CN102917232A - Face recognition based 3D (three dimension) display self-adaptive adjusting method and face recognition based 3D display self-adaptive adjusting device - Google Patents
Face recognition based 3D (three dimension) display self-adaptive adjusting method and face recognition based 3D display self-adaptive adjusting device Download PDFInfo
- Publication number
- CN102917232A CN102917232A CN2012104075417A CN201210407541A CN102917232A CN 102917232 A CN102917232 A CN 102917232A CN 2012104075417 A CN2012104075417 A CN 2012104075417A CN 201210407541 A CN201210407541 A CN 201210407541A CN 102917232 A CN102917232 A CN 102917232A
- Authority
- CN
- China
- Prior art keywords
- face
- people
- image
- value
- point
- 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 25
- 230000001815 facial effect Effects 0.000 claims description 51
- 230000003044 adaptive effect Effects 0.000 claims description 20
- 230000001105 regulatory effect Effects 0.000 claims description 13
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 22
- 230000009466 transformation Effects 0.000 abstract 1
- 230000008859 change Effects 0.000 description 6
- 230000006872 improvement Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a face recognition based 3D (three dimension) display self-adaptive adjusting method and a face recognition based 3D display self-adaptive adjusting device. The face recognition 3D display self-adaptive adjusting method includes: acquiring a picture taken by a camera and analyzing a face picture from the taken picture; determining position coordinates and distance coordinates of a face according to the face picture; searching a zoom value parameter reference table according to the face position coordinates and determining a zoom value; searching a field depth parameter reference table according to the face distance coordinates and determining a field depth value; and configuring display parameters of a display screen and adjusting display pictures of the display screen according to the zoom value and the field depth value. By the face recognition technology, the zoom value and the 3D field depth value can be dynamically adjusted, an observer can optionally observe from any positions, observation effect is not affected by limit of positions, and picture transformation and distortion caused by the fact that the position of the observer deviates from the central position of display equipment are avoided.
Description
Technical field
The present invention relates to 3D Display Technique field, the 3D that specially refers to based on recognition of face shows adaptive regulation method and device.
Background technology
Along with the development of 3D technology, the 3D technology more and more is applied in television set or the other display equipment.But, existing display device with 3D display effect, in order to reach best display effect, usually need to provide relative angle and viewing distance between beholder and the display device, so not only having limited to the position that the user watches can not arbitrarily change, and causes the Product Experience sense poor.In addition, when the beholder departed from the center of display device, problem on deformation appearred in the display frame meeting, can be larger near beholder's part picture, can be less away from beholder's part picture, and cause the display frame distortion.
Summary of the invention
Main purpose of the present invention is not subjected to the viewing location restriction for providing a kind of, avoids the 3D based on recognition of face of distortion to show adaptive regulation method and device.
The present invention proposes a kind of 3D based on recognition of face and shows adaptive regulation method, comprises step:
Obtain the image that camera is taken, from the image of described shooting, resolve facial image;
According to described facial image, determine position coordinates and the range coordinate of people's face;
Search the scale value parameter table of comparisons according to described people's face position coordinates, determine scale value; Search the depth of field value parameter table of comparisons according to described people's face range coordinate, determine depth of field value;
According to described scale value and depth of field value, configure the display parameters of described display screen, adjust the display frame of described display screen.
Preferably, described according to facial image, determine that the step of the range coordinate of people's face specifically comprises:
According to described facial image, obtain the radius value of described facial image;
More described radius value and default radius standard value are big or small, determine the range coordinate of people's face.
Preferably, the step of determining described default radius standard value comprises:
When the distance between camera and the people's face is predeterminable range, obtain the standard picture that camera is taken;
From described standard picture, parse the standard faces image that is positioned on the predeterminable range coordinate;
According to described standard faces image, obtain the radius value of described standard faces image, be defined as default radius standard value.
Preferably, described according to facial image, determine that the step of the position coordinates of people's face specifically comprises:
According to described facial image, determine the central point of people's face;
When described central point is one, determine the position coordinates of described central point behaviour face.
Preferably, described according to facial image, determine that the step of the central point of people's face also comprises afterwards:
When described central point when being a plurality of, consist of the upper level triangle as the summit take the center of the image of adjacent two central points and described shooting, determine upper level barycenter oftriangle point;
When described upper level barycenter oftriangle point is one, determine that described upper level barycenter oftriangle point is the position coordinates of people's face;
When described upper level barycenter oftriangle point when a plurality of, take the center of the image of adjacent two upper level barycenter oftriangle points and described shooting as summit formation next stage triangle, determine next stage barycenter oftriangle point, circulate according to this.
The present invention also proposes a kind of 3D based on recognition of face and shows self-adaptive regulating, comprising:
Image collection module is used for obtaining the image that camera is taken, and resolves facial image from the image of described shooting;
The coordinate determination module is used for according to described facial image, determines position coordinates and the range coordinate of people's face;
Parameter adjustment module is used for searching the scale value parameter table of comparisons according to described people's face position coordinates, determines scale value; Search the depth of field value parameter table of comparisons according to described people's face range coordinate, determine depth of field value;
Show configuration module, be used for according to described scale value and depth of field value, configure the display parameters of described display screen, adjust the display frame of described display screen.
Preferably, described coordinate determination module specifically comprises the range coordinate submodule, is used for according to described facial image, obtains the radius value of described facial image; More described radius value and default radius standard value are big or small, determine the range coordinate of people's face.
Preferably, described image collection module also is used for, and when the distance between camera and the people's face is predeterminable range, obtains the standard picture that camera is taken; From described standard picture, parse the standard faces image that is positioned on the predeterminable range coordinate;
Described range coordinate submodule also is used for, and according to described standard faces image, obtains the radius value of described standard faces image, is defined as default radius standard value.
Preferably, described coordinate determination module specifically comprises the position coordinates submodule, is used for according to described facial image, determines the central point of people's face; When described central point is one, determine the position coordinates of described central point behaviour face.
Preferably, described position coordinates submodule also is used for:
When described central point when being a plurality of, consist of the upper level triangle as the summit take the center of the image of adjacent two central points and described shooting, determine upper level barycenter oftriangle point;
When described upper level barycenter oftriangle point is one, determine that described upper level barycenter oftriangle point is the position coordinates of people's face;
When described upper level barycenter oftriangle point when a plurality of, take the center of the image of adjacent two upper level barycenter oftriangle points and described shooting as summit formation next stage triangle, determine next stage barycenter oftriangle point, circulate according to this.
The present invention adopts face recognition technology, the scale value of dynamic adjustments display frame and 3D depth of field value, the beholder can arbitrarily change viewing location, and its viewing effect is not subjected to the impact of position limitation, the figure deformation and the distortion that cause during the center that can avoid departing from display device because of the beholder.
Description of drawings
Fig. 1 is the flow chart that the 3D that the present invention is based on recognition of face shows the first embodiment of adaptive regulation method;
Fig. 2 is the flow chart that the 3D that the present invention is based on recognition of face shows the second embodiment of adaptive regulation method;
Fig. 3 is the flow chart that the 3D that the present invention is based on recognition of face shows the 3rd embodiment of adaptive regulation method;
Fig. 4 is the flow chart that the 3D that the present invention is based on recognition of face shows the 4th embodiment of adaptive regulation method;
Fig. 5 is the flow chart that the 3D that the present invention is based on recognition of face shows the 5th embodiment of adaptive regulation method;
Fig. 6 is the structural representation that the 3D that the present invention is based on recognition of face shows the first embodiment of self-adaptive regulating;
Fig. 7 is the structural representation that the 3D that the present invention is based on recognition of face shows the second embodiment of self-adaptive regulating;
Fig. 8 is the structural representation that the 3D that the present invention is based on recognition of face shows the 3rd embodiment of self-adaptive regulating.
The realization of the object of the invention, functional characteristics and advantage are described further with reference to accompanying drawing in connection with embodiment.
Embodiment
Should be appreciated that specific embodiment described herein only in order to explain the present invention, is not intended to limit the present invention.
As shown in Figure 1, Fig. 1 is the flow chart that the 3D that the present invention is based on recognition of face shows the first embodiment of adaptive regulation method.The 3D based on recognition of face that the present embodiment is mentioned shows that adaptive regulation method comprises:
Step S10 obtains the image that camera is taken, and resolves facial image from the image of taking;
The present embodiment can be applicable to possess the display device of 3D display effect, for example, 3D TV based on the Android system, in the time of before the beholder stands in display panel, display device passes through the image at camera BR scene, and in conjunction with the recognition of face database, extract the face characteristic in the image of taking, for example, adopt OpenCV(Open Source Computer Vision Library, cross-platform computer vision storehouse) face identification functions that provides.
Step S20 according to facial image, determines position coordinates and the range coordinate of people's face;
In order to determine the concrete coordinate of people's face, can determine by simple two-dimensional coordinate position coordinates and the range coordinate of people's face, for example, two-dimension picture obtains the relative position of people's face and screen, judge the distance of people's face by people's face picture size, or detect the distance of people's face and screen by sensor.In addition, can also adopt the tri-dimensional picture style of shooting, obtain people's face at three-dimensional three-dimensional coordinate, for example, at whole floor a plurality of cameras are installed, are obtained the positional information of people's face before display screen, the distance, people's face that comprises people's face and display screen is to angle position of screen etc.
Step S30 searches the scale value parameter table of comparisons according to people's face position coordinates, determines scale value; Search the depth of field value parameter table of comparisons according to people's face range coordinate, determine depth of field value;
By physical location and the range coordinate of people's face, search the parameter table of comparisons, obtain the optimum value of scale value and 3D depth of field value under present case, and by system interface is set and refreshes display effect, to reach the optimum efficiency of watching.Wherein, regulate scale value by people's face position coordinates, the beholder can arbitrarily change viewing location, and its viewing effect is not subjected to the impact of position limitation; Regulate depth of field value by people's face range coordinate, the figure deformation and the distortion that cause during the center that can avoid departing from display device because of the beholder.In addition, the scale value parameter table of comparisons and the dark value parameter table of comparisons can carry out dynamic adjustments according to the corresponding relation that pre-establishes, this corresponding relation considers the factors such as home environment and market demo environment and formulates, and through the corresponding relation of the subjective effect the best after the test repeatedly.
Step S40, according to scale value and depth of field value, the display parameters of configuration display screen are adjusted the display frame of display screen.
The present embodiment adopts face recognition technology, obtain position coordinates and the range coordinate of people's face, the scale value of dynamic adjustments display frame and 3D depth of field value, the beholder can arbitrarily change viewing location, its viewing effect is not subjected to the impact of position limitation, the figure deformation and the distortion that cause during the center that can avoid departing from display device because of the beholder.
As shown in Figure 2, Fig. 2 is the flow chart that the 3D that the present invention is based on recognition of face shows the second embodiment of adaptive regulation method.The present embodiment is take embodiment illustrated in fig. 1 as the basis, to the detailed description of the step of determining people's face range coordinate.Wherein, step S20 specifically comprises:
Step S211 according to facial image, obtains the radius value of facial image;
Step S212, relatively radius value and default radius standard value are big or small, determine the range coordinate of people's face.
The present embodiment is approximately circular with facial image, and relatively the radius value of the facial image of current shooting and default radius standard value size illustrates the far and near relation of distance between user and the television set.For example, default radius standard value is the 20-30 pixel, and be normal viewing distance this moment, and the optimum value of 3D depth of field value is 15 in this scope.When radius value during less than 20 pixel, illustrate that user and television set are distant, so 3D depth of field value also should increase; Otherwise, when radius value greater than 30 pixel the time, illustrating that user and television set are nearer, 3D depth of field value should reduce.Range coordinate according to people's face is determined best 3D depth of field value, all can see best image effect to reach the user in the different distance scope.
As shown in Figure 3, Fig. 3 is the flow chart that the 3D that the present invention is based on recognition of face shows the 3rd embodiment of adaptive regulation method.The present embodiment, specifically comprises definite detailed description of presetting the step of radius standard value take embodiment illustrated in fig. 2 as the basis:
Step S51 when the distance between camera and the people's face is predeterminable range, obtains the standard picture that camera is taken;
Step S52 parses the standard faces image that is positioned on the predeterminable range coordinate from standard picture;
Step S53 according to the standard faces image, obtains the radius value of standard faces image, is defined as default radius standard value.
But definite training in advance of default radius standard value in the present embodiment, for example, one family has two kinsfolks, comprise an adult and a child, because everyone face feature is different, can be before watching TV, gather the facial image on the predeterminable range coordinate, for example, can with over against the position of 3 meters of video screens as the predeterminable range coordinate, each kinsfolk is sitting in respectively the position of predeterminable range coordinate, takes facial image by camera, obtains each kinsfolk's standard faces image and default radius standard value, when watching TV, can identify according to the facial image of the reality that photographs this kinsfolk's identity, or judge identity according to login account, for example, it is current that watch TV is child among this kinsfolk, then people's face radius of this child's reality and his default radius standard value are compared, determine people's face range coordinate of this child, and then the optimum distance effect that is suitable for this child is adjusted in display frame.
As shown in Figure 4, Fig. 4 is the flow chart that the 3D that the present invention is based on recognition of face shows the 4th embodiment of adaptive regulation method.The present embodiment is take embodiment illustrated in fig. 1 as the basis, to the detailed description of the step of determining people's face position coordinates.Wherein, step S20 specifically comprises:
Step S221 according to facial image, determines the central point of people's face;
Step S222 when central point is one, determines the position coordinates of central point behaviour face.
The situation that the present embodiment is watched the 3D picture for a people can be approximately facial image circle or polygon, and the center of circle or polygonal center namely are the central point of people's face, determines to be people's face position coordinates.When adjusting depth of field value, when facial image is positioned at the centre position of photographic images, its position coordinates is in a critical field, for example, the lower left corner of photographic images is initial point, the value of its two-dimensional coordinate x axle is 0, the value of lower-right most point two-dimensional coordinate x axle is 1280, then the value of the two-dimensional coordinate x axle in centre position is 640, when scope between 0-400 of the value of the two-dimensional coordinate x axle of people's face position coordinates in photographic images, the relative television set of viewing location that the user then is described is taken back, scale value in the lateral resolution 400-800 scope of display frame should be increased by 30%, scale value in the lateral resolution 800-1280 scope increases by 60%, and anamorphose improves, and effectively avoids the vision deviation and the distortion that cause because departing from the display screen center.
As shown in Figure 5, Fig. 5 is the flow chart that the 3D that the present invention is based on recognition of face shows the 5th embodiment of adaptive regulation method.The present embodiment has increased the step of determining a plurality of people's face position coordinateses on basis embodiment illustrated in fig. 4.Wherein, step S20 specifically comprises:
Step S231 according to facial image, determines the central point of people's face;
Step S232 judges whether central point is one; If so, execution in step S233 then; If not, execution in step S234 then;
Step S233 determines the position coordinates of central point behaviour face;
Step S234 consists of i level triangle take the center of the image of adjacent two central points and shooting as the summit, determine i level barycenter oftriangle point;
Step S235 judges whether i level barycenter oftriangle point is one; If so, execution in step S236 then; If not, execution in step S237 then;
Step S236 determines that i level barycenter oftriangle point is the position coordinates of people's face;
Step S237 consists of i+1 level triangle take the center of adjacent two i level barycenter oftriangle points and the image taken as the summit, determine i+1 level barycenter oftriangle point, makes i+1=i, returns step S235.
In the present embodiment, when having a plurality of users to watch simultaneously the 3D content in the picture, at first be the center point coordinate that obtains each user people's face, form a plurality of triangles with center and each central point of the image taken, calculate respectively each barycenter oftriangle.When two users watched simultaneously, the focus point that then obtains this moment was 1; When number of users during greater than two, then focus point is greater than 1, each barycenter oftriangle point coordinates that will obtain again reorganizes and is new triangle, continue to calculate focus point, until finally obtain a focus point, this focus point is the reference point coordinate that the most suitable each user who obtains after comprehensive each user's viewing location watches 3D effect, makes many people watch the display effect of 3D picture to obtain remarkable improvement.
As shown in Figure 6, Fig. 6 is the structural representation that the 3D that the present invention is based on recognition of face shows the first embodiment of self-adaptive regulating.The 3D based on recognition of face that the present embodiment is mentioned shows self-adaptive regulating, comprising:
Coordinate determination module 20 is used for according to facial image, determines position coordinates and the range coordinate of people's face;
The present embodiment can be applicable to possess the display device of 3D display effect, for example, 3D TV based on the Android system, in the time of before the beholder stands in display panel, display device passes through the image at camera BR scene, and in conjunction with the recognition of face database, extract the face characteristic in the image of taking, for example, adopt OpenCV(Open Source Computer Vision Library, cross-platform computer vision storehouse) face identification functions that provides.In order to determine the concrete coordinate of people's face, can determine by simple two-dimensional coordinate position coordinates and the range coordinate of people's face, for example, two-dimension picture obtains the relative position of people's face and screen, judge the distance of people's face by people's face picture size, or detect the distance of people's face and screen by sensor.In addition, can also adopt the tri-dimensional picture style of shooting, obtain people's face at three-dimensional three-dimensional coordinate, for example, at whole floor a plurality of cameras are installed, are obtained the positional information of people's face before display screen, the distance, people's face that comprises people's face and display screen is to angle position of screen etc.By physical location and the range coordinate of people's face, search the parameter table of comparisons, obtain the optimum value of scale value and 3D depth of field value under present case, and by system interface is set and refreshes display effect, to reach the optimum efficiency of watching.Wherein, regulate scale value by people's face position coordinates, the beholder can arbitrarily change viewing location, and its viewing effect is not subjected to the impact of position limitation; Regulate depth of field value by people's face range coordinate, the figure deformation and the distortion that cause during the center that can avoid departing from display device because of the beholder.In addition, the scale value parameter table of comparisons and the dark value parameter table of comparisons can carry out dynamic adjustments according to the corresponding relation that pre-establishes, this corresponding relation considers the factors such as home environment and market demo environment and formulates, and through the corresponding relation of the subjective effect the best after the test repeatedly.The present embodiment adopts face recognition technology, obtain position coordinates and the range coordinate of people's face, the scale value of dynamic adjustments display frame and 3D depth of field value, the beholder can arbitrarily change viewing location, its viewing effect is not subjected to the impact of position limitation, the figure deformation and the distortion that cause during the center that can avoid departing from display device because of the beholder.
As shown in Figure 7, Fig. 7 is the structural representation that the 3D that the present invention is based on recognition of face shows the second embodiment of self-adaptive regulating.The present embodiment take embodiment illustrated in fig. 6 as the basis, to the detailed description of the first embodiment of coordinate determination module.Coordinate determination module 20 specifically comprises range coordinate submodule 21, is used for according to facial image, obtains the radius value of facial image; Relatively radius value and default radius standard value are big or small, determine the range coordinate of people's face.
The present embodiment is approximately circular with facial image, and relatively the radius value of the facial image of current shooting and default radius standard value size illustrates the far and near relation of distance between user and the television set.For example, default radius standard value is the 20-30 pixel, and be normal viewing distance this moment, and the optimum value of 3D depth of field value is 15 in this scope.When radius value during less than 20 pixel, illustrate that user and television set are distant, so 3D depth of field value also should increase; Otherwise, when radius value greater than 30 pixel the time, illustrating that user and television set are nearer, 3D depth of field value should reduce.Range coordinate according to people's face is determined best 3D depth of field value, all can see best image effect to reach the user in the different distance scope.
In the embodiment of the invention, image collection module 10 also is used for, and when the distance between camera and the people's face is predeterminable range, obtains the standard picture that camera is taken; From standard picture, parse the standard faces image that is positioned on the predeterminable range coordinate;
Range coordinate submodule 21 also is used for, and according to the standard faces image, obtains the radius value of standard faces image, is defined as default radius standard value.
But definite training in advance of default radius standard value in the present embodiment, for example, one family has two kinsfolks, comprise an adult and a child, because everyone face feature is different, can be before watching TV, gather the facial image on the predeterminable range coordinate, for example, can with over against the position of 3 meters of video screens as the predeterminable range coordinate, each kinsfolk is sitting in respectively the position of predeterminable range coordinate, takes facial image by camera, obtains each kinsfolk's standard faces image and default radius standard value, when watching TV, can identify according to the facial image of the reality that photographs this kinsfolk's identity, or judge identity according to login account, for example, it is current that watch TV is child among this kinsfolk, then people's face radius of this child's reality and his default radius standard value are compared, determine people's face range coordinate of this child, and then the optimum distance effect that is suitable for this child is adjusted in display frame.
As shown in Figure 8, Fig. 8 is the structural representation that the 3D that the present invention is based on recognition of face shows the 3rd embodiment of self-adaptive regulating.The present embodiment take embodiment illustrated in fig. 6 as the basis, to the detailed description of the second embodiment of coordinate determination module.Coordinate determination module 20 specifically comprises position coordinates submodule 22, is used for according to facial image, determines the central point of people's face; When central point is one, determine the position coordinates of central point behaviour face.
The situation that the present embodiment is watched the 3D picture for a people can be approximately facial image circle or polygon, and the center of circle or polygonal center namely are the central point of people's face, determines to be people's face position coordinates.When adjusting depth of field value, when facial image is positioned at the centre position of photographic images, its position coordinates is in a critical field, for example, the lower left corner of photographic images is initial point, the value of its two-dimensional coordinate x axle is 0, the value of lower-right most point two-dimensional coordinate x axle is 1280, then the value of the two-dimensional coordinate x axle in centre position is 640, when scope between 0-400 of the value of the two-dimensional coordinate x axle of people's face position coordinates in photographic images, the relative television set of viewing location that the user then is described is taken back, scale value in the lateral resolution 400-800 scope of display frame should be increased by 30%, scale value in the lateral resolution 800-1280 scope increases by 60%, and anamorphose improves, and effectively avoids the vision deviation and the distortion that cause because departing from the display screen center.
In the embodiment of the invention, position coordinates submodule 22 also is used for:
When central point when being a plurality of, consist of the upper level triangle as the summit take the center of the image of adjacent two central points and shooting, determine upper level barycenter oftriangle point;
When upper level barycenter oftriangle point is one, determine that upper level barycenter oftriangle point is the position coordinates of people's face;
When upper level barycenter oftriangle point when a plurality of, consist of the next stage triangle as the summit take the center of adjacent two upper level barycenter oftriangle points and the image taken, determine next stage barycenter oftriangle point, circulate according to this.
In the present embodiment, when having a plurality of users to watch simultaneously the 3D content in the picture, at first be the center point coordinate that obtains each user people's face, form a plurality of triangles with center and each central point of the image taken, calculate respectively each barycenter oftriangle.When two users watched simultaneously, the focus point that then obtains this moment was 1; When number of users during greater than two, then focus point is greater than 1, each barycenter oftriangle point coordinates that will obtain again reorganizes and is new triangle, continue to calculate focus point, until finally obtain a focus point, this focus point is the reference point coordinate that the most suitable each user who obtains after comprehensive each user's viewing location watches 3D effect, makes many people watch the display effect of 3D picture to obtain remarkable improvement.
The above only is the preferred embodiments of the present invention; be not so limit claim of the present invention; every equivalent structure or equivalent flow process conversion that utilizes specification of the present invention and accompanying drawing content to do; or directly or indirectly be used in other relevant technical fields, all in like manner be included in the scope of patent protection of the present invention.
Claims (10)
1. the 3D based on recognition of face shows adaptive regulation method, it is characterized in that, comprises step:
Obtain the image that camera is taken, from the image of described shooting, resolve facial image;
According to described facial image, determine position coordinates and the range coordinate of people's face;
Search the scale value parameter table of comparisons according to described people's face position coordinates, determine scale value; Search the depth of field value parameter table of comparisons according to described people's face range coordinate, determine depth of field value;
According to described scale value and depth of field value, configure the display parameters of described display screen, adjust the display frame of described display screen.
2. the 3D based on recognition of face according to claim 1 shows adaptive regulation method, it is characterized in that, and is described according to facial image, determines that the step of the range coordinate of people's face specifically comprises:
According to described facial image, obtain the radius value of described facial image;
More described radius value and default radius standard value are big or small, determine the range coordinate of people's face.
3. the 3D based on recognition of face according to claim 2 shows adaptive regulation method, it is characterized in that, determines that the step of described default radius standard value comprises:
When the distance between camera and the people's face is predeterminable range, obtain the standard picture that camera is taken;
From described standard picture, parse the standard faces image that is positioned on the predeterminable range coordinate;
According to described standard faces image, obtain the radius value of described standard faces image, be defined as default radius standard value.
4. according to claim 1 to 3 each described 3D demonstration adaptive regulation methods based on recognition of face, it is characterized in that, described according to facial image, determine that the step of the position coordinates of people's face specifically comprises:
According to described facial image, determine the central point of people's face;
When described central point is one, determine the position coordinates of described central point behaviour face.
5. the 3D based on recognition of face according to claim 4 shows adaptive regulation method, it is characterized in that, and is described according to facial image, determines that the step of the central point of people's face also comprises afterwards:
When described central point when being a plurality of, consist of the upper level triangle as the summit take the center of the image of adjacent two central points and described shooting, determine upper level barycenter oftriangle point;
When described upper level barycenter oftriangle point is one, determine that described upper level barycenter oftriangle point is the position coordinates of people's face;
When described upper level barycenter oftriangle point when a plurality of, take the center of the image of adjacent two upper level barycenter oftriangle points and described shooting as summit formation next stage triangle, determine next stage barycenter oftriangle point, circulate according to this.
6. the 3D based on recognition of face shows self-adaptive regulating, it is characterized in that, comprising:
Image collection module is used for obtaining the image that camera is taken, and resolves facial image from the image of described shooting;
The coordinate determination module is used for according to described facial image, determines position coordinates and the range coordinate of people's face;
Parameter adjustment module is used for searching the scale value parameter table of comparisons according to described people's face position coordinates, determines scale value; Search the depth of field value parameter table of comparisons according to described people's face range coordinate, determine depth of field value;
Show configuration module, be used for according to described scale value and depth of field value, configure the display parameters of described display screen, adjust the display frame of described display screen.
7. the 3D based on recognition of face according to claim 6 shows self-adaptive regulating, it is characterized in that, described coordinate determination module specifically comprises the range coordinate submodule, is used for according to described facial image, obtains the radius value of described facial image; More described radius value and default radius standard value are big or small, determine the range coordinate of people's face.
8. the 3D based on recognition of face according to claim 7 shows self-adaptive regulating, it is characterized in that, described image collection module also is used for, and when the distance between camera and the people's face is predeterminable range, obtains the standard picture that camera is taken; From described standard picture, parse the standard faces image that is positioned on the predeterminable range coordinate;
Described range coordinate submodule also is used for, and according to described standard faces image, obtains the radius value of described standard faces image, is defined as default radius standard value.
9. according to claim 6 to 8 each described 3D demonstration self-adaptive regulatings based on recognition of face, it is characterized in that, described coordinate determination module specifically comprises the position coordinates submodule, is used for according to described facial image, determines the central point of people's face; When described central point is one, determine the position coordinates of described central point behaviour face.
10. the 3D based on recognition of face according to claim 9 shows self-adaptive regulating, it is characterized in that, described position coordinates submodule also is used for:
When described central point when being a plurality of, consist of the upper level triangle as the summit take the center of the image of adjacent two central points and described shooting, determine upper level barycenter oftriangle point;
When described upper level barycenter oftriangle point is one, determine that described upper level barycenter oftriangle point is the position coordinates of people's face;
When described upper level barycenter oftriangle point when a plurality of, take the center of the image of adjacent two upper level barycenter oftriangle points and described shooting as summit formation next stage triangle, determine next stage barycenter oftriangle point, circulate according to this.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210407541.7A CN102917232B (en) | 2012-10-23 | 2012-10-23 | Face recognition based 3D (three dimension) display self-adaptive adjusting method and face recognition based 3D display self-adaptive adjusting device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210407541.7A CN102917232B (en) | 2012-10-23 | 2012-10-23 | Face recognition based 3D (three dimension) display self-adaptive adjusting method and face recognition based 3D display self-adaptive adjusting device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102917232A true CN102917232A (en) | 2013-02-06 |
| CN102917232B CN102917232B (en) | 2014-12-24 |
Family
ID=47615441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210407541.7A Active CN102917232B (en) | 2012-10-23 | 2012-10-23 | Face recognition based 3D (three dimension) display self-adaptive adjusting method and face recognition based 3D display self-adaptive adjusting device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102917232B (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103760980A (en) * | 2014-01-21 | 2014-04-30 | Tcl集团股份有限公司 | Display method, system and device for conducting dynamic adjustment according to positions of two eyes |
| CN103986959A (en) * | 2014-05-08 | 2014-08-13 | 海信集团有限公司 | Automatic parameter adjusting method and device of smart television equipment |
| CN104020842A (en) * | 2013-03-01 | 2014-09-03 | 联想(北京)有限公司 | Display method and device and electronic device |
| CN104125395A (en) * | 2014-05-30 | 2014-10-29 | 深圳市中兴移动通信有限公司 | Method and device for realizing automatic shooting |
| CN104410882A (en) * | 2014-11-28 | 2015-03-11 | 苏州福丰科技有限公司 | Smart television with three-dimensional face scanning function |
| CN104519331A (en) * | 2013-09-27 | 2015-04-15 | 联想(北京)有限公司 | Data processing method and electronic device |
| CN104539923A (en) * | 2014-12-03 | 2015-04-22 | 深圳市亿思达科技集团有限公司 | Depth-of-field adaptive holographic display method and device thereof |
| CN104883524A (en) * | 2015-06-02 | 2015-09-02 | 阔地教育科技有限公司 | Method and system for automatically tracking and shooting moving object in online class |
| CN105405104A (en) * | 2015-09-24 | 2016-03-16 | 华为技术有限公司 | Method and apparatus for face image correction |
| CN105592367A (en) * | 2015-12-23 | 2016-05-18 | 青岛海信电器股份有限公司 | Image display parameter adjusting method and system |
| CN105681861A (en) * | 2016-03-04 | 2016-06-15 | 青岛海信电器股份有限公司 | Adjusting method and system for display subtitle of terminal |
| CN105807952A (en) * | 2016-03-07 | 2016-07-27 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN106127163A (en) * | 2016-06-29 | 2016-11-16 | 深圳大学 | A kind of monocular ranging localization detecting system and detection method thereof |
| CN106303565A (en) * | 2016-08-12 | 2017-01-04 | 广州华多网络科技有限公司 | The image quality optimization method of net cast and device |
| CN106454315A (en) * | 2016-10-26 | 2017-02-22 | 深圳市魔眼科技有限公司 | Adaptive virtual view-to-stereoscopic view method and apparatus, and display device |
| CN106774937A (en) * | 2017-01-13 | 2017-05-31 | 宇龙计算机通信科技(深圳)有限公司 | Image interactive method and its device in a kind of augmented reality |
| WO2017088472A1 (en) * | 2015-11-26 | 2017-06-01 | 乐视控股（北京）有限公司 | Video playing processing method and device |
| CN106843821A (en) * | 2015-12-07 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | The method and apparatus of adjust automatically screen |
| CN106855744A (en) * | 2016-12-30 | 2017-06-16 | 维沃移动通信有限公司 | A kind of screen display method and mobile terminal |
| CN106919246A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | The display methods and device of a kind of application interface |
| CN107147897A (en) * | 2017-06-09 | 2017-09-08 | 西安闻泰电子科技有限公司 | Method for displaying image and device |
| WO2017177616A1 (en) * | 2016-04-15 | 2017-10-19 | 中兴通讯股份有限公司 | Face recognition method and device, and picture displaying method and device |
| CN107368491A (en) * | 2016-05-12 | 2017-11-21 | 富泰华工业（深圳）有限公司 | Making video system and method |
| CN107748656A (en) * | 2017-10-19 | 2018-03-02 | 广东欧珀移动通信有限公司 | A kind of picture display process, device, terminal and storage medium |
| CN107870708A (en) * | 2016-09-27 | 2018-04-03 | 富士施乐株式会社 | Image display device, image processing system and method for displaying image |
| CN108604367A (en) * | 2016-03-09 | 2018-09-28 | 华为技术有限公司 | A kind of display methods and hand-hold electronic equipments |
| CN109584285A (en) * | 2017-09-29 | 2019-04-05 | 上海中兴软件有限责任公司 | A kind of control method, device and computer-readable medium showing content |
| US10531066B2 (en) | 2015-06-30 | 2020-01-07 | Samsung Electronics Co., Ltd | Method for displaying 3D image and device for same |
| CN111429519A (en) * | 2020-03-27 | 2020-07-17 | 贝壳技术有限公司 | Three-dimensional scene display method and device, readable storage medium and electronic equipment |
| CN112748796A (en) * | 2019-10-30 | 2021-05-04 | 京东方科技集团股份有限公司 | Display method and display device |
| CN112995566A (en) * | 2019-12-17 | 2021-06-18 | 佛山市云米电器科技有限公司 | Sound source positioning method based on display equipment, display equipment and storage medium |
| CN113900525A (en) * | 2021-10-29 | 2022-01-07 | 深圳Tcl数字技术有限公司 | Digital human display method and device and display equipment |
| CN114816641A (en) * | 2022-05-09 | 2022-07-29 | 海信视像科技股份有限公司 | Display device, multimedia content display method, and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030035001A1 (en) * | 2001-08-15 | 2003-02-20 | Van Geest Bartolomeus Wilhelmus Damianus | 3D video conferencing |
| CN1973555A (en) * | 2004-06-24 | 2007-05-30 | 索尼爱立信移动通讯有限公司 | Proximity assisted 3D rendering |
| CN102216977A (en) * | 2011-06-24 | 2011-10-12 | 华为终端有限公司 | A method for automatically adjusting screen display and a device thereof |
-
2012
- 2012-10-23 CN CN201210407541.7A patent/CN102917232B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030035001A1 (en) * | 2001-08-15 | 2003-02-20 | Van Geest Bartolomeus Wilhelmus Damianus | 3D video conferencing |
| CN1973555A (en) * | 2004-06-24 | 2007-05-30 | 索尼爱立信移动通讯有限公司 | Proximity assisted 3D rendering |
| CN102216977A (en) * | 2011-06-24 | 2011-10-12 | 华为终端有限公司 | A method for automatically adjusting screen display and a device thereof |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104020842B (en) * | 2013-03-01 | 2018-03-27 | 联想(北京)有限公司 | A kind of display methods and device, electronic equipment |
| CN104020842A (en) * | 2013-03-01 | 2014-09-03 | 联想(北京)有限公司 | Display method and device and electronic device |
| CN104519331B (en) * | 2013-09-27 | 2019-02-05 | 联想(北京)有限公司 | A kind of data processing method and electronic equipment |
| CN104519331A (en) * | 2013-09-27 | 2015-04-15 | 联想(北京)有限公司 | Data processing method and electronic device |
| CN103760980A (en) * | 2014-01-21 | 2014-04-30 | Tcl集团股份有限公司 | Display method, system and device for conducting dynamic adjustment according to positions of two eyes |
| CN103986959A (en) * | 2014-05-08 | 2014-08-13 | 海信集团有限公司 | Automatic parameter adjusting method and device of smart television equipment |
| CN103986959B (en) * | 2014-05-08 | 2017-10-03 | 海信集团有限公司 | A kind of method and device of intelligent television equipment adjust automatically parameter |
| CN104125395A (en) * | 2014-05-30 | 2014-10-29 | 深圳市中兴移动通信有限公司 | Method and device for realizing automatic shooting |
| CN104410882A (en) * | 2014-11-28 | 2015-03-11 | 苏州福丰科技有限公司 | Smart television with three-dimensional face scanning function |
| CN104539923A (en) * | 2014-12-03 | 2015-04-22 | 深圳市亿思达科技集团有限公司 | Depth-of-field adaptive holographic display method and device thereof |
| CN104883524A (en) * | 2015-06-02 | 2015-09-02 | 阔地教育科技有限公司 | Method and system for automatically tracking and shooting moving object in online class |
| CN104883524B (en) * | 2015-06-02 | 2018-09-11 | 阔地教育科技有限公司 | Moving target automatic tracking image pickup method and system in a kind of Online class |
| US10531066B2 (en) | 2015-06-30 | 2020-01-07 | Samsung Electronics Co., Ltd | Method for displaying 3D image and device for same |
| CN105405104B (en) * | 2015-09-24 | 2018-05-29 | 华为技术有限公司 | A kind of method and device of face image correcting |
| CN105405104A (en) * | 2015-09-24 | 2016-03-16 | 华为技术有限公司 | Method and apparatus for face image correction |
| WO2017088472A1 (en) * | 2015-11-26 | 2017-06-01 | 乐视控股（北京）有限公司 | Video playing processing method and device |
| CN106843821A (en) * | 2015-12-07 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | The method and apparatus of adjust automatically screen |
| CN105592367A (en) * | 2015-12-23 | 2016-05-18 | 青岛海信电器股份有限公司 | Image display parameter adjusting method and system |
| CN106919246A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | The display methods and device of a kind of application interface |
| CN105681861A (en) * | 2016-03-04 | 2016-06-15 | 青岛海信电器股份有限公司 | Adjusting method and system for display subtitle of terminal |
| CN105807952A (en) * | 2016-03-07 | 2016-07-27 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| US10950200B2 (en) | 2016-03-09 | 2021-03-16 | Huawei Technologies Co., Ltd. | Display method and handheld electronic device |
| CN108604367A (en) * | 2016-03-09 | 2018-09-28 | 华为技术有限公司 | A kind of display methods and hand-hold electronic equipments |
| WO2017177616A1 (en) * | 2016-04-15 | 2017-10-19 | 中兴通讯股份有限公司 | Face recognition method and device, and picture displaying method and device |
| US10740594B2 (en) | 2016-04-15 | 2020-08-11 | Zte Corporation | Face recognition method and device, and picture displaying method and device |
| CN107368491A (en) * | 2016-05-12 | 2017-11-21 | 富泰华工业（深圳）有限公司 | Making video system and method |
| CN107368491B (en) * | 2016-05-12 | 2023-07-25 | 富泰华工业（深圳）有限公司 | Image making system and method |
| CN106127163A (en) * | 2016-06-29 | 2016-11-16 | 深圳大学 | A kind of monocular ranging localization detecting system and detection method thereof |
| CN106303565A (en) * | 2016-08-12 | 2017-01-04 | 广州华多网络科技有限公司 | The image quality optimization method of net cast and device |
| CN106303565B (en) * | 2016-08-12 | 2019-06-18 | 广州华多网络科技有限公司 | The image quality optimization method and apparatus of net cast |
| CN107870708A (en) * | 2016-09-27 | 2018-04-03 | 富士施乐株式会社 | Image display device, image processing system and method for displaying image |
| CN106454315A (en) * | 2016-10-26 | 2017-02-22 | 深圳市魔眼科技有限公司 | Adaptive virtual view-to-stereoscopic view method and apparatus, and display device |
| CN106855744A (en) * | 2016-12-30 | 2017-06-16 | 维沃移动通信有限公司 | A kind of screen display method and mobile terminal |
| CN106774937A (en) * | 2017-01-13 | 2017-05-31 | 宇龙计算机通信科技(深圳)有限公司 | Image interactive method and its device in a kind of augmented reality |
| CN106774937B (en) * | 2017-01-13 | 2020-01-10 | 宇龙计算机通信科技(深圳)有限公司 | Image interaction method and device in augmented reality technology |
| CN107147897A (en) * | 2017-06-09 | 2017-09-08 | 西安闻泰电子科技有限公司 | Method for displaying image and device |
| CN109584285B (en) * | 2017-09-29 | 2024-03-29 | 中兴通讯股份有限公司 | Control method and device for display content and computer readable medium |
| CN109584285A (en) * | 2017-09-29 | 2019-04-05 | 上海中兴软件有限责任公司 | A kind of control method, device and computer-readable medium showing content |
| CN107748656A (en) * | 2017-10-19 | 2018-03-02 | 广东欧珀移动通信有限公司 | A kind of picture display process, device, terminal and storage medium |
| CN112748796A (en) * | 2019-10-30 | 2021-05-04 | 京东方科技集团股份有限公司 | Display method and display device |
| CN112748796B (en) * | 2019-10-30 | 2024-02-20 | 京东方科技集团股份有限公司 | Display method and display device |
| CN112995566A (en) * | 2019-12-17 | 2021-06-18 | 佛山市云米电器科技有限公司 | Sound source positioning method based on display equipment, display equipment and storage medium |
| CN112995566B (en) * | 2019-12-17 | 2024-04-05 | 佛山市云米电器科技有限公司 | Sound source positioning method based on display device, display device and storage medium |
| CN111429519B (en) * | 2020-03-27 | 2021-07-16 | 贝壳找房(北京)科技有限公司 | Three-dimensional scene display method and device, readable storage medium and electronic equipment |
| CN111429519A (en) * | 2020-03-27 | 2020-07-17 | 贝壳技术有限公司 | Three-dimensional scene display method and device, readable storage medium and electronic equipment |
| CN113900525A (en) * | 2021-10-29 | 2022-01-07 | 深圳Tcl数字技术有限公司 | Digital human display method and device and display equipment |
| CN114816641A (en) * | 2022-05-09 | 2022-07-29 | 海信视像科技股份有限公司 | Display device, multimedia content display method, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102917232B (en) | 2014-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102917232B (en) | Face recognition based 3D (three dimension) display self-adaptive adjusting method and face recognition based 3D display self-adaptive adjusting device | |
| US10855909B2 (en) | Method and apparatus for obtaining binocular panoramic image, and storage medium | |
| US9165535B2 (en) | System and method for determining a zoom factor of content displayed on a display device | |
| EP3395066B1 (en) | Depth map generation apparatus, method and non-transitory computer-readable medium therefor | |
| US9509922B2 (en) | Content normalization on digital displays | |
| US10319104B2 (en) | Method and system for determining datum plane | |
| US20120060177A1 (en) | Perspective display systems and methods | |
| KR20060113514A (en) | Image processing apparatus, image processing method, and program and recording medium used therewith | |
| KR20140057594A (en) | Interactive screen viewing | |
| US11050997B2 (en) | Dynamic display system capable of generating images corresponding to positions of users | |
| US20120013604A1 (en) | Display apparatus and method for setting sense of depth thereof | |
| CN109741289B (en) | Image fusion method and VR equipment | |
| CN108076208B (en) | Display processing method and device and terminal | |
| US20180184065A1 (en) | Method, apparatus, and non-transitory computer readable medium for generating depth maps | |
| US10885651B2 (en) | Information processing method, wearable electronic device, and processing apparatus and system | |
| US8878915B2 (en) | Image processing device and image processing method | |
| US20230056036A1 (en) | Method and device for generating a panoramic image | |
| CN115668913A (en) | Stereoscopic display method, device, medium and system for field performance | |
| US20190281280A1 (en) | Parallax Display using Head-Tracking and Light-Field Display | |
| US20180143523A1 (en) | Spherical omnipolar imaging | |
| US9767580B2 (en) | Apparatuses, methods, and systems for 2-dimensional and 3-dimensional rendering and display of plenoptic images | |
| US20120121163A1 (en) | 3d display apparatus and method for extracting depth of 3d image thereof | |
| CN113259650A (en) | Stereoscopic image display method, device, medium and system based on eye tracking | |
| CN102970567A (en) | Video processing apparatus and video processing method | |
| CN115209193B (en) | Display processing equipment and method and display system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhang Qi Inventor after: Wen Junfeng Inventor after: Li Xin Inventor after: Xue Ke Inventor after: Zhan Xinquan Inventor after: Du Haijiang Inventor after: Jiang Zhiwei Inventor before: Zhang Qi |
|
| COR | Change of bibliographic data | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20161027 Address after: 510075, Guangdong, Guangzhou Yuexiu District martyrs Road 80, 1008 and 1009 rooms, one of the self-made (only office use) Patentee after: Guangdong mainfort Mdt InfoTech Ltd Address before: 518057 Guangdong city of Shenzhen province Nanshan District Gao Xin Road SKYWORTH building A block 13-16 Patentee before: Shenzhen Skyworth-RGB Electronics Co., Ltd. |
|
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 510070 Eighth Floor, 23-1 Building, Courtyard 100 Xianliezhong Road, Yuexiu District, Guangzhou City, Guangdong Province Patentee after: Zhongke Skynet (Guangdong) Technology Co., Ltd. Address before: Room 1008 and 1009, 80 Xianlie Middle Road, Yuexiu District, Guangzhou City (office use only) Patentee before: Guangdong mainfort Mdt InfoTech Ltd |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: 3D display adaptive adjustment method and device based on face recognition Effective date of registration: 20211102 Granted publication date: 20141224 Pledgee: Industrial and Commercial Bank of China Limited Guangzhou Industrial Avenue sub branch Pledgor: ZHONGKE TIANWANG (GUANGDONG) TECHNOLOGY Co.,Ltd. Registration number: Y2021440000329 |