CN111047632A - Method and device for processing picture color of nail image - Google Patents
Method and device for processing picture color of nail image Download PDFInfo
- Publication number
- CN111047632A CN111047632A CN201911223438.5A CN201911223438A CN111047632A CN 111047632 A CN111047632 A CN 111047632A CN 201911223438 A CN201911223438 A CN 201911223438A CN 111047632 A CN111047632 A CN 111047632A
- Authority
- CN
- China
- Prior art keywords
- nail
- image
- sticker
- color
- hand image
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004040 coloring Methods 0.000 claims abstract description 11
- 230000009466 transformation Effects 0.000 claims description 19
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 13
- 230000004927 fusion Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 5
- 230000004807 localization Effects 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000011897 real-time detection Methods 0.000 abstract description 3
- 210000000282 nail Anatomy 0.000 description 150
- 238000012549 training Methods 0.000 description 21
- 238000010586 diagram Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 210000004905 finger nail Anatomy 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 2
- 230000003416 augmentation Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/49—Analysis of texture based on structural texture description, e.g. using primitives or placement rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of image processing, and discloses a method and a device for processing the image color of a nail image, wherein the method comprises the steps of obtaining a first hand image containing a nail; determining a nail region in the first hand image; carrying out image color processing on the nail area to obtain a second hand image; and outputting/displaying the second hand image. The invention can be used for detecting the nail area in real time and coloring the nail according to the color or the pattern appointed by the user, and has the advantages of small model, high speed, real-time detection and coloring, and different nail beautifying experience for the user.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a method and a device for processing a picture color of a nail image, a storage medium and electronic equipment.
Background
At present, image processing applications on intelligent electronic devices are increasing, and for example, application software for beautifying faces in real time on a smart phone is very abundant. However, relatively few applications are made for nail art.
For example, a user wants to make a nail art product, but does not know the effect after nail art, and how to simulate the effect after the user finishes making the nail art product in real time before nail art is not available in the prior art.
Disclosure of Invention
The application provides a method and a device for processing the image color of a nail image, a storage medium and an electronic device, which are used for solving the problem of how to know the simulation effect after nail beautifying in advance before nail beautifying.
According to a first aspect of the present application, there is provided a method of color processing of a nail image, comprising: acquiring a first hand image containing a nail; determining a nail region in the first hand image; carrying out image color processing on the nail area to obtain a second hand image; and outputting/displaying the second hand image.
In some embodiments, said determining a nail region in said first hand image comprises: locating a nail in the first hand image in real time; a nail region of the nail in the first hand image is identified.
In some embodiments, the steps of locating a nail in the first hand image in real time and identifying a nail region of the nail in the first hand image are performed sequentially by inputting the first hand image into a pre-trained neural network.
In some embodiments, said subjecting said nail region to image color processing to obtain a second hand image comprises: acquiring a nail art sticker selected by a user; changing the shape of the nail sticker to obtain a sticker to be pasted, wherein the nail sticker can be pasted on the nail area; and fusing the to-be-pasted sticker with the nail area to obtain a second hand image.
In some embodiments, said fusing said sticker to be affixed with said nail region resulting in a second hand image comprises: acquiring image parameters of the to-be-pasted sticker and image parameters of the nail area; substituting the image parameters of the to-be-pasted paper and the image parameters of the nail area into an image fusion calculation formula to obtain fused image parameters; and generating the second hand image according to the fused image parameters.
In some embodiments, the nail sticker includes, but is not limited to, a color, a pattern, or a combination of a color and a pattern.
In some embodiments, the step of transforming the shape of the nail sticker to obtain a sticker to be attached enabling the nail sticker to be attached on the nail region is performed by one or more of the following transformation models: a rigid transformation model, an affine transformation model, a perspective transformation model and a non-linear transformation model.
According to a second aspect of the present application, there is provided a nail image color processing apparatus comprising: the image acquisition module is used for acquiring a first hand image containing a nail; a nail localization module to determine a nail region in the first hand image; the nail drawing and coloring module is used for carrying out drawing and coloring treatment on the nail area to obtain a second hand image; and the image display module is used for outputting/displaying the second hand image.
In some embodiments, the nail positioning module comprises: a real-time positioning unit for positioning the nail in the first hand image in real time; a nail region identification unit configured to identify a nail region of the nail in the first hand image.
In some embodiments, the nail localization module is a pre-trained neural network for inputting the first hand image into the pre-trained neural network to localize the nail in the first hand image and identify a nail region of the nail in the first hand image in real time.
In some embodiments, the nail map coloring module comprises: the sticker acquiring unit is used for acquiring nail art stickers selected by a user; the sticker converting unit is used for converting the shape of the nail sticker to obtain a sticker to be pasted, which can enable the nail sticker to be pasted on the nail area; and the sticker fusing unit is used for fusing the to-be-pasted sticker with the nail region to obtain a second hand image.
According to a third aspect of the present application, there is provided a storage medium, wherein the storage medium stores a computer program, which when executed performs the method of any of the above first aspects.
According to a fourth aspect of the present application, there is provided an electronic device comprising: at least one processor; at least one memory storing a computer program; the processor is configured to execute the computer program in the memory, and the computer program executes the method according to any one of the first aspect.
The method for processing the picture color of the nail image can be used for detecting the nail area in real time and coloring the nail according to the color or the pattern specified by the user, and has the advantages of small model, high speed, real-time detection and coloring, and different nail beautifying experience for the user.
Drawings
Fig. 1 is a flowchart of an implementation of a method for processing color of a nail image according to some embodiments of the present disclosure.
Fig. 2 is a flowchart illustrating an implementation of step S12 in a method for processing color images of nail images according to some embodiments of the present application.
FIG. 3 is a diagram of a model training architecture for a neural network used to locate nail regions as provided in the present example.
Fig. 4 is a flowchart of an implementation of the above step S13 provided in some embodiments of the present application.
Fig. 5 is a flowchart illustrating an implementation of the step S43 provided in an embodiment of the present application.
Fig. 6 is a schematic structural diagram of a color processing apparatus for nail images according to an embodiment of the present disclosure.
FIG. 7 is a schematic structural view of an embodiment of a nail positioning module in the image color processing apparatus for nail images shown in FIG. 6.
FIG. 8 is a schematic structural view of an embodiment of a nail color module in the color processing apparatus for nail images shown in FIG. 6.
Fig. 9 is a schematic configuration diagram of an embodiment of a sticker fusion unit in the image color processing apparatus for nail images shown in fig. 6.
Fig. 10 is a schematic structural diagram of an electronic device provided in the present application.
Fig. 11 is a schematic structural diagram of an electronic device provided in the present application.
Detailed Description
Example 1
Fig. 1 is a flowchart of an implementation of a method for processing color of a nail image according to some embodiments of the present disclosure.
As shown in fig. 1, the method for processing the color of the nail image includes the steps of:
s11, acquiring a first hand image containing a nail;
s12, determining a nail region in the first hand image;
s13, performing image color processing on the nail area to obtain a second hand image;
and S14, outputting and displaying the second hand image.
In step S11, the first hand image may be a single frame image, a sequence of images, or a video captured at one end. For example, the first hand image may be a sequence of images or a real-time video of images captured by a camera of a mobile phone in real time, or may be an image selected from a local gallery or a file.
In step S12, it is necessary to identify an image region including a nail in the acquired first hand image so as to find a target region of a color.
For example, fig. 2 is a flowchart illustrating the implementation of step S12 in a method for processing color of a nail image according to some embodiments of the present application.
As shown in fig. 2, the determining the nail region in the first hand image specifically includes the following steps:
s21, positioning the fingernails in the first hand image in real time;
s22, recognizing the nail area of the nail in the first hand image.
In the above step S21, the positioning is to obtain the position of the nail included in the image, for example, in a real-time captured video image, the first hand image is changed in real time, so it is important how to quickly position the nail at this time, and if the nail is positioned inaccurately or delayed, the color effect of the image is not consistent.
In step S22, after the nail in the first hand image is located, it is necessary to recognize the image and obtain a nail region.
In some embodiments, the above steps S21 and S22 may be sequentially performed by inputting the first hand image into a pre-trained neural network.
For example, fig. 3 is a diagram of a model training architecture for a neural network for locating nail regions as provided in this example.
As shown in fig. 3, the training process of the neural network is as follows:
s31, marking a training sample, collecting various images of fingers and hand backs including complete nails, manually marking nail areas, marking the nail areas as 1, and marking the other areas as 0 to obtain a training mask image;
s32, randomly dividing the training data into a training set and a test set;
s33, performing sample augmentation, such as rotation, scaling, color transformation and the like, on the training data;
and S34, sending the training data into the neural network training model.
In the neural network training model shown in fig. 3, Image represents an input Image, a Conv layer represents extracted Image features, Max pool represents a reduced Image, the amount of calculation is reduced, bottleeck represents extracted Image features, upSample represents to be used for up-sampling, a small Image is enlarged, add represents to be used for fusing features of different layers, so that not only low-layer texture and color features but also high-layer semantic features exist.
Specifically, the neural network training model extracts features through a convolutional layer, and then a batchnorm layer is used for feature normalization; the relu layer is used for feature truncation, so that a value less than 0 is 0; the pool layer is used for reducing the characteristic diagram and reducing the calculation amount; upsamplample is used for upsampling, which can be realized by interpolation, and is used for amplifying the small image; the add is used for fusing features of different layers, and the add can be specifically element-wise add.
In addition, the loss function in the neural network training model is cross entropy, and the formula is as follows:
wherein T represents the number of categories, here 2 (i.e., including belonging to the nail region and not belonging to the nail region), yjThe true value of the point is shown, namely whether the pixel point on the image belongs to the nail region is 1 or not, and S is SjIndicating the predicted value of the point.
In the implementation, the neural network model is formed by a training part and a testing part, wherein training data is collected in the training part, a model capable of positioning the fingernails is trained, and the training part can be completed on a server; and the testing part is used for testing the real-time positioning fingernails, and the testing part can be realized in an intelligent terminal.
It should be understood that the training of the neural network is a routine technique for those skilled in the art, and the present embodiment provides key parameters and model architecture for training the neural network for different applications, such as the above-mentioned localization of the nail region, as the training of the neural network of the present embodiment is sufficiently clear and complete for those skilled in the art to implement the present embodiment. In addition, the nail positioning is not limited to be realized by the neural network model, and those skilled in the art can also realize other training models, such as machine learning and deep learning. And will not be described in detail herein.
In step S13, a second hand image after nail-painting is obtained by performing a color mapping process on the recognized nail region.
Fig. 4 is a flowchart of an implementation of the above step S13 provided in some embodiments of the present application.
As shown in fig. 4, in some embodiments, the color processing on the nail region to obtain the second hand image may specifically include the following steps:
s41, acquiring nail stickers selected by the user;
s42, transforming the shape of the nail sticker to obtain a sticker to be pasted, wherein the sticker can be pasted on the nail area;
and S43, fusing the to-be-pasted paper and the nail area to obtain a second hand image.
In step S41, the user can select his/her favorite nail sticker, which can be a color, a pattern, or a combination of colors and patterns made according to various nail products.
In step S42, since the nail region in the first hand image has a different shape, the nail sticker cannot be directly attached to the nail region, and it is necessary to deform the nail sticker so that the shape of the nail sticker can be matched or matched with the nail region.
Specifically, the shape transformation of the nail sticker may be implemented by one or more of the following transformation models: a rigid transformation model, an affine transformation model, a perspective transformation model and a non-linear transformation model.
In step S43, the sticker to be attached is fused with the nail region, that is, the sticker to be attached is covered on the nail region, so as to obtain a simulated effect diagram after nail beautifying.
Fig. 5 is a flowchart illustrating implementation of the step S43 provided in an embodiment of the present application.
As shown in fig. 5, the step of fusing the sticker to be pasted with the nail region to obtain the second hand image may include:
s51, acquiring the image parameters of the to-be-pasted paper and the image parameters of the nail area;
s52, substituting the image parameters of the to-be-pasted paper and the image parameters of the nail area into an image fusion calculation formula to obtain fused image parameters;
and S53, generating the second hand image according to the fused image parameters.
For example, assuming that the image parameter of the sticker to be pasted is S and the image parameter of the nail region is T, S and T can be fused together by the following formula:
result＝S*alpha+T*(1.0-alpha)；
wherein S represents the paster after affine transformation, T represents the image corresponding to the nail region on the original drawing, alpha is an empirical value, and alpha is within the scope of [0, 1 ]. In general, alpha may be 0.6-0.8. In some embodiments, the user may also custom adjust the alpha value. The sticker S after affine transformation can be completely attached to the nail region T by the above method.
The image color processing method of the nail image provided by the embodiment can be used for detecting the nail area in real time and coloring the nail according to the color or the pattern specified by the user, and has the advantages of small model, high speed, real-time detection and coloring, and different nail beautifying experience for the user.
Example 2
The present example also provides a picture color processing apparatus of nail images based on the same inventive concept of the method in embodiment 1.
Fig. 6 is a schematic structural diagram of a color processing apparatus for nail images according to an embodiment of the present disclosure.
As shown in fig. 6, the nail image color processing apparatus 6 includes: an image acquisition module 61 for acquiring a first hand image containing a nail; a nail positioning module 62 for determining a nail region in the first hand image; a nail drawing color module 63, configured to perform drawing color processing on the nail region to obtain a second hand image; and an image display module 64, configured to output/display the second hand image.
FIG. 7 is a schematic structural view of an embodiment of a nail positioning module 62 in the image color processing apparatus for nail images shown in FIG. 6.
Referring to fig. 7, the nail positioning module 62 includes: a real-time positioning unit 71 for positioning the nail in the first hand image in real time; a nail region recognition unit 72 for recognizing a nail region of the nail in the first hand image.
Specifically, the nail positioning module is a pre-trained neural network, and is configured to input the first hand image into the pre-trained neural network to position the nail in the first hand image in real time and identify a nail region of the nail in the first hand image.
FIG. 8 is a schematic structural view of an embodiment of a nail color module 63 in the color processing apparatus for nail images shown in FIG. 6.
Referring to fig. 8, the nail drawing module 63 includes: a sticker acquiring unit 81 for acquiring a nail sticker selected by a user; a sticker converting unit 82 for converting the shape of the nail sticker to obtain a sticker to be attached, which enables the nail sticker to be attached to the nail region; and the sticker fusing unit 83 is used for fusing the to-be-pasted sticker with the nail region to obtain a second hand image.
Fig. 9 is a schematic configuration diagram of an embodiment of a sticker fusion unit in the image color processing apparatus for nail images shown in fig. 6.
Referring to fig. 9, the sticker fusion unit 83 includes: an image parameter acquiring unit 91 configured to acquire an image parameter of the to-be-pasted paper and an image parameter of the nail region; the image fusion calculation unit 92 is used for substituting the image parameters of the to-be-pasted paper and the image parameters of the nail region into an image fusion calculation formula to obtain fused image parameters; a fused image generating unit 93, configured to generate the second hand image according to the fused image parameters.
Example 3
The present example also provides an electronic device and a storage medium based on the same inventive concept of the method in embodiment 1.
Fig. 10 is a schematic structural diagram of an electronic device provided in the present application.
As shown in fig. 10, the electronic device 10 includes: at least one processor 101; at least one memory storing a computer program; the processor is configured to execute the computer program 103 in the memory 102, and the computer program 103 executes the method in any of the embodiments of embodiment 1.
In some embodiments, the electronic device may further include a display screen coupled to the processor.
In some embodiments, the illustrated electronic device 10 may be a smart electronic device terminal, such as a smartphone, tablet, computer, or the like, or may be a server.
Fig. 11 is a schematic structural diagram of a storage medium provided in the present application.
As shown in fig. 11, the storage medium 11 stores a computer program 103, and the computer program 103 executes the method in any one of the embodiments of embodiment 1 when running.
Claims (10)
1. A method for processing color of a nail image, comprising:
acquiring a first hand image containing a nail;
determining a nail region in the first hand image;
carrying out image color processing on the nail area to obtain a second hand image;
and outputting/displaying the second hand image.
2. The method for processing a nail image according to claim 1, wherein the determining a nail region in the first hand image comprises:
locating a nail in the first hand image in real time;
a nail region of the nail in the first hand image is identified.
3. The method for processing color chart of nail images according to claim 2, wherein the steps of locating the nail in the first hand image in real time and recognizing the nail region of the nail in the first hand image are sequentially performed by inputting the first hand image into a neural network trained in advance.
4. The method for processing color of a nail image according to claim 1, wherein the processing of the color of the nail region to obtain a second hand image comprises:
acquiring a nail art sticker selected by a user;
changing the shape of the nail sticker to obtain a sticker to be pasted, wherein the nail sticker can be pasted on the nail area;
and fusing the to-be-pasted sticker with the nail area to obtain a second hand image.
5. The method for processing color of a nail image according to claim 4, wherein the fusing the sticker to be attached to the nail region to obtain a second hand image comprises:
acquiring image parameters of the to-be-pasted sticker and image parameters of the nail area;
substituting the image parameters of the to-be-pasted paper and the image parameters of the nail area into an image fusion calculation formula to obtain fused image parameters;
and generating the second hand image according to the fused image parameters.
6. The method for color-processing a nail image according to claim 4, wherein the nail sticker includes, but is not limited to, a color, a pattern, or a combination of a color and a pattern.
7. The method for processing color of a nail image according to claim 4, wherein the step of transforming the shape of the nail sticker to obtain a sticker to be attached so that the nail sticker can be attached to the nail region is performed by one or more of the following transformation models: a rigid transformation model, an affine transformation model, a perspective transformation model and a non-linear transformation model.
8. A nail image color processing apparatus comprising:
the image acquisition module is used for acquiring a first hand image containing a nail;
a nail localization module to determine a nail region in the first hand image;
the nail drawing and coloring module is used for carrying out drawing and coloring treatment on the nail area to obtain a second hand image;
and the image display module is used for outputting/displaying the second hand image.
9. A storage medium, characterized in that the storage medium stores a computer program which executes the method for processing the color of a nail image according to any one of claims 1 to 7.
10. An electronic device, comprising:
at least one processor;
at least one memory storing a computer program;
the processor is configured to run a computer program stored in the memory, and the computer program is configured to execute the method for processing the nail image according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911223438.5A CN111047632A (en) | 2019-12-03 | 2019-12-03 | Method and device for processing picture color of nail image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911223438.5A CN111047632A (en) | 2019-12-03 | 2019-12-03 | Method and device for processing picture color of nail image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111047632A true CN111047632A (en) | 2020-04-21 |
Family
ID=70234538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911223438.5A Pending CN111047632A (en) | 2019-12-03 | 2019-12-03 | Method and device for processing picture color of nail image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111047632A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739028A (en) * | 2020-05-26 | 2020-10-02 | 华南理工大学 | Nail region image acquisition method, system, computing device and storage medium |
| CN113705529A (en) * | 2021-09-08 | 2021-11-26 | 口碑(上海)信息技术有限公司 | Image processing method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102555525A (en) * | 2010-10-28 | 2012-07-11 | 卡西欧计算机株式会社 | Nail print apparatus and print control method |
| CN103660610A (en) * | 2012-08-31 | 2014-03-26 | 卡西欧计算机株式会社 | Nail print apparatus and print control method thereof |
| CN109376575A (en) * | 2018-08-20 | 2019-02-22 | 奇酷互联网络科技（深圳）有限公司 | Method, mobile terminal and the storage medium that human body in image is beautified |
| CN110136092A (en) * | 2019-05-21 | 2019-08-16 | 北京三快在线科技有限公司 | Image processing method, device and storage medium |
-
2019
- 2019-12-03 CN CN201911223438.5A patent/CN111047632A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102555525A (en) * | 2010-10-28 | 2012-07-11 | 卡西欧计算机株式会社 | Nail print apparatus and print control method |
| CN103660610A (en) * | 2012-08-31 | 2014-03-26 | 卡西欧计算机株式会社 | Nail print apparatus and print control method thereof |
| CN109376575A (en) * | 2018-08-20 | 2019-02-22 | 奇酷互联网络科技（深圳）有限公司 | Method, mobile terminal and the storage medium that human body in image is beautified |
| CN110136092A (en) * | 2019-05-21 | 2019-08-16 | 北京三快在线科技有限公司 | Image processing method, device and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739028A (en) * | 2020-05-26 | 2020-10-02 | 华南理工大学 | Nail region image acquisition method, system, computing device and storage medium |
| CN113705529A (en) * | 2021-09-08 | 2021-11-26 | 口碑(上海)信息技术有限公司 | Image processing method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9349076B1 (en) | Template-based target object detection in an image | |
| CN107798653B (en) | Image processing method and device | |
| CN109583483B (en) | Target detection method and system based on convolutional neural network | |
| CN112052186B (en) | Target detection method, device, equipment and storage medium | |
| CN110659582A (en) | Image conversion model training method, heterogeneous face recognition method, device and equipment | |
| CN110427859A (en) | A kind of method for detecting human face, device, electronic equipment and storage medium | |
| KR101955919B1 (en) | Method and program for providing tht region-of-interest in image by deep-learing algorithm | |
| CN110097616B (en) | Combined drawing method and device, terminal equipment and readable storage medium | |
| CN109409199B (en) | Micro-expression training method and device, storage medium and electronic equipment | |
| CN112561973A (en) | Method and device for training image registration model and electronic equipment | |
| CN109670517A (en) | Object detection method, device, electronic equipment and target detection model | |
| CN109816694A (en) | Method for tracking target, device and electronic equipment | |
| CN111047632A (en) | Method and device for processing picture color of nail image | |
| CN113160231A (en) | Sample generation method, sample generation device and electronic equipment | |
| CN115482322A (en) | Computer-implemented method and system for generating a synthetic training data set | |
| CN116452745A (en) | Hand modeling, hand model processing method, device and medium | |
| CN114373050A (en) | Chemistry experiment teaching system and method based on HoloLens | |
| CN115008454A (en) | Robot online hand-eye calibration method based on multi-frame pseudo label data enhancement | |
| CN115100469A (en) | Target attribute identification method, training method and device based on segmentation algorithm | |
| CN117911827A (en) | Multi-mode target detection method, device, equipment and storage medium | |
| JP6699048B2 (en) | Feature selecting device, tag related area extracting device, method, and program | |
| CN112287790A (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN112860060B (en) | Image recognition method, device and storage medium | |
| CN113034420B (en) | Industrial product surface defect segmentation method and system based on frequency space domain characteristics | |
| CN109840948A (en) | The put-on method and device of target object based on augmented reality |
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: 20200421 |