image, where the human eye key points include a left eye key point and a right eye key point; a block template creating module 220 for creating a block template for blocking the eye, wherein the block template comprises a gray level map, a gray point is arranged in the center of the gray level map, and the gray point is higher than the gray level of the rest part of the gray level map; an eye shielding image generating module 230, configured to generate an eye shielding image according to the eye key points and the shielding template; and the affine module 240 is configured to affine the eye blocking image to the eye position of the human face image to generate a human face pseudoeye image.
In an embodiment, the generate eye-occlusion image module 230 further comprises: and the image transformation module 231 is used for randomly transforming the shape of the shielding template, including transforming the size, the aspect ratio and the horizontal angle of the shielding template.
In an embodiment, the image transformation module 231 is further configured to randomly transform the gray scale value of the gray scale map, and the transformed gray point is higher than the gray scale value of the rest of the gray scale map.
In an embodiment, the generate eye-occlusion image module 230 further comprises: a module 232 for obtaining a local image of human eye, which is used for obtaining a local image of human eye with the same size as the gray image according to the key points of human eye and the gray image; the generating module 233 is configured to generate an eye shielding image having the same elliptical shape according to the eye local image and the shielding template.
The embodiment of the invention also provides a training device for the artificial eye shielding model, which is used for training the artificial eye shielding model through training sample data, wherein the training sample data is generated through the human face artificial eye image generation method of any one of the embodiments.
The functions implemented by the modules in the apparatus correspond to the steps in the method described above, and for concrete implementation and technical effects, please refer to the description of the method steps above, which is not described herein again.
As shown in fig. 6, one embodiment of the present invention provides an electronic device 30. The electronic device 30 includes a memory 310, a processor 320, and an Input/Output (I/O) interface 330. The memory 310 is used for storing instructions. And a processor 320 for calling the instructions stored in the memory 310 to execute the method for generating the image of the artificial eye of the human face according to the embodiment of the invention. The processor 320 is connected to the memory 310 and the I/O interface 330, respectively, for example, via a bus system and/or other connection mechanism (not shown). The memory 310 may be used to store programs and data, including programs for eye occlusion data generation involved in embodiments of the present invention, and the processor 320 executes various functional applications and data processing of the electronic device 30 by running the programs stored in the memory 310.
In an embodiment of the present invention, the processor 320 may be implemented in at least one hardware form of a Digital Signal Processor (DSP), a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), and the processor 320 may be one or a combination of several Central Processing Units (CPUs) or other forms of Processing units with data Processing capability and/or instruction execution capability.
In the embodiment of the present invention, the I/O interface 330 may be used to receive input instructions (e.g., numeric or character information, and generate key signal inputs related to user settings and function control of the electronic device 30, etc.), and may also output various information (e.g., images or sounds, etc.) to the outside. The I/O interface 330 may comprise one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a mouse, a joystick, a trackball, a microphone, a speaker, a touch panel, and the like.
In some embodiments, the invention provides a computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, perform any of the methods described above.
Although operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in serial order, or that all illustrated operations be performed, to achieve desirable results. In certain environments, multitasking and parallel processing may be advantageous.
The methods and apparatus of the present invention can be accomplished with standard programming techniques with rule based logic or other logic to accomplish the various method steps. It should also be noted that the words "means" and "module," as used herein and in the claims, is intended to encompass implementations using one or more lines of software code, and/or hardware implementations, and/or equipment for receiving inputs.
Any of the steps, operations, or procedures described herein may be performed or implemented using one or more hardware or software modules, alone or in combination with other devices. In one embodiment, the software modules are implemented using a computer program product comprising a computer readable medium containing computer program code, which is executable by a computer processor for performing any or all of the described steps, operations, or procedures.
The foregoing description of the implementation of the invention has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise form disclosed, and modifications and variations are possible in light of the above teachings or may be acquired from practice of the invention. The embodiments were chosen and described in order to explain the principles of the invention and its practical application to enable one skilled in the art to utilize the invention in various embodiments and with various modifications as are suited to the particular use contemplated.
Claims (9)
1. A human face pseudoeye image generation method comprises the following steps:
acquiring human eye key points, namely acquiring human eye key points through a human face image, wherein the human eye key points comprise a left eye key point and a right eye key point;
creating a shielding template for shielding eyes, wherein the shielding template comprises a gray level image, the center of the gray level image is provided with a gray point, and the gray point is higher than the gray value of the rest part of the gray level image; the shielding template further comprises a binary image, the binary image is the same as the gray image in shape, an ellipse is embedded in the binary image, the internal pixel value of the ellipse is 1, and the external pixel value is 0;
generating an eye shielding image, namely generating the eye shielding image according to the key points of the human eyes and the shielding template;
affine transformation, wherein the generated eye shielding image is affine to the eye position of the human face image through affine transformation, the eye image in the original human face image is covered, and a human face artificial eye image is generated;
correspondingly, the step of generating the eye blocking image comprises the following steps:
acquiring a human eye local image, namely acquiring the human eye local image with the same size as the gray image according to the human eye key points and the gray image;
and a generation step of generating the eye shielding image having the same elliptical shape from the partial image of the human eye, the gray scale image, and the binary image.
2. The method of claim 1, wherein the generating an eye occlusion image step further comprises:
an image transformation step, wherein the shape of the shielding template is randomly transformed to obtain the transformed shielding template, and the random transformation comprises the transformation of the size, the height-width ratio and the horizontal angle of the shielding template; and generating the eye shielding image based on the combination of the transformed shielding template and the key points of the human eyes.
3. The method of claim 2, wherein the image transforming step further comprises: and randomly transforming the gray value of the gray map to obtain the transformed gray map, wherein the transformed gray points are higher than the gray value of the rest part of the gray map.
4. The method of claim 1, wherein the step of obtaining human eye keypoints further comprises: and acquiring a plurality of eye key points through the face image, and respectively selecting the eye key points corresponding to the left eye and the right eye as the eye key points.
5. A training method of an artificial eye shielding model, which trains the artificial eye shielding model by training sample data, wherein the training sample data is generated by the human face artificial eye image generation method according to any one of claims 1 to 4.
6. An image generation device for a human face pseudoeye comprises:
the human eye key point acquisition module is used for acquiring human eye key points through a human face image, wherein the human eye key points comprise a left eye key point and a right eye key point;
the eye shielding method comprises the steps of creating a shielding template module, creating a shielding template for shielding eyes, wherein the shielding template comprises a gray map, the center of the gray map is provided with a gray point, and the gray point is higher than the gray value of the rest part of the gray map;
the eye shielding image generating module is used for generating an eye shielding image according to the key points of the human eyes and the shielding template;
the affine module is used for affine transforming the generated eye shielding image to the eye position of the human face image, covering the eye image in the original human face image and generating a human face pseudoeye image;
correspondingly, the module for generating the eye blocking image further comprises: the module for acquiring the human eye local image is used for acquiring the human eye local image with the same size as the gray image according to the human eye key points and the gray image; and the generating module is used for generating an eye shielding image which is the same as the elliptical shape according to the human eye local image and the shielding template.
7. A training device of an artificial eye shielding model is used for training the artificial eye shielding model through training sample data, wherein the training sample data is generated through the human face artificial eye image generation method of any one of claims 1 to 4.
8. An electronic device, wherein the electronic device comprises:
a memory to store instructions; and
a processor for calling the instructions stored in the memory to execute the method for generating the image of the human face pseudoeye according to any one of claims 1 to 4 or the method for training the pseudoeye occlusion model according to claim 5.
9. A computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions that, when executed by a processor, perform the method for generating an image of a human face pseudoeye according to any one of claims 1 to 4 or the method for training a pseudoeye occlusion model according to claim 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910295861.XA CN110070017B (en) | 2019-04-12 | 2019-04-12 | Method and device for generating human face artificial eye image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910295861.XA CN110070017B (en) | 2019-04-12 | 2019-04-12 | Method and device for generating human face artificial eye image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110070017A CN110070017A (en) | 2019-07-30 |
| CN110070017B true CN110070017B (en) | 2021-08-24 |
Family
ID=67367716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910295861.XA Active CN110070017B (en) | 2019-04-12 | 2019-04-12 | Method and device for generating human face artificial eye image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110070017B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110610127B (en) * | 2019-08-01 | 2023-10-27 | 平安科技（深圳）有限公司 | Face recognition method and device, storage medium and electronic equipment |
| CN113673278A (en) * | 2020-05-13 | 2021-11-19 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN111882627B (en) * | 2020-07-20 | 2024-08-20 | 广州市百果园信息技术有限公司 | Image processing method, video processing method, apparatus, device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034079A (en) * | 2009-09-24 | 2011-04-27 | 汉王科技股份有限公司 | Method and system for identifying faces shaded by eyeglasses |
| CN103218605A (en) * | 2013-04-09 | 2013-07-24 | 东南大学 | Quick eye locating method based on integral projection and edge detection |
| CN105184253A (en) * | 2015-09-01 | 2015-12-23 | 北京旷视科技有限公司 | Face identification method and face identification system |
| CN107833197A (en) * | 2017-10-31 | 2018-03-23 | 广东欧珀移动通信有限公司 | Method, apparatus, computer-readable recording medium and the electronic equipment of image procossing |
| CN109165571A (en) * | 2018-08-03 | 2019-01-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for being inserted into image |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100695155B1 (en) * | 2005-06-18 | 2007-03-14 | 삼성전자주식회사 | Apparatus and method for detecting occluded face and apparatus and method for discriminating illicit transactor employing the same |
| US8571272B2 (en) * | 2006-03-12 | 2013-10-29 | Google Inc. | Techniques for enabling or establishing the use of face recognition algorithms |
| US9690979B2 (en) * | 2006-03-12 | 2017-06-27 | Google Inc. | Techniques for enabling or establishing the use of face recognition algorithms |
| US9323980B2 (en) * | 2011-05-13 | 2016-04-26 | Microsoft Technology Licensing, Llc | Pose-robust recognition |
| KR101956071B1 (en) * | 2015-01-13 | 2019-03-08 | 삼성전자주식회사 | Method and apparatus for verifying a user |
| EP3185176A1 (en) * | 2015-12-21 | 2017-06-28 | THOMSON Licensing | Method and device for synthesizing an image of a face partially occluded |
| CN106096560A (en) * | 2016-06-15 | 2016-11-09 | 广州尚云在线科技有限公司 | A kind of face alignment method |
-
2019
- 2019-04-12 CN CN201910295861.XA patent/CN110070017B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034079A (en) * | 2009-09-24 | 2011-04-27 | 汉王科技股份有限公司 | Method and system for identifying faces shaded by eyeglasses |
| CN103218605A (en) * | 2013-04-09 | 2013-07-24 | 东南大学 | Quick eye locating method based on integral projection and edge detection |
| CN105184253A (en) * | 2015-09-01 | 2015-12-23 | 北京旷视科技有限公司 | Face identification method and face identification system |
| CN107833197A (en) * | 2017-10-31 | 2018-03-23 | 广东欧珀移动通信有限公司 | Method, apparatus, computer-readable recording medium and the electronic equipment of image procossing |
| CN109165571A (en) * | 2018-08-03 | 2019-01-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for being inserted into image |
Non-Patent Citations (5)
| Title |
|---|
| "PCANet下的遮挡定位人脸识别算法";郭伟等;《计算机科学与探索》;20190130;第13卷(第12期);全文 * |
| "Random Gabor based templates for facial expression recognition in images with facial occlusion";Ligang Zhang等;《Neurocomputing》;20141205;第145卷;全文 * |
| "ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing";C. Lin等;《2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition》;20181217;全文 * |
| "TUOD遮挡图像库的设计与实现";高磊等;《图学学报》;20181215;第2018年卷(第6期);全文 * |
| "基于生成式对抗网络的人脸眼镜迁移";陈民钦;《中国优秀硕士学位论文全文数据库·信息科技辑》;20190215;第2019年卷(第2期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110070017A (en) | 2019-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022161286A1 (en) | Image detection method, model training method, device, medium, and program product | |
| CN105917353B (en) | Feature extraction and matching for biological identification and template renewal | |
| US8792722B2 (en) | Hand gesture detection | |
| CN112084917B (en) | Living body detection method and device | |
| CN110070017B (en) | Method and device for generating human face artificial eye image | |
| CN110991533B (en) | Image recognition method, recognition device, terminal device and readable storage medium | |
| KR20200118076A (en) | Biometric detection method and device, electronic device and storage medium | |
| US11436436B2 (en) | Data augmentation system, data augmentation method, and information storage medium | |
| CN110163111A (en) | Method, apparatus of calling out the numbers, electronic equipment and storage medium based on recognition of face | |
| CN111027628B (en) | Model determination method and system | |
| WO2019200702A1 (en) | Descreening system training method and apparatus, descreening method and apparatus, device, and medium | |
| CN110046622B (en) | Targeted attack sample generation method, device, equipment and storage medium | |
| CN110852311A (en) | Three-dimensional human hand key point positioning method and device | |
| CN110969046B (en) | Face recognition method, face recognition device and computer-readable storage medium | |
| CN110765843B (en) | Face verification method, device, computer equipment and storage medium | |
| WO2019232850A1 (en) | Method and apparatus for recognizing handwritten chinese character image, computer device, and storage medium | |
| CN111639667B (en) | Image recognition method, device, electronic equipment and computer readable storage medium | |
| CN110059607B (en) | Living body multiplex detection method, living body multiplex detection device, computer equipment and storage medium | |
| CN112529888B (en) | Face image evaluation method, device, equipment and medium based on deep learning | |
| CN112651953A (en) | Image similarity calculation method and device, computer equipment and storage medium | |
| CN113919497A (en) | Attack and defense method based on feature manipulation for continuous learning ability system | |
| CN113221601B (en) | Character recognition method, device and computer readable storage medium | |
| CN111353325A (en) | Key point detection model training method and device | |
| CN116543261A (en) | Model training method for image recognition, image recognition method device and medium | |
| EP4064215A2 (en) | Method and apparatus for face anti-spoofing |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |