CN113793406A - Portrait business card generating method and device, electronic equipment and storage medium - Google Patents
Portrait business card generating method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113793406A CN113793406A CN202111087077.3A CN202111087077A CN113793406A CN 113793406 A CN113793406 A CN 113793406A CN 202111087077 A CN202111087077 A CN 202111087077A CN 113793406 A CN113793406 A CN 113793406A
- Authority
- CN
- China
- Prior art keywords
- portrait
- picture
- business card
- area
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000007781 pre-processing Methods 0.000 claims abstract description 28
- 238000001514 detection method Methods 0.000 claims description 47
- 230000006870 function Effects 0.000 claims description 33
- 230000011218 segmentation Effects 0.000 claims description 23
- 230000004913 activation Effects 0.000 claims description 22
- 238000011176 pooling Methods 0.000 claims description 22
- 238000010606 normalization Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 238000003709 image segmentation Methods 0.000 claims description 15
- 230000009467 reduction Effects 0.000 claims description 14
- 238000009499 grossing Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000007726 management method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- 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
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Editing Of Facsimile Originals (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a portrait business card generation method, which comprises the following steps: preprocessing a user picture to be identified to obtain a standard picture; detecting the standard picture by using a pre-constructed portrait matting model to obtain a portrait picture; segmenting the portrait picture by utilizing the portrait matting model to obtain a portrait region; judging whether a picture frame exists in the acquired photo area in the business card template; if the photo area has a picture frame, the portrait area is arranged in the picture frame, and the business card information is arranged on the business card template to obtain a first portrait business card; and if the photo area has no picture frame, the portrait area is distributed in the photo area, and the business card information is distributed in the business card template to obtain a second portrait business card. The invention also relates to a block chain technology, and the portrait business cards can be stored in the block chain nodes. The invention also provides a portrait business card generating device, electronic equipment and a medium. The invention can improve the efficiency of generating the portrait business card.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a portrait business card generation method and device, electronic equipment and a storage medium.
Background
At present, in the process of making portrait business cards, a user generally selects a business card template first, and then performs matting and photo adjustment processing on a template photo to obtain the portrait business card.
However, in general, a user needs to find a position for placing a photo in a business card template, and the photo size provided by the business card template is different from the photo size of the user, so that the user often needs to stretch the photo when adjusting the photo size, which causes the photo to deform and damages the image of the user, and this process involves a large amount of manual operations, which results in low efficiency of generating a portrait business card.
Disclosure of Invention
The invention provides a portrait business card generation method, a portrait business card generation device, electronic equipment and a computer medium, and mainly aims to improve the efficiency of portrait business card generation.
In order to achieve the above object, the invention provides a portrait business card generating method, which comprises:
acquiring a user picture to be identified, and preprocessing the user picture to be identified to obtain a standard picture;
inputting the standard picture into a pre-constructed image matting model, detecting the standard picture by using an image detection network in the image matting model to obtain an image picture, and then segmenting the image picture by using an image segmentation network in the image matting model to obtain an image area, wherein the image matting model comprises end-to-end connection of an image detection network and an image segmentation network;
acquiring a business card template and business card information, and judging whether a picture frame exists in a picture area in the business card template;
if the photo area in the business card template has a picture frame, the portrait area is arranged in the picture frame, and the business card information is arranged on the business card template to obtain a first portrait business card;
and if the photo area in the business card template has no picture frame, the portrait area is distributed in the photo area, and the business card information is distributed in the business card template to obtain a second portrait business card.
Optionally, the detecting the standard picture by using the portrait detecting network in the portrait matting model to obtain a portrait picture includes:
performing feature extraction on the standard picture by using the convolution layer in the portrait detection network to obtain a feature picture;
performing dimensionality reduction operation on the feature picture by using a pooling layer in the portrait detection network to obtain a dimensionality reduction picture;
fully connecting the dimensionality reduction pictures by using a full connection layer in the portrait detection network to obtain a spliced portrait picture;
and outputting the spliced portrait picture by using an activation function in the portrait detection network to obtain the portrait picture.
Optionally, the segmenting the portrait picture by using the portrait segmentation network in the portrait matting model to obtain a portrait region includes:
extracting the characteristics of the portrait picture by using the cavity convolution layer in the portrait segmentation network and carrying out characteristic fusion to obtain a fused portrait picture;
carrying out portrait segmentation on the fused portrait picture by utilizing a pyramid pooling layer in the portrait segmentation network to obtain a segmented portrait picture;
and inputting the segmented portrait picture into an activation function in the portrait segmentation network to obtain a portrait area output by the activation function.
Optionally, if a picture frame exists in the photo area in the business card template, the portrait area is laid out in the picture frame, including:
if a picture frame exists in the picture area in the business card template, obtaining the picture frame height, the picture frame width and the picture frame center line of the picture frame;
and carrying out zooming operation on the portrait area according to the picture frame height, the picture frame width and the picture frame center line, so that the portrait area height is consistent with the picture frame height, the portrait area width is consistent with the picture frame width, the area center line is consistent with the picture frame center line, and the portrait area is distributed in the picture frame.
Optionally, if the photo area in the business card template has no frame, laying the portrait area in the photo area, including:
if the photo area in the name card template has no picture frame, acquiring a top edge value coordinate and a bottom edge value coordinate of the photo area;
and after the top edge value coordinates are aligned with the top edge of the portrait area and the top edge of the photo area, calculating the scaling ratio of the portrait area, and calculating the bottom edge value of the portrait area according to the scaling ratio and the bottom edge value, so that the portrait area is laid out in the photo area.
Optionally, the preprocessing the picture of the user to be identified to obtain a standard picture includes:
carrying out digital processing on the user picture to be identified to obtain a digital picture;
performing histogram equalization operation on the digital picture to obtain an equalized picture;
carrying out sharpening smoothing operation on the balanced picture to obtain an enhanced picture;
and carrying out normalization operation on the enhanced picture to obtain a standard picture.
Optionally, the normalizing the enhanced picture to obtain a standard picture includes:
and carrying out geometric normalization and gray level normalization operation on the standard picture to obtain the standard picture.
In order to solve the above problem, the present invention further provides a portrait business card generation apparatus, comprising:
the system comprises a preprocessing operation module, a standard image acquisition module and a recognition module, wherein the preprocessing operation module is used for acquiring a user image to be recognized and carrying out preprocessing operation on the user image to be recognized to obtain the standard image;
the model matting module is used for inputting the standard picture into a pre-constructed image matting model, detecting the standard picture by utilizing an image detection network in the image matting model to obtain an image picture, and then segmenting the image picture by utilizing an image segmentation network in the image matting model to obtain an image region, wherein the image matting model comprises end-to-end connection of the image detection network and the image segmentation network;
the picture frame judging module is used for acquiring a business card template and business card information and judging whether a picture frame exists in a photo area in the business card template;
the first portrait business card generating module is used for laying the portrait area in the picture frame and laying the business card information on the business card template to obtain a first portrait business card if the photo area in the business card template has the picture frame;
and the second portrait business card generation module is used for laying out the portrait area in the photo area if no picture frame exists in the photo area in the business card template, and laying out the business card information in the business card template to obtain a second portrait business card.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one computer program; and
and the processor executes the computer program stored in the memory to realize the portrait business card generation method.
In order to solve the above problem, the present invention further provides a computer medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the portrait business card generation method described above.
In the embodiment of the invention, firstly, the standard picture is obtained by preprocessing the picture of the user to be identified, and after the preprocessing operation is carried out, the details in the standard picture can be more prominent, the picture is clearer and the picture quality is higher; secondly, detecting the characteristics of the standard picture by using a portrait detection network in a pre-constructed portrait matting model, and cutting the detected portrait to obtain a portrait picture; further, the portrait picture is divided by utilizing a portrait division network in the portrait matting model, and the detected portrait picture is divided, so that portrait matting is realized, and a portrait area is obtained; and finally, according to the name card template, the name card information input by the user and the portrait area are arranged in the photo area in the name card template, so that the portrait name card is obtained, user adjustment is not needed, and the generation efficiency of the portrait name card is improved. Therefore, the portrait business card generation method, the portrait business card generation device, the electronic equipment and the storage medium provided by the embodiment of the invention can improve the efficiency of portrait business card generation.
Drawings
Fig. 1 is a schematic flow chart of a portrait card generation method according to an embodiment of the present invention;
FIG. 2 is a schematic block diagram of a portrait card creation apparatus according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an internal structure of an electronic device implementing a portrait business card generation method according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention provides a portrait business card generation method. The execution subject of the portrait business card generation method includes, but is not limited to, at least one of the electronic devices of the server, the terminal, and the like, which can be configured to execute the method provided by the embodiment of the present application. In other words, the portrait business card generation method may be executed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Referring to fig. 1, which is a schematic flow chart of a portrait business card generation method according to an embodiment of the present invention, in an embodiment of the present invention, the portrait business card generation method includes:
and S1, acquiring a user picture to be identified, and preprocessing the user picture to be identified to obtain a standard picture.
In the embodiment of the invention, the picture of the user to be identified is the picture to be identified containing the portrait picture of the user. For example, the picture of the user to be identified is a certificate photo or a picture including a portrait taken by the user, and the picture of the user to be identified can be obtained from a picture uploaded by the user.
In the embodiment of the invention, the image is preprocessed, so that the defects of insufficient gray scale, noise point, contrast and the like caused by different acquisition environments (such as illumination brightness, equipment performance and the like) and the problems of uncertain size and position of the portrait in the whole image caused by the difference of distance and focal length can be avoided, and the consistency of the size and the position of the portrait in the portrait image and the quality of the portrait image can be improved by preprocessing the image.
In detail, the preprocessing the picture of the user to be identified to obtain a standard picture includes:
carrying out digital processing on the user picture to be identified to obtain a digital picture;
performing histogram equalization operation on the digital picture to obtain an equalized picture;
carrying out sharpening smoothing operation on the balanced picture to obtain an enhanced picture;
and carrying out normalization operation on the enhanced picture to obtain a standard picture.
In the embodiment of the invention, the digital processing is to perform gray sampling and quantization on the user picture to be identified on an M x N dot matrix to obtain a digital picture which can be processed by a computer.
In an embodiment of the present invention, performing the histogram equalization operation can convert the digital picture into an equalized picture having the same pixel point at each gray level.
In an optional embodiment of the present invention, the contour information in the picture can be enhanced by performing a sharpening operation on the equalized picture by using a LoG operator, so that details of the picture are highlighted, but noise of the sharpened picture is enhanced, and therefore, the smoothing process is further performed, so that the noise of the picture is eliminated, and the contour or lines of the picture are not blurred.
Preferably, the smoothing process may be performed by a median method.
In the embodiment of the present invention, the purpose of normalizing the enhanced pictures is to make pictures taken under different conditions (such as illumination intensity, direction, distance, posture, and the like) consistent.
Further, the normalizing the enhanced picture to obtain a standard picture includes:
and carrying out geometric normalization and gray level normalization operation on the standard picture to obtain the standard picture.
In an embodiment of the invention, the geometric normalization is helpful for correcting size difference and angle inclination caused by imaging distance change and portrait posture change in the picture, and the gray scale normalization is helpful for compensating the portrait in the picture obtained under different light intensities and light source directions.
S2, inputting the standard picture to a pre-constructed image matting model, detecting the standard picture by using an image detection network in the image matting model to obtain an image picture, and then segmenting the image picture by using an image segmentation network in the image matting model to obtain an image region, wherein the image matting model comprises end-to-end connection of an image detection network and an image segmentation network.
In the embodiment of the invention, the standard picture is input into a pre-constructed portrait matting model, so that a portrait background which divides the background and the portrait can be obtained, wherein the portrait matting model comprises end-to-end connection of a portrait detection network and a portrait division network.
In the embodiment of the invention, the portrait picture is a picture obtained by cutting out the portrait after the portrait is detected by the portrait detection network. The method comprises the following steps of utilizing a portrait detection network in a pre-constructed portrait matting model to detect a standard picture so as to detect a portrait outline and obtain a detected portrait picture, wherein the portrait detection network comprises: convolutional layers, pooling layers, full-link layers, and activation functions.
In detail, the detecting the standard picture by using the portrait detecting network in the portrait matting model to obtain a portrait picture includes:
performing feature extraction on the standard picture by using the convolution layer in the portrait detection network to obtain a feature picture;
performing dimensionality reduction operation on the feature picture by using a pooling layer in the portrait detection network to obtain a dimensionality reduction picture;
fully connecting the dimensionality reduction pictures by using a full connection layer in the portrait detection network to obtain a spliced portrait picture;
and outputting the spliced portrait picture by using an activation function in the portrait detection network to obtain the portrait picture.
In the embodiment of the invention, the feature extraction is a feature picture obtained by calculating the pixel matrix of the standard picture.
In an embodiment of the present invention, performing pooling operation on the standard picture by using the pooling layer is to perform average region division on the feature picture, and replace a pixel value in the region with an average value of a sum of all pixel values in the region, so that the feature extracted from the feature picture is not lost and dimension reduction operation is performed.
Preferably, the activation function may be a ReLU function, and the stitched portrait picture may be activated to obtain the finally detected portrait picture including the portrait feature information.
In the embodiment of the present invention, a detected portrait image is segmented by using a segmentation network in the portrait matting model, so as to implement portrait matting and obtain a portrait region, wherein the portrait segmentation network includes: a hole convolution layer, a pyramid pooling layer, and an activation function.
Further, the segmenting the portrait picture by using the portrait segmentation network in the portrait matting model to obtain a portrait region includes:
extracting the characteristics of the portrait picture by using the cavity convolution layer in the portrait segmentation network and carrying out characteristic fusion to obtain a fused portrait picture;
carrying out portrait segmentation on the fused portrait picture by utilizing a pyramid pooling layer in the portrait segmentation network to obtain a segmented portrait picture;
and inputting the segmented portrait picture into an activation function in the portrait segmentation network to obtain a portrait area output by the activation function.
In the embodiment of the invention, the hole convolution layer has more special holes than a common convolution layer, and the visual field is wider, so that the global information of more pictures can be mastered through feature fusion under the condition that the feature pictures are reduced by the same times.
In an embodiment of the present invention, the pyramid pooling layer replaces a general pooling layer, so that no matter what the size of the picture input into the portrait splitting network is, the split pictures with the same picture size can be output.
Preferably, the activation function may be a Sigmoid function, and the segmented portrait picture may be activated to obtain a portrait area with a background separated from the portrait.
S3, obtaining the name card template and the name card information, and judging whether a picture frame exists in the picture area in the name card template.
In the embodiment of the invention, the business card template mainly comprises a photo area and a business card information area.
In this embodiment, the business card template may be obtained from a preset business card template library. The name card information refers to self-introduction information of the user, including name, telephone, company, position, company address, etc. the name card information may be information input to the website by the user or directly obtained from the enterprise website.
In the embodiment of the invention, whether a picture frame exists in the picture area in the name card template can be judged by using a boosting Edge Learning algorithm (Boosted Edge Learning Bel).
S4, if a picture frame exists in the photo area in the business card template, the portrait area is arranged in the picture frame, and the business card information is arranged on the business card template to obtain a first portrait business card.
In detail, if there is a picture frame in the photo area in the business card template, the step of laying out the portrait area in the picture frame includes:
if a picture frame exists in the picture area in the business card template, obtaining the picture frame height, the picture frame width and the picture frame center line of the picture frame;
and carrying out zooming operation on the portrait area according to the picture frame height, the picture frame width and the picture frame center line, so that the portrait area height is consistent with the picture frame height, the portrait area width is consistent with the picture frame width, the area center line is consistent with the picture frame center line, and the portrait area is distributed in the picture frame.
In an embodiment of the present invention, the height of the portrait area after scaling is consistent with the frame height, a scaling ratio, which is a frame height box _ h/portrait area height for _ h, is obtained, the width of the portrait area and the width of the frame are calculated by using the scaling ratio, and then the central line of the scaled portrait area is aligned with the central line of the frame, so that the portrait area is centered in the frame.
In the embodiment of the invention, the first portrait business card refers to a business card with a picture frame in a photo area.
In the embodiment of the invention, the business card information can be distributed on the business card template according to the business card template, if the business card information is too long, the line is changed according to the preset specified line number, and the first portrait business card is generated by distributing the portrait area in the picture frame.
S5, if the photo area in the business card template has no picture frame, the portrait area is arranged in the photo area, and the business card information is arranged in the business card template to obtain a second portrait business card.
In the embodiment of the invention, in order to ensure that the portrait area is distributed in the business card template without visual 'abrupt' or 'suspension' feeling, the business card template without a picture frame in the photo area can be selected.
In detail, if the photo area in the business card template has no frame, the step of laying out the portrait area in the photo area includes:
if the photo area in the name card template has no picture frame, acquiring a top edge value coordinate and a bottom edge value coordinate of the photo area;
and after the top edge value coordinates are aligned with the top edge of the portrait area and the top edge of the photo area, calculating the scaling ratio of the portrait area, and calculating the bottom edge value of the portrait area according to the scaling ratio and the bottom edge value, so that the portrait area is laid out in the photo area.
In the embodiment of the present invention, a cascading style sheet technique may be used to calculate a scaling ratio of the portrait area, and the portrait area is scaled according to the scaling ratio to obtain the portrait area aligned with the top edge and the bottom edge of the photo area.
In the embodiment of the invention, the second portrait business card refers to a business card without a picture frame in the photo area of the business card template.
In the embodiment of the invention, the business card information can be distributed on the business card template according to the business card template, if the business card information is too long, the line is changed according to the preset specified line number, and a second portrait business card is generated in the photo area according to the portrait area distribution.
In the embodiment of the invention, firstly, the standard picture is obtained by preprocessing the picture of the user to be identified, and after the preprocessing operation is carried out, the details in the standard picture can be more prominent, the picture is clearer and the picture quality is higher; secondly, detecting the characteristics of the standard picture by using a portrait detection network in a pre-constructed portrait matting model, and cutting the detected portrait to obtain a portrait picture; further, the portrait picture is divided by utilizing a portrait division network in the portrait matting model, and the detected portrait picture is divided, so that portrait matting is realized, and a portrait area is obtained; and finally, according to the name card template, the name card information input by the user and the portrait area are arranged in the photo area in the name card template, so that the portrait name card is obtained, user adjustment is not needed, and the generation efficiency of the portrait name card is improved. Therefore, the portrait business card generation method provided by the embodiment of the invention can improve the efficiency of portrait business card generation.
Fig. 2 is a functional block diagram of the portrait card creation apparatus of the present invention.
The portrait business card creation apparatus 100 of the present invention may be installed in an electronic device. According to the implemented functions, the portrait business card generation device may include a preprocessing operation module 101, a model matting module 102, a picture frame judgment module 103, a first portrait business card generation module 104, and a second portrait business card generation module 105, which may also be referred to as a unit, and refers to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the preprocessing operation module 101 is configured to acquire a user picture to be identified, and perform preprocessing operation on the user picture to be identified to obtain a standard picture.
In the embodiment of the invention, the picture of the user to be identified is the picture to be identified containing the portrait picture of the user. For example, the picture of the user to be identified is a certificate photo or a picture including a portrait taken by the user, and the picture of the user to be identified can be obtained from a picture uploaded by the user.
In the embodiment of the invention, the image is preprocessed, so that the defects of insufficient gray scale, noise point, contrast and the like caused by different acquisition environments (such as illumination brightness, equipment performance and the like) and the problems of uncertain size and position of the portrait in the whole image caused by the difference of distance and focal length can be avoided, and the consistency of the size and the position of the portrait in the portrait image and the quality of the portrait image can be improved by preprocessing the image.
In detail, the preprocessing operation module 101 performs preprocessing operation on the to-be-identified user picture by executing the following operations to obtain a standard picture, including:
carrying out digital processing on the user picture to be identified to obtain a digital picture;
performing histogram equalization operation on the digital picture to obtain an equalized picture;
carrying out sharpening smoothing operation on the balanced picture to obtain an enhanced picture;
and carrying out normalization operation on the enhanced picture to obtain a standard picture.
In the embodiment of the invention, the digital processing is to perform gray sampling and quantization on the user picture to be identified on an M x N dot matrix to obtain a digital picture which can be processed by a computer.
In an embodiment of the present invention, performing the histogram equalization operation can convert the digital picture into an equalized picture having the same pixel point at each gray level.
In an optional embodiment of the present invention, the contour information in the picture can be enhanced by performing a sharpening operation on the equalized picture by using a LoG operator, so that details of the picture are highlighted, but noise of the sharpened picture is enhanced, and therefore, the smoothing process is further performed, so that the noise of the picture is eliminated, and the contour or lines of the picture are not blurred.
Preferably, the smoothing process may be performed by a median method.
In the embodiment of the present invention, the purpose of normalizing the enhanced pictures is to make pictures taken under different conditions (such as illumination intensity, direction, distance, posture, and the like) consistent.
Further, the normalizing the enhanced picture to obtain a standard picture includes:
and carrying out geometric normalization and gray level normalization operation on the standard picture to obtain the standard picture.
In an embodiment of the invention, the geometric normalization is helpful for correcting size difference and angle inclination caused by imaging distance change and portrait posture change in the picture, and the gray scale normalization is helpful for compensating the portrait in the picture obtained under different light intensities and light source directions.
The model matting module 102 is configured to input the standard picture to a pre-constructed portrait matting model, detect the standard picture by using a portrait detection network in the portrait matting model, obtain a portrait picture, and then divide the portrait into two parts by using a portrait division network in the portrait matting model, so as to obtain a portrait region, where the portrait matting model includes an end-to-end connection of a portrait detection network and a portrait division network.
In the embodiment of the invention, the standard picture is input into a pre-constructed portrait matting model, so that a portrait background which divides the background and the portrait can be obtained, wherein the portrait matting model comprises end-to-end connection of a portrait detection network and a portrait division network.
In the embodiment of the invention, the portrait picture is a picture obtained by cutting out the portrait after the portrait is detected by the portrait detection network. The method comprises the following steps of utilizing a portrait detection network in a pre-constructed portrait matting model to detect a standard picture so as to detect a portrait outline and obtain a detected portrait picture, wherein the portrait detection network comprises: convolutional layers, pooling layers, full-link layers, and activation functions.
In detail, the model matting module 102 detects the standard picture by using a portrait detection network in the portrait matting model to obtain a portrait picture by performing the following operations, including:
performing feature extraction on the standard picture by using the convolution layer in the portrait detection network to obtain a feature picture;
performing dimensionality reduction operation on the feature picture by using a pooling layer in the portrait detection network to obtain a dimensionality reduction picture;
fully connecting the dimensionality reduction pictures by using a full connection layer in the portrait detection network to obtain a spliced portrait picture;
and outputting the spliced portrait picture by using an activation function in the portrait detection network to obtain the portrait picture.
In the embodiment of the invention, the feature extraction is a feature picture obtained by calculating the pixel matrix of the standard picture.
In an embodiment of the present invention, performing pooling operation on the standard picture by using the pooling layer is to perform average region division on the feature picture, and replace a pixel value in the region with an average value of a sum of all pixel values in the region, so that the feature extracted from the feature picture is not lost and dimension reduction operation is performed.
Preferably, the activation function may be a ReLU function, and the stitched portrait picture may be activated to obtain the finally detected portrait picture including the portrait feature information.
In the embodiment of the present invention, a detected portrait image is segmented by using a segmentation network in the portrait matting model, so as to implement portrait matting and obtain a portrait region, wherein the portrait segmentation network includes: a hole convolution layer, a pyramid pooling layer, and an activation function.
Further, the model matting module 102 segments the image picture by using an image segmentation network in the image matting model to obtain an image region by performing the following operations:
extracting the characteristics of the portrait picture by using the cavity convolution layer in the portrait segmentation network and carrying out characteristic fusion to obtain a fused portrait picture;
carrying out portrait segmentation on the fused portrait picture by utilizing a pyramid pooling layer in the portrait segmentation network to obtain a segmented portrait picture;
and inputting the segmented portrait picture into an activation function in the portrait segmentation network to obtain a portrait area output by the activation function.
In the embodiment of the invention, the hole convolution layer has more special holes than a common convolution layer, and the visual field is wider, so that the global information of more pictures can be mastered through feature fusion under the condition that the feature pictures are reduced by the same times.
In an embodiment of the present invention, the pyramid pooling layer replaces a general pooling layer, so that no matter what the size of the picture input into the portrait splitting network is, the split pictures with the same picture size can be output.
Preferably, the activation function may be a Sigmoid function, and the segmented portrait picture may be activated to obtain a portrait area with a background separated from the portrait.
The picture frame judging module 103 is used for acquiring the business card template and the business card information and judging whether a picture frame exists in a photo area in the business card template.
In the embodiment of the invention, the business card template mainly comprises a photo area and a business card information area.
In this embodiment, the business card template may be obtained from a preset business card template library. The name card information refers to self-introduction information of the user, including name, telephone, company, position, company address, etc. the name card information may be information input to the website by the user or directly obtained from the enterprise website.
In the embodiment of the invention, whether a picture frame exists in the picture area in the name card template can be judged by using a boosting Edge Learning algorithm (Boosted Edge Learning Bel).
The first portrait business card generation module 104 is configured to, if a picture frame is located in a photo area in the business card template, arrange the portrait area in the picture frame, and arrange the business card information on the business card template to obtain a first portrait business card.
In detail, the first portrait card generation module 104 may perform the following operations to, if a picture frame exists in a photo region in the card template, lay out the portrait region in the picture frame, including:
if a picture frame exists in the picture area in the business card template, obtaining the picture frame height, the picture frame width and the picture frame center line of the picture frame;
and carrying out zooming operation on the portrait area according to the picture frame height, the picture frame width and the picture frame center line, so that the portrait area height is consistent with the picture frame height, the portrait area width is consistent with the picture frame width, the area center line is consistent with the picture frame center line, and the portrait area is distributed in the picture frame.
In an embodiment of the present invention, the height of the portrait area after scaling is consistent with the frame height, a scaling ratio, which is a frame height box _ h/portrait area height for _ h, is obtained, the width of the portrait area and the width of the frame are calculated by using the scaling ratio, and then the central line of the scaled portrait area is aligned with the central line of the frame, so that the portrait area is centered in the frame.
In the embodiment of the invention, the first portrait business card refers to a business card with a picture frame in a photo area.
In the embodiment of the invention, the business card information can be distributed on the business card template according to the business card template, if the business card information is too long, the line is changed according to the preset specified line number, and the first portrait business card is generated by distributing the portrait area in the picture frame.
And the second portrait business card generation module 105 is used for laying out the portrait area in the photo area if no picture frame exists in the photo area in the business card template, and laying out the business card information in the business card template to obtain a second portrait business card.
In the embodiment of the invention, in order to ensure that the portrait area is distributed in the business card template without visual 'abrupt' or 'suspension' feeling, the business card template without a picture frame in the photo area can be selected.
In detail, if the photo area in the business card template has no frame, the step of laying out the portrait area in the photo area includes:
if the photo area in the name card template has no picture frame, acquiring a top edge value coordinate and a bottom edge value coordinate of the photo area;
and after the top edge value coordinates are aligned with the top edge of the portrait area and the top edge of the photo area, calculating the scaling ratio of the portrait area, and calculating the bottom edge value of the portrait area according to the scaling ratio and the bottom edge value, so that the portrait area is laid out in the photo area.
In the embodiment of the present invention, a cascading style sheet technique may be used to calculate a scaling ratio of the portrait area, and the portrait area is scaled according to the scaling ratio to obtain the portrait area aligned with the top edge and the bottom edge of the photo area.
In the embodiment of the invention, the second portrait business card refers to a business card without a picture frame in the photo area of the business card template.
In the embodiment of the invention, the business card information can be distributed on the business card template according to the business card template, if the business card information is too long, the line is changed according to the preset specified line number, and a second portrait business card is generated in the photo area according to the portrait area distribution.
In the embodiment of the invention, firstly, the standard picture is obtained by preprocessing the picture of the user to be identified, and after the preprocessing operation is carried out, the details in the standard picture can be more prominent, the picture is clearer and the picture quality is higher; secondly, detecting the characteristics of the standard picture by using a portrait detection network in a pre-constructed portrait matting model, and cutting the detected portrait to obtain a portrait picture; further, the portrait picture is divided by utilizing a portrait division network in the portrait matting model, and the detected portrait picture is divided, so that portrait matting is realized, and a portrait area is obtained; and finally, according to the name card template, the name card information input by the user and the portrait area are arranged in the photo area in the name card template, so that the portrait name card is obtained, user adjustment is not needed, and the generation efficiency of the portrait name card is improved. Therefore, the portrait business card generation device provided by the embodiment of the invention can improve the efficiency of portrait business card generation.
Fig. 3 is a schematic structural diagram of an electronic device for implementing a portrait business card generation method according to the present invention.
The electronic device may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further include a computer program, such as a portrait business card creation program, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of media, which includes flash memory, removable hard disk, multimedia card, card type memory (e.g., SD or DX memory, etc.), magnetic memory, local disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of a portrait card creation program, etc., but also to temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (such as a portrait name card generation program) stored in the memory 11 and calling data stored in the memory 11.
The communication bus 12 may be a PerIPheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The communication bus 12 is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
Fig. 3 shows only an electronic device having components, and those skilled in the art will appreciate that the structure shown in fig. 3 does not constitute a limitation of the electronic device, and may include fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Optionally, the communication interface 13 may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices.
Optionally, the communication interface 13 may further include a user interface, which may be a Display (Display), an input unit (such as a Keyboard (Keyboard)), and optionally, a standard wired interface, or a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The portrait business card generation program stored in the memory 11 of the electronic device is a combination of a plurality of computer programs, and when running in the processor 10, can realize:
acquiring a user picture to be identified, and preprocessing the user picture to be identified to obtain a standard picture;
inputting the standard picture into a pre-constructed image matting model, detecting the standard picture by using an image detection network in the image matting model to obtain an image picture, and then segmenting the image picture by using an image segmentation network in the image matting model to obtain an image area, wherein the image matting model comprises end-to-end connection of an image detection network and an image segmentation network;
acquiring a business card template and business card information, and judging whether a picture frame exists in a picture area in the business card template;
if the photo area in the business card template has a picture frame, the portrait area is arranged in the picture frame, and the business card information is arranged on the business card template to obtain a first portrait business card;
and if the photo area in the business card template has no picture frame, the portrait area is distributed in the photo area, and the business card information is distributed in the business card template to obtain a second portrait business card.
Specifically, the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the computer program, which is not described herein again.
Further, the electronic device integrated module/unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable medium. The computer readable medium may be non-volatile or volatile. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
An embodiment of the present invention may further provide a computer medium, where the computer medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program may implement:
acquiring a user picture to be identified, and preprocessing the user picture to be identified to obtain a standard picture;
inputting the standard picture into a pre-constructed image matting model, detecting the standard picture by using an image detection network in the image matting model to obtain an image picture, and then segmenting the image picture by using an image segmentation network in the image matting model to obtain an image area, wherein the image matting model comprises end-to-end connection of an image detection network and an image segmentation network;
acquiring a business card template and business card information, and judging whether a picture frame exists in a picture area in the business card template;
if the photo area in the business card template has a picture frame, the portrait area is arranged in the picture frame, and the business card information is arranged on the business card template to obtain a first portrait business card;
and if the photo area in the business card template has no picture frame, the portrait area is distributed in the photo area, and the business card information is distributed in the business card template to obtain a second portrait business card.
Further, the computer usable medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A portrait business card generation method, the method comprising:
acquiring a user picture to be identified, and preprocessing the user picture to be identified to obtain a standard picture;
inputting the standard picture into a pre-constructed image matting model, detecting the standard picture by using an image detection network in the image matting model to obtain an image picture, and then segmenting the image picture by using an image segmentation network in the image matting model to obtain an image area, wherein the image matting model comprises end-to-end connection of an image detection network and an image segmentation network;
acquiring a business card template and business card information, and judging whether a picture frame exists in a picture area in the business card template;
if the photo area in the business card template has a picture frame, the portrait area is arranged in the picture frame, and the business card information is arranged on the business card template to obtain a first portrait business card;
and if the photo area in the business card template has no picture frame, the portrait area is distributed in the photo area, and the business card information is distributed in the business card template to obtain a second portrait business card.
2. The portrait business card generation method of claim 1, wherein the face detection network comprises: convolution layer, pooling layer, full connection layer and activation function, the utilization portrait detection network in the portrait cutout model is right the standard picture detects, obtains the portrait picture, includes:
performing feature extraction on the standard picture by using the convolution layer in the portrait detection network to obtain a feature picture;
performing dimensionality reduction operation on the feature picture by using a pooling layer in the portrait detection network to obtain a dimensionality reduction picture;
fully connecting the dimensionality reduction pictures by using a full connection layer in the portrait detection network to obtain a spliced portrait picture;
and outputting the spliced portrait picture by using an activation function in the portrait detection network to obtain the portrait picture.
3. The portrait business card generation method of claim 1, wherein the portrait segmentation network comprises: the cavity convolution layer, pyramid pooling layer and activation function, the utilization portrait cut apart the network in the portrait cutout model is right the portrait picture is cut apart, obtains the portrait region, includes:
extracting the characteristics of the portrait picture by using the cavity convolution layer in the portrait segmentation network and carrying out characteristic fusion to obtain a fused portrait picture;
carrying out portrait segmentation on the fused portrait picture by utilizing a pyramid pooling layer in the portrait segmentation network to obtain a segmented portrait picture;
and inputting the segmented portrait picture into an activation function in the portrait segmentation network to obtain a portrait area output by the activation function.
4. The portrait business card generation method of claim 1, wherein if a picture frame exists in a photo area in the business card template, laying out the portrait area in the picture frame comprises:
if a picture frame exists in the picture area in the business card template, obtaining the picture frame height, the picture frame width and the picture frame center line of the picture frame;
and carrying out zooming operation on the portrait area according to the picture frame height, the picture frame width and the picture frame center line, so that the portrait area height is consistent with the picture frame height, the portrait area width is consistent with the picture frame width, the area center line is consistent with the picture frame center line, and the portrait area is distributed in the picture frame.
5. The method for generating a portrait business card of claim 1, wherein if the photo area in the business card template has no frame, the step of laying out the portrait area in the photo area comprises:
if the photo area in the name card template has no picture frame, acquiring a top edge value coordinate and a bottom edge value coordinate of the photo area;
and after the top edge value coordinates are aligned with the top edge of the portrait area and the top edge of the photo area, calculating the scaling ratio of the portrait area, and calculating the bottom edge value of the portrait area according to the scaling ratio and the bottom edge value, so that the portrait area is laid out in the photo area.
6. The portrait business card generation method of claim 1, wherein the preprocessing operation on the picture of the user to be identified to obtain a standard picture comprises:
carrying out digital processing on the user picture to be identified to obtain a digital picture;
performing histogram equalization operation on the digital picture to obtain an equalized picture;
carrying out sharpening smoothing operation on the balanced picture to obtain an enhanced picture;
and carrying out normalization operation on the enhanced picture to obtain a standard picture.
7. The portrait business card generation method of claim 6, wherein the normalizing operation on the enhanced picture to obtain a standard picture comprises:
and carrying out geometric normalization and gray level normalization operation on the standard picture to obtain the standard picture.
8. A portrait business card creation apparatus, comprising:
the system comprises a preprocessing operation module, a standard image acquisition module and a recognition module, wherein the preprocessing operation module is used for acquiring a user image to be recognized and carrying out preprocessing operation on the user image to be recognized to obtain the standard image;
the model matting module is used for inputting the standard picture into a pre-constructed image matting model, detecting the standard picture by utilizing an image detection network in the image matting model to obtain an image picture, and then segmenting the image picture by utilizing an image segmentation network in the image matting model to obtain an image region, wherein the image matting model comprises end-to-end connection of the image detection network and the image segmentation network;
the picture frame judging module is used for acquiring a business card template and business card information and judging whether a picture frame exists in a photo area in the business card template;
the first portrait business card generating module is used for laying the portrait area in the picture frame and laying the business card information on the business card template to obtain a first portrait business card if the photo area in the business card template has the picture frame;
and the second portrait business card generation module is used for laying out the portrait area in the photo area if no picture frame exists in the photo area in the business card template, and laying out the business card information in the business card template to obtain a second portrait business card.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the portrait business card generation method of any of claims 1 to 7.
10. A computer medium storing a computer program, wherein the computer program, when executed by a processor, implements the portrait business card generation method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111087077.3A CN113793406B (en) | 2021-09-16 | 2021-09-16 | Portrait business card generation method and device, electronic equipment and storable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111087077.3A CN113793406B (en) | 2021-09-16 | 2021-09-16 | Portrait business card generation method and device, electronic equipment and storable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113793406A true CN113793406A (en) | 2021-12-14 |
| CN113793406B CN113793406B (en) | 2024-08-27 |
Family
ID=78878605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111087077.3A Active CN113793406B (en) | 2021-09-16 | 2021-09-16 | Portrait business card generation method and device, electronic equipment and storable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113793406B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1571566A (en) * | 2004-03-03 | 2005-01-26 | 马堃 | Multiplexing synthetic method for memberized electronic handset visiting card |
| CN110889855A (en) * | 2019-10-28 | 2020-03-17 | 公安部交通管理科学研究所 | Certificate photo matting method and system based on end-to-end convolutional neural network |
| CN111445557A (en) * | 2020-03-23 | 2020-07-24 | 中国建设银行股份有限公司 | Automatic generation method and device for bank branch business card |
| CN111476201A (en) * | 2020-04-29 | 2020-07-31 | Oppo广东移动通信有限公司 | Certificate photo manufacturing method, terminal and storage medium |
| CN112991377A (en) * | 2021-04-22 | 2021-06-18 | 辽宁向日葵教育科技有限公司 | Keying algorithm based on opencv and shader fusion technology |
-
2021
- 2021-09-16 CN CN202111087077.3A patent/CN113793406B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1571566A (en) * | 2004-03-03 | 2005-01-26 | 马堃 | Multiplexing synthetic method for memberized electronic handset visiting card |
| CN110889855A (en) * | 2019-10-28 | 2020-03-17 | 公安部交通管理科学研究所 | Certificate photo matting method and system based on end-to-end convolutional neural network |
| CN111445557A (en) * | 2020-03-23 | 2020-07-24 | 中国建设银行股份有限公司 | Automatic generation method and device for bank branch business card |
| CN111476201A (en) * | 2020-04-29 | 2020-07-31 | Oppo广东移动通信有限公司 | Certificate photo manufacturing method, terminal and storage medium |
| CN112991377A (en) * | 2021-04-22 | 2021-06-18 | 辽宁向日葵教育科技有限公司 | Keying algorithm based on opencv and shader fusion technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113793406B (en) | 2024-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111652845B (en) | Automatic labeling method and device for abnormal cells, electronic equipment and storage medium | |
| CN112528863A (en) | Identification method and device of table structure, electronic equipment and storage medium | |
| WO2021151277A1 (en) | Method and apparatus for determining severity of damage on target object, electronic device, and storage medium | |
| CN111783982B (en) | Method, device, equipment and medium for acquiring attack sample | |
| CN111862096B (en) | Image segmentation method and device, electronic equipment and storage medium | |
| CN112132812B (en) | Certificate verification method and device, electronic equipment and medium | |
| CN111476760B (en) | Medical image generation method and device, electronic equipment and medium | |
| CN113705462A (en) | Face recognition method and device, electronic equipment and computer readable storage medium | |
| CN114708461A (en) | Multi-modal learning model-based classification method, device, equipment and storage medium | |
| CN111985449A (en) | Rescue scene image identification method, device, equipment and computer medium | |
| CN117455762A (en) | Method and system for improving resolution of recorded picture based on panoramic automobile data recorder | |
| CN113420684A (en) | Report recognition method and device based on feature extraction, electronic equipment and medium | |
| CN115049836B (en) | Image segmentation method, device, equipment and storage medium | |
| CN113793406B (en) | Portrait business card generation method and device, electronic equipment and storable medium | |
| CN115482169A (en) | Low-illumination image enhancement method and device, electronic equipment and storage medium | |
| CN113705686B (en) | Image classification method, device, electronic equipment and readable storage medium | |
| CN115203375A (en) | Data enhancement method, device, equipment and storage medium of image-text cross-modal model | |
| CN112233194B (en) | Medical picture optimization method, device, equipment and computer readable storage medium | |
| CN113705459B (en) | Face snapshot method and device, electronic equipment and storage medium | |
| CN111652226B (en) | Picture-based target identification method and device and readable storage medium | |
| CN112183520A (en) | Intelligent data information processing method and device, electronic equipment and storage medium | |
| CN112541899A (en) | Incomplete certificate detection method and device, electronic equipment and computer storage medium | |
| CN114359645B (en) | Image expansion method, device, equipment and storage medium based on characteristic area | |
| CN113487630B (en) | Matting method, device, equipment and storage medium based on material analysis technology | |
| CN118506393B (en) | Method and system for realizing intelligent recognition of engineering drawing based on OCR technology |
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 |