CN110536044B - Automatic certificate photo shooting method and device - Google Patents
Automatic certificate photo shooting method and device Download PDFInfo
- Publication number
- CN110536044B CN110536044B CN201910858868.8A CN201910858868A CN110536044B CN 110536044 B CN110536044 B CN 110536044B CN 201910858868 A CN201910858868 A CN 201910858868A CN 110536044 B CN110536044 B CN 110536044B
- Authority
- CN
- China
- Prior art keywords
- shooting
- photo
- picture
- person
- shot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/62—Control of parameters via user interfaces
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/667—Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/04—Synchronising
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/272—Means for inserting a foreground image in a background image, i.e. inlay, outlay
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Studio Devices (AREA)
- Cameras Adapted For Combination With Other Photographic Or Optical Apparatuses (AREA)
Abstract
The application discloses an automatic certificate photo shooting method and device. The method comprises the steps of monitoring the height of a shot person; adjusting the shooting height of the shooting device according to the height of the shot person; the left screen and the right screen of the shooting device synchronously play dynamic pictures, respectively capture the moving line positions of the left eyeball and the right eyeball of a shot person, and lock the positions of the two eyeballs; dynamically adjusting a screen picture, guiding a shot person to migrate a visual focus, correcting the eyeball position and the face form, detecting the eyeball position and the face form of the shot person in real time, and taking a picture when the eyeball position and the face form of the shot person are detected to accord with a shooting rule; and (3) extracting the portrait in the shot photo, fusing the portrait with a preselected background, and cutting the fused image into a certificate photo for automatic typesetting and outputting. According to the certificate photo shooting method, a photographer can take photos only by standing or sitting in front of the shooting device and then directly watching the dynamic pictures on the screen of the shooting device, and the natural expression of the eye presented in the photos is smiling.
Description
Technical Field
The application relates to the technical field of portrait shooting, in particular to an automatic certificate photo shooting method and device.
Background
In the existing portrait shooting process, especially the shooting of identification photos, a background picture is generally required to be set in advance, and then a photographer shoots the photos.
With the increasing demand for photographing, some automatic photographing methods for identification photographs have appeared, generally, an alignment frame is set first, and then a user adjusts a face into the alignment frame to perform photographing, which causes that a photographed person is always in a passive state during photographing, cannot be in an optimal photographing state, and has poor human-computer interaction experience.
In addition, the requirement for the photo for taking the certificate photo is high, but in the shooting process, the eyeball of a person does not necessarily look at the camera, so that the eyeball moving line is not clear, and the face contour cannot be adjusted according to the contour of the person. Based on the defects, the application is produced.
Disclosure of Invention
The application provides an automatic certificate photo shooting method, which comprises the following steps:
monitoring the height of a shot person;
adjusting the shooting height of the shooting device according to the height of the shot person;
the left screen and the right screen of the shooting device synchronously play dynamic pictures, respectively capture the moving line positions of the left eyeball and the right eyeball of a shot person, and lock the positions of the two eyeballs;
dynamically adjusting a screen picture, guiding a shot person to migrate a visual focus, correcting the eyeball position and the face form, detecting the eyeball position and the face form of the shot person in real time, and taking a picture when the eyeball position and the face form of the shot person are detected to accord with a shooting rule;
and (3) extracting the portrait in the shot photo, fusing the portrait with a preselected background, and cutting the fused image into a certificate photo for automatic typesetting and outputting.
The automatic identification photo shooting method comprises the steps that a height sensor is arranged at the top of a shooting device, a ground weight sensor is arranged in a fixed station area which can be monitored by the height sensor, after the ground weight sensor detects that a person to be shot stands in the detectable fixed station area, a shooting starting signal is transmitted to the shooting device, and the shooting device monitors the height of a human body through the height sensor.
The automatic identification photo shooting method comprises the steps of detecting the eyeball position and the face form of a shot person in real time, starting a continuous shooting mode when the eyeball position and the face form of the shot person are detected to accord with shooting rules, shooting a plurality of photos, and selecting one photo from the photos to execute green screen matting.
The method for automatically shooting the identification photo comprises the following steps of:
displaying all shot photos on a display screen, selecting the photos through a touch screen by a shot person, selecting the needed background color and the needed certificate photo size by the shot person, and then performing green screen matting on the photos selected by the shot person;
or, training an image selection machine model for selecting the optimal photo in advance in the shooting device, learning the existing aesthetic big data by adopting a neural network algorithm to obtain the machine model most conforming to modern aesthetics, inputting a plurality of shot photos into the machine model, and selecting the optimal photo for green-curtain matting.
The method for automatically shooting the certificate photo comprises the following steps of:
organizing dynamic pictures, converting the organized dynamic pictures into sequence frames, and storing the sequence frames according to the dynamic sequence of the pictures;
setting the number of virtual viewpoints to be rendered and the resolution of an output multi-view sequence frame;
setting image segmentation parameters, and splitting the current frame image into a left image and a right image according to the image segmentation parameters;
and setting the visual range of the left and right images according to the distance between the two screens, and rendering the virtual viewpoints in the visual range of the left and right images according to the number of the set virtual viewpoints to be rendered.
The automatic identification photo shooting method comprises the following steps of:
the left screen and the right screen of the shooting device respectively acquire left and right face images of a shot person, convert the images into gray level images and then carry out binarization;
intercepting ROI images of eye regions in the left and right face images, performing corrosion re-expansion operation on the ROI images, and performing drying treatment on the corroded and re-expanded images;
the eyeball position is extracted from the image after the dryness is removed.
The automatic identification photo shooting method comprises the following steps of dynamically adjusting a screen, guiding a shot person to move a visual focus, and correcting an eyeball position and a face form:
determining the central point position of the picture to be played and the area of the picture to be played according to the positioned eyeball position;
adjusting the position of the picture display area according to the eyeball position to attract the eyeball to move;
adjusting the size, color and brightness of a picture display area, and dispersing visual focus;
and playing dynamic smile expression to guide the facial expression to be smile naturally.
The automatic certificate photo shooting method comprises the following steps of cutting the fused image into the certificate photo: the method comprises the steps of obtaining a square 1 with a nose tip of a human face as a center based on a human face recognition algorithm, amplifying the square 1 by 2.5 times to obtain a square 2, taking the square 2 as the size of a photo-capture head, carrying out mask cutting processing on the square 2 according to a certificate photo-capture standard, and reserving an image in an effective area to obtain a certificate photo-capture.
The application also provides an automatic certificate photo shooting device which comprises a shell and a shooting area surrounded by the shell; dividing a fixed station area and a photographing area in the photographing area, arranging a ground weight sensor on the fixed station area for detecting whether a photographed person enters or not, arranging a green curtain on the inner surface of the shell opposite to the photographing area, and placing a photographing device in the photographing area;
the device of shooing includes controller, two display screens, altitude sensor, shooting equipment, photography banks spare and photo printing equipment, and two display screens, altitude sensor, shooting equipment, photography banks spare and photo printing equipment are connected to the controller, and altitude sensor and photography banks spare set up at the device top of shooing, set up the interval and the people's eye distance matching of two display screens, set up the shooting equipment in the centre of two display screens.
The application also provides an automatic certificate photo shooting device which comprises a height measuring module, a height adjusting module, a dynamic picture playing module, a dynamic picture adjusting module, a shooting module, a certificate photo output module and a printing module;
the height measuring module is used for detecting the height of the shot person;
the height adjusting module is used for adjusting the shooting height of the shooting device according to the height of the shot person measured by the height measuring module;
the dynamic picture playing module is used for simultaneously playing dynamic pictures by a left screen and a right screen of the shooting device, respectively capturing the moving line positions of left and right eyeballs of a shot person and locking the positions of the two eyeballs;
the dynamic picture adjusting module is used for dynamically adjusting a screen picture, guiding a shot person to migrate a visual focus and correcting the position of eyeballs;
the shooting module detects the eyeball position and the face shape of the shot person in real time and shoots when detecting that the eyeball position and the face shape of the shot person accord with the shooting rule;
the certificate photo output module is used for picking out the portrait in the shot photo, fusing the portrait with a preselected background and cutting the fused image into the certificate photo;
and the printing module is used for automatically typesetting, printing and outputting the cut certificate photo.
The beneficial effect that this application realized is as follows: by adopting the automatic certificate photo shooting method, the automatic shooting of the certificate photo can be realized without autonomous operation of a photographer under the condition of ensuring that the expression of the photographer is natural, the photographer only needs to stand or sit in front of the shooting device, then the photographing can be realized by directly viewing the dynamic picture on the screen of the shooting device, the whole process is like watching a television by the photographer, the photographing can be quickly finished unconsciously under the natural state, and the eye expression presented in the photo is smiling.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings can be obtained by those skilled in the art according to the drawings.
FIG. 1 is a flowchart of an automatic identification photo shooting method provided in an embodiment of the present application;
FIG. 2 is a schematic view of a process for locking the position of an eye;
FIG. 3 is a schematic diagram of a trace change of a screen;
fig. 4 is a schematic diagram of an automatic camera for identification photographs.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
As shown in fig. 1, an embodiment of the present application provides an automatic identification photo shooting method, which is applied to a shooting device provided by the present application, and the shooting method specifically includes the following steps:
specifically, a height sensor is arranged at the top of the shooting device of the application and used for detecting the height of a shot person; a ground weight sensor is arranged in a fixed area which can be monitored by the height sensor and is used for monitoring whether a human body enters the shooting, after the ground weight sensor detects that a shot person stands in the detectable fixed area, a shooting starting signal is transmitted to the shooting device, and the shooting device monitors the height of the human body through the height sensor;
as an alternative embodiment, when the photographing device detects that the height of the photographed person is higher than a preset height (e.g., 140cm), the photographed person is prompted to sit on a set chair, the height of the chair is set to 40cm, and if the height of the photographed person is lower than the preset height, the photographed person is prompted to stand.
specifically, after the shooting device detects the height of a shot person, the driving motor is controlled to drive the sliding rail to move according to the height of the shot person, and the shooting height of the shooting device is adjusted, so that a screen shooting area of the shooting device can be aligned to the face of the shot person;
in addition, in order to reduce the power consumption, the shooting equipment and the shooting lamp assembly are in a closed state when no shooting service is available, the shooting equipment and the shooting lamp assembly are started when a shot person is monitored to enter the shooting process, and the height of the shooting lamp assembly is adjusted when the shooting height of the shooting device is adjusted, so that the irradiation angle of the shooting lamp assembly and the shooting angle of the shooting equipment reach the optimal state.
in the embodiment of the application, the shooting device consists of two screens, and a camera lens is arranged between the two screens. Since the interpupillary distance of the human body is generally 57-67mm, the distance between the two screens is preferably set to be 57 mm; after the height of the shooting device is adjusted, the shooting device organizes a dynamic picture, and the played dynamic picture of 16:9, 1080p is divided into two parts which are respectively rendered on two screens of the shooting device;
after the shooting device organizes the dynamic picture, the dynamic picture is divided to obtain two sub-pictures, then two sets of processing threads are respectively established in the shooting device and are used for respectively processing the left screen and the right screen, the two sub-pictures are respectively sent to the two screens, and then the two sub-pictures are respectively rendered on the corresponding screens, and the method specifically comprises the following sub-steps:
step S11, converting the organized dynamic pictures into sequence frames, and storing the sequence frames according to the dynamic sequence of the pictures;
step S12, setting the number of virtual viewpoints to be rendered and the resolution of the output multi-view sequence frame;
the present application takes a dynamic picture as an example of a left-right format, and sets the number of virtual views to be rendered to 8 views, and the resolution of a sequence frame to 1920 × 1680.
S13, setting image segmentation parameters, and splitting the current frame image into a left image and a right image according to the image segmentation parameters;
specifically, the resolution of the left and right images is zoomed to 960 × 540, the setting of the image segmentation parameters comprises the setting of filtering parameters and image segmentation parameters, wherein the setting of the filtering parameters comprises the setting of the size of a filtering window, the sigma value of a color component and the sigma value of a position component, then the filtering of the left and right images is respectively carried out by a fast bilateral filtering algorithm, and the color space of the left and right images is converted into a Lab color model from RGB; setting image segmentation parameters comprises setting a color threshold, a radius threshold and the number of pixel points of a minimum region, and splitting the current frame image into a left image and a right image according to the image segmentation parameters.
Step S14, setting the visual range of the left and right images according to the distance between the two screens;
and step S15, rendering the virtual viewpoints according to the set number of the virtual viewpoints needing to be rendered in the visual range of the left and right road images.
Fig. 2 is a schematic diagram of a process of locking the positions of eyeballs, capturing the positions of the moving lines of the left and right eyeballs of the subject, and locking the positions of the two eyeballs, specifically including the following sub-steps:
step S21, the left and right screens of the shooting device respectively acquire left and right face images of the shot person, convert the images into gray level images and then carry out binarization;
step S22, intercepting ROI images of eye regions in the left and right face images, carrying out corrosion re-expansion operation on the ROI images, and then carrying out drying treatment on the corroded and re-expanded images;
specifically, a region to be processed is outlined in a circular, rectangular or irregular polygonal mode or the like through an algorithm and a function of machine vision software such as Halcon, OpenCV, Matlab and the like in the processed image, namely, the region is a region of interest ROI image (the first image in fig. 2 is obtained by intercepting the ROI image in a rectangular mode), then the ROI image is corroded and then expanded, and then drying processing is performed to obtain an image shown in the second image in fig. 2.
Step S23, extracting eyeball positions from the images after drying;
specifically, pixel points are extracted from the image after the dryness is removed, then the gradient of each pixel point (i.e., the maximum value obtained by the directional derivative of the pixel point along the direction, including the amplitude and the direction) is calculated, as the gray value closer to the center position of the eyeball is lower, more connecting lines in the gradient direction are intersected at the point, and the point with the largest straight line intersection point in the gradient direction is searched to be the eyeball position, so that the third graph in fig. 2 is obtained.
In addition, when the eyeballs are positioned, the user is prompted to tilt the head leftwards or rightwards according to the positions of the eyeballs, so that the eyeballs can look straight at the picture in parallel.
as an optional embodiment, a shooting thread and an eyeball capturing thread are started simultaneously in the shooting device of the present application, wherein the eyeball capturing thread detects the eyeball position in real time, when the eyeball position of a human body is detected to reach an optimal shooting mode, the eyeball capturing thread immediately transmits a shooting signal to the shooting thread, the shooting thread starts a continuous shooting mode, and a plurality of photos are taken as alternatives;
the method comprises the following steps of dynamically adjusting a screen, guiding a shot to move visual focus, and correcting eyeball positions and facial forms, and specifically comprises the following substeps:
step 141, determining the central point position of the picture to be played and the area of the picture to be played according to the positioned eyeball position;
by way of example, fig. 3 is a schematic diagram of a track change of a screen, which includes 6 basic pictures, where a playing area of picture 1 is a visual field area of an eyeball, and includes a central bright point and a large number of interference elements surrounding the central bright point, and a display area of the central bright point is determined by a located eyeball position;
because the human eyes see the object by matching the pupils and the retinas, in order to accurately acquire the visual field change of the eyes after the positions of the eyeballs are changed, the visual field of the eyes is simulated by a preset eye simulation system, the simulated left and right eyeballs, the left and right eye pupils and the left and right eye retinas corresponding to the left and right eyeballs are arranged in the eye simulation system, the centers of the left and right eye retinas are set to be fixed, the pupil movement angles of the left and right eyes are respectively detected by an eyeball tracking technology, the pupil movement angles and the initial pupil positions are subjected to superposition operation, the relative positions of the pupil center points and the retina center points are obtained, and the current positions of the eyeballs after movement are captured;
respectively taking the connecting line of the current pupil center point of the left eyeball and the current pupil center point of the right eyeball and the corresponding retina center point as the center lines, wherein the angle range space between the two center lines is the visual field of the eyes of the shot person, after the visual field of the eyes of the shot person is determined, the center point of the visual field is taken as the center point of the playing picture, and then the picture is played in the visual field area.
Step 142, adjusting the position of the picture display area according to the eyeball position to attract the eyeball to move;
the picture played in the visual field area is divided into a central resolution area and an effective visual field area of human eyes according to the visual range of human eyes, for example, the picture in fig. 3 changes, a central bright point in the picture is the central resolution area, and the area which can be distinguished by a photographer without rotating the head is the effective visual field area of human eyes;
if the eyeball watching center resolution area is detected to form a certain angle with the parallel line, the position of the display picture needs to be adjusted, so that the center resolution area of the display picture is parallel to the eyeball watching direction.
Step 143, adjusting the size, color and brightness of the picture display area, and dispersing the visual focus;
in FIG. 3, the frames 2-5 are schematic views illustrating the adjustment of the frame display area. Specifically, the area of the display region is calculated by the following formula:
wherein s is the area of the picture display area, alpha 1 and beta 1 are the angles between the left eye pupil and the left and right edges of the display area and the parallel lines, alpha 2 and beta 2 are the angles between the right eye pupil and the left and right edges of the display area and the parallel lines, a is the distance between the human eye pupil of the photographed person, and b is the distance between the central resolution area and the central point of the human eye pupil;
the adjusting of the brightness of the picture specifically comprises the following substeps:
step S31, counting the sensitivity of human eyes to brightness, and predetermining the preset optimal brightness value of the display screen capable of matching the current environment brightness;
the preset optimal brightness value is an optimal brightness value which is predetermined according to the sensitivity of big data statistics on color and brightness of normal human eyes.
Step S32, calculating the intensity of the ambient light, the color brightness value and the contrast of the display screen, and calculating the current brightness value of the display screen;
step S33, comparing the current brightness value with a preset optimal brightness value, if the absolute value of the difference between the current brightness value and the preset optimal brightness value is less than or equal to a preset threshold value, the brightness does not need to be adjusted, and if the absolute value of the difference between the current brightness value and the preset optimal brightness value is greater than the preset threshold value, the brightness of the display screen is adjusted by adjusting the voltage value of the analog positive power supply of the display screen, so that the absolute value of the difference between the current brightness value and the preset optimal brightness value of the display screen is within the preset threshold value;
the brightness of the picture is determined by the voltage value of the analog positive voltage, and the voltage value is adjusted by adjusting the resistance value in the analog positive voltage drop circuit.
In addition, the adjusting of the color of the picture specifically comprises the following substeps:
step S41, counting the sensitivity of human eyes to colors, and predetermining the gray value change of pixel points to be displayed according to the sensitivity of human eyes to colors;
for example, the sensitivity of human eyes to colors is white, yellow, blue and green in order from high to low, and in order to attract the attention of the eyes and then redisperse the attention of the eyes, the gray value of a pixel point to be displayed is predetermined to be changed into white → green → yellow → blue.
Step S42, continuously adjusting the gray value of the picture pixel point according to the predetermined gray value change of the pixel point to be displayed;
specifically, the gray value of the pixel point of the picture is continuously changed according to the preset gray value of the pixel point to be displayed, namely white → green → yellow → blue.
Step 144, playing the dynamic smile expression and guiding the facial expression to be naturally smile;
in fig. 3, a frame 6 is a schematic diagram of the transformation of the dynamic expression, and the facial expression of the photographed person is guided to tend to be naturally smiling by transforming the expression from the sad expression to the normal expression and then to the smile expression.
In the whole shooting process of this application, as long as the person of shooing stands or is just sitting in the face of shooting device, then look directly at the dynamic picture on the shooting device screen and can realize shooing, whole process is like watching TV by the person of shooing, and unconsciously can accomplish fast under natural state and shoot, and the natural expression of the eye that presents in the picture is smiling moreover.
as an optional embodiment, after shooting a plurality of photos, the shooting device of the application presents all the shot photos on the display screen, the shot person selects the photos through the touch screen, the shot person selects the required background color and the required certificate photo size, then the shot selected photos are subjected to green screen matting, the scratched portrait is fused with the background color selected by the shot person, the cropping is carried out according to the certificate photo size selected by the shot person, the automatic typesetting and outputting are carried out after the cropping is finished, and the whole certificate photo shooting process is completed;
as another optional embodiment, an image selection machine model for selecting an optimal photo is trained in advance in the shooting device of the application, the existing aesthetic big data is learned by adopting a neural network algorithm to obtain the machine model most conforming to modern aesthetics, the shooting device inputs the machine model after shooting a plurality of photos, an optimal photo is selected, then a portrait is extracted from the photo, the portrait is fused with a preselected background, and the fused image is cut into the certificate photo to be automatically typeset and output;
the specific operation of cutting the certificate photo is as follows: the method comprises the steps of obtaining a square 1 with a nose tip of a human face as a center based on a human face recognition algorithm, amplifying the square 1 by 2.5 times to obtain a square 2, taking the square 2 as the size of a photo-capture head, carrying out mask cutting processing on the square 2 according to a certificate photo-capture standard, and reserving an image in an effective area to obtain a certificate photo-capture.
Example two
The second embodiment of the application provides a device is shot to certificate photo, includes the photographic area that shell and shell surround. Dividing a fixed station area and a photographing area in the photographing area, and arranging a green curtain on the inner surface of the shell opposite to the photographing area; placing a photographing device in the photographing area; the photographing device comprises a controller, two display screens, a height sensor, photographing equipment, a photographing lamp assembly and photo printing equipment, wherein the controller is connected with the two display screens, the height sensor, the photographing equipment, the photographing lamp assembly and the photo printing equipment; the ground weight sensor is arranged on the fixed standing area and used for detecting whether a shot person stands in the detectable fixed standing area or not, and when the shot person is detected to enter the fixed standing area, a standing signal is transmitted to the shooting device in the shooting area.
The controller is configured to execute the method for capturing a certificate photo according to the first embodiment, as shown in fig. 4, and specifically includes a height measuring module 410, a height adjusting module 420, a starting module 430, a dynamic image playing module 440, a dynamic image adjusting module 450, a capturing module 460, a certificate photo output module 470, and a printing module 480;
the height measuring module 410 is used for responding to the in-position signal of the ground weight sensor and measuring the height of the shot person through a height sensor arranged at the top of the photographing device;
a height adjusting module 420 for adjusting the heights of the camera lamp assembly and the camera according to the height of the person to be photographed measured by the height measuring module 410, and aligning the camera height of the camera and the irradiation angle of the camera lamp assembly to the face of the person to be photographed;
a starting module 430 for starting the photographing lamp assembly and the photographing apparatus, wherein the starting time may be started after responding to a seating signal of the ground weight sensor, or may be started after adjusting the heights of the photographing lamp assembly and the photographing apparatus;
the dynamic picture playing module 440 is used for playing dynamic pictures simultaneously by a left screen and a right screen of the shooting device, respectively capturing the moving line positions of left and right eyeballs of a shot person and locking the positions of the two eyeballs;
specifically, the dynamic picture playing module 440 is configured to organize a dynamic picture, then divide the dynamic picture to obtain two sub-pictures, create two sets of processing threads in the shooting device, respectively, for processing the left and right screens, respectively, send the two sub-pictures to the two screens, and then render the two sub-pictures to the corresponding screens;
further, the dynamic picture playing module 440 is specifically configured to convert the organized dynamic picture into a sequence frame, store the sequence frame according to a dynamic sequence of the picture, set the number of virtual viewpoints to be rendered and the resolution of the output multi-view sequence frame, set an image segmentation parameter, split the current frame image into two left and right images according to the image segmentation parameter, set a visual range of the left and right images according to a distance between two screens, and perform rendering of the virtual viewpoints in the visual range of the left and right images according to the set number of virtual viewpoints to be rendered;
further, the eyeball position locking in the dynamic picture playing module 440 is specifically configured to obtain left and right face images of the person to be photographed, convert the images into grayscale images, perform binarization, construct a circular structural element, perform erosion and re-expansion operations on the images, perform de-drying processing on a central circular area, reduce the circular structural element, and extract the eyeball position from the de-dried images.
In addition, the shooting device also comprises a prompting module used for prompting that the head needs to be inclined leftwards or rightwards according to the prompting of the position of the eyeball so that the eyeball looks straight at the picture in parallel.
The dynamic picture adjusting module 450 is configured to dynamically adjust a screen picture, guide a photographed person to migrate a visual focus, and correct an eyeball position;
specifically, the dynamic picture adjusting module 450 is specifically configured to determine a center point position of the picture to be played and an area of the picture to be played according to the located eyeball position, adjust a position of a picture display area according to the eyeball position, attract eyeball migration, adjust a size, a color, and a brightness of the picture display area, disperse a visual focus, play a dynamic smile expression, and guide a facial expression to be naturally smiled.
The shooting module 460 is configured to detect the eyeball position and the facial form of the photographed person in real time, and start the continuous shooting mode to shoot a plurality of photos when it is detected that the eyeball position and the facial form of the photographed person conform to the shooting rule.
The certificate photo output module 470 is used for selecting photos, picking up the portrait by adopting a green curtain matting technology, fusing the portrait with a preselected background, and cutting the fused image into the certificate photo;
the certificate photo output module 470 is specifically configured to cut the fused image into a certificate photo, and specifically includes: obtaining a square 1 with a nose tip of a human face as a center based on a human face recognition algorithm, amplifying the square 1 by 2.5 times to obtain a square 2, taking the square 2 as the size of a photo-capture head, carrying out mask cutting processing on the square 2 according to a certificate photo-capture standard, and reserving an image in an effective area to obtain a certificate photo-capture;
in addition, the selected photo in the certificate photo output module 470 is specifically used for displaying all the taken photos on the display screen, the taken person selects the photos through the touch screen, the taken person selects the required background color and the required certificate photo size, and then the taken and selected photo is subjected to green screen matting; or an image selection machine model used for selecting the optimal photo is trained in advance in the shooting device, the existing aesthetic big data is learned by adopting a neural network algorithm to obtain the machine model most conforming to modern aesthetics, a plurality of shot photos are input into the machine model, and the optimal photo is selected for green-curtain matting.
And the printing module 480 is used for automatically typesetting and printing the cut certificate photo.
The technical effect that adopts the technical scheme of this application to reach is as follows:
(1) the automatic shooting is realized, and the problem that the human eyeball cannot be accurately aligned with the camera during the automatic shooting is solved;
(2) the shot pictures are natural in eyesight, the phenomenon of high light spots in eyeballs is solved, the expression is smiling, and the beauty of modern people is better met;
(3) the number of the shot pictures is large, and the satisfactory pictures can be selected according to a machine learning model or manual selection;
(4) the green curtain photographing is carried out, then the matting technology is adopted to matte the portrait, and any background color can be fused;
(5) the shooting process does not need the touch screen operation of the shooter, and the interaction is simple and clear.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (9)
1. An automatic identification photo shooting method is characterized by comprising the following steps:
monitoring the height of a shot person;
adjusting the shooting height of the shooting device according to the height of the shot person;
the left screen and the right screen of the shooting device synchronously play dynamic pictures, respectively capture the moving line positions of the left eyeball and the right eyeball of a shot person, and lock the positions of the two eyeballs;
dynamically adjusting a screen picture, guiding a shot person to migrate a visual focus, correcting the eyeball position and the face form, detecting the eyeball position and the face form of the shot person in real time, and taking a picture when the eyeball position and the face form of the shot person are detected to accord with a shooting rule;
picking up the portrait in the shot photo, fusing the portrait with a preselected background, and cutting the fused image into a certificate photo for automatic typesetting and outputting;
dynamically adjusting a screen picture, guiding a shot person to transfer a visual focus, and correcting the eyeball position and the face form, and specifically comprising the following substeps:
determining the central point position of the picture to be played and the area of the picture to be played according to the positioned eyeball position;
adjusting the position of the picture display area according to the eyeball position to attract the eyeball to move;
adjusting the size, color and brightness of a picture display area, and dispersing visual focus;
and playing dynamic smile expression to guide the facial expression to be smile naturally.
2. The automatic photographing method of the identification photo as claimed in claim 1, wherein a height sensor is provided at a top of the photographing device, a ground weight sensor is provided in a fixed station area which can be detected by the height sensor, and after the ground weight sensor detects that the person to be photographed stands in the fixed station area which can be detected, a photographing start signal is transmitted to the photographing device which monitors a height of the person through the height sensor.
3. The automatic taking method of the certificate photo as claimed in claim 1, characterized in that the eyeball position and the face shape of the person to be taken are detected in real time, when the eyeball position and the face shape of the person to be taken are detected to accord with the photographing rule, the continuous photographing mode is started, a plurality of photos are taken, and one photo is selected from the photos to perform green screen matting.
4. The method of claim 3, wherein selecting the picture from the plurality of pictures comprises:
displaying all shot photos on a display screen, selecting the photos through a touch screen by a shot person, selecting the needed background color and the needed certificate photo size by the shot person, and then performing green screen matting on the photos selected by the shot person;
or, training an image selection machine model for selecting the optimal photo in advance in the shooting device, learning the existing aesthetic big data by adopting a neural network algorithm to obtain the machine model most conforming to modern aesthetics, inputting a plurality of shot photos into the machine model, and selecting the optimal photo for green-curtain matting.
5. The automatic capturing method for credentials photo according to claim 1, wherein the left and right screens of the capturing device synchronously play the dynamic picture, specifically comprising the following sub-steps:
organizing dynamic pictures, converting the organized dynamic pictures into sequence frames, and storing the sequence frames according to the dynamic sequence of the pictures;
setting the number of virtual viewpoints to be rendered and the resolution of an output multi-view sequence frame;
setting image segmentation parameters, and splitting the current frame image into a left image and a right image according to the image segmentation parameters;
and setting the visual range of the left and right images according to the distance between the two screens, and rendering the virtual viewpoints in the visual range of the left and right images according to the number of the set virtual viewpoints to be rendered.
6. The automatic photographing method for the identification photo of claim 1, wherein the moving line positions of the left and right eyeballs of the photographed person are captured, and the positions of the two eyeballs are locked, comprising the following sub-steps:
the left screen and the right screen of the shooting device respectively acquire left and right face images of a shot person, convert the images into gray level images and then carry out binarization;
intercepting ROI images of eye regions in the left and right face images, performing corrosion re-expansion operation on the ROI images, and performing drying treatment on the corroded and re-expanded images;
the eyeball position is extracted from the image after the dryness is removed.
7. The automatic capturing method of a certificate photo as claimed in claim 1, characterized in that the fused image is cut into the certificate photo, specifically: the method comprises the steps of obtaining a square 1 with a nose tip of a human face as a center based on a human face recognition algorithm, amplifying the square 1 by 2.5 times to obtain a square 2, taking the square 2 as the size of a photo-capture head, carrying out mask cutting processing on the square 2 according to a certificate photo-capture standard, and reserving an image in an effective area to obtain a certificate photo-capture.
8. An automatic document camera apparatus for carrying out the automatic document camera method according to any one of claims 1 to 7, characterized in that the apparatus comprises a housing and a camera area enclosed by the housing; dividing a fixed station area and a photographing area in the photographing area, arranging a ground weight sensor on the fixed station area for detecting whether a photographed person enters or not, arranging a green curtain on the inner surface of the shell opposite to the photographing area, and placing a photographing device in the photographing area;
the device of shooing includes controller, two display screens, altitude sensor, shooting equipment, photography banks spare and photo printing equipment, and two display screens, altitude sensor, shooting equipment, photography banks spare and photo printing equipment are connected to the controller, and altitude sensor and photography banks spare set up at the device top of shooing, set up the interval and the people's eye distance matching of two display screens, set up the shooting equipment in the centre of two display screens.
9. An automatic certificate photo shooting device is characterized by comprising a height measuring module, a height adjusting module, a dynamic picture playing module, a dynamic picture adjusting module, a shooting module, a certificate photo output module and a printing module;
the height measuring module is used for detecting the height of the shot person;
the height adjusting module is used for adjusting the shooting height of the shooting device according to the height of the shot person measured by the height measuring module;
the dynamic picture playing module is used for simultaneously playing dynamic pictures by a left screen and a right screen of the shooting device, respectively capturing the moving line positions of left and right eyeballs of a shot person and locking the positions of the two eyeballs;
the dynamic picture adjusting module is used for dynamically adjusting a screen picture, guiding a shot person to migrate a visual focus and correcting the position of eyeballs;
the shooting module detects the eyeball position and the face shape of the shot person in real time and shoots when detecting that the eyeball position and the face shape of the shot person accord with the shooting rule;
the certificate photo output module is used for picking out the portrait in the shot photo, fusing the portrait with a preselected background and cutting the fused image into the certificate photo;
the printing module is used for automatically typesetting, printing and outputting the cut certificate photo;
the screen picture is dynamically adjusted, the shot person is guided to migrate the visual focus, and the eyeball position is corrected, and the method specifically comprises the following steps:
determining the central point position of the picture to be played and the area of the picture to be played according to the positioned eyeball position;
adjusting the position of the picture display area according to the eyeball position to attract the eyeball to move;
adjusting the size, color and brightness of a picture display area, and dispersing visual focus;
and playing dynamic smile expression to guide the facial expression to be smile naturally.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910858868.8A CN110536044B (en) | 2019-09-11 | 2019-09-11 | Automatic certificate photo shooting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910858868.8A CN110536044B (en) | 2019-09-11 | 2019-09-11 | Automatic certificate photo shooting method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110536044A CN110536044A (en) | 2019-12-03 |
| CN110536044B true CN110536044B (en) | 2022-02-22 |
Family
ID=68668201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910858868.8A Active CN110536044B (en) | 2019-09-11 | 2019-09-11 | Automatic certificate photo shooting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110536044B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113035359A (en) * | 2021-05-06 | 2021-06-25 | 青岛通产智能科技股份有限公司 | Multifunctional self-service mini-car management station |
| CN113784039B (en) * | 2021-08-03 | 2023-07-11 | 北京达佳互联信息技术有限公司 | Head portrait processing method, head portrait processing device, electronic equipment and computer readable storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001186323A (en) * | 1999-12-24 | 2001-07-06 | Fuji Photo Film Co Ltd | Identification photograph system and picture on processing method |
| CN101216881B (en) * | 2007-12-28 | 2011-07-06 | 北京中星微电子有限公司 | A method and device for automatic image acquisition |
| CN207399348U (en) * | 2017-09-18 | 2018-05-22 | 东斓视觉科技发展（北京）有限公司 | The self-service collecting device of certificate photo |
| JP2019061576A (en) * | 2017-09-27 | 2019-04-18 | 大日本印刷株式会社 | Automatic identification photo machine and electronic application system |
| CN209219622U (en) * | 2018-08-01 | 2019-08-09 | 杭州云拍科技有限公司 | A kind of adjustable seat device of intelligence certificate photo capture apparatus |
| CN110191280A (en) * | 2019-05-24 | 2019-08-30 | Oppo广东移动通信有限公司 | The photographic method and Related product shown based on cover board |
-
2019
- 2019-09-11 CN CN201910858868.8A patent/CN110536044B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110536044A (en) | 2019-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108427503B (en) | Human eye tracking method and human eye tracking device | |
| CN107818305B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| US10855909B2 (en) | Method and apparatus for obtaining binocular panoramic image, and storage medium | |
| CN107766831B (en) | Image processing method, image processing device, mobile terminal and computer-readable storage medium | |
| US9692964B2 (en) | Modification of post-viewing parameters for digital images using image region or feature information | |
| US8717352B2 (en) | Tracing-type stereo display apparatus and tracing-type stereo display method | |
| CN108537155B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| JP6165459B2 (en) | Method for correcting user's line of sight in video, machine-readable storage medium, and portable terminal | |
| JP4865038B2 (en) | Digital image processing using face detection and skin tone information | |
| JP3761059B2 (en) | Method and apparatus for detecting human face and observer tracking display | |
| US20180104106A1 (en) | A system and method for displaying a video image | |
| CN103369214A (en) | An image acquiring method and an image acquiring apparatus | |
| CN104317385A (en) | Gesture identification method and system | |
| JP2020526735A (en) | Pupil distance measurement method, wearable eye device and storage medium | |
| CN110536044B (en) | Automatic certificate photo shooting method and device | |
| CN115599219B (en) | Eye protection control method, system and equipment for display screen and storage medium | |
| CN103679767A (en) | Image generation apparatus and image generation method | |
| KR20170011362A (en) | Imaging apparatus and method for the same | |
| CN112183200A (en) | Eye movement tracking method and system based on video image | |
| CN109493293A (en) | A kind of image processing method and device, display equipment | |
| JPWO2022074865A5 (en) | LIFE DETECTION DEVICE, CONTROL METHOD, AND PROGRAM | |
| US9323981B2 (en) | Face component extraction apparatus, face component extraction method and recording medium in which program for face component extraction method is stored | |
| CN116453198B (en) | Sight line calibration method and device based on head posture difference | |
| CN107911609B (en) | Image processing method, image processing device, computer-readable storage medium and electronic equipment | |
| CN106846302B (en) | Detection method for correctly taking tool and examination table based on method |
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 |