CN108615223A - Tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm - Google Patents
Tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm Download PDFInfo
- Publication number
- CN108615223A CN108615223A CN201810435287.9A CN201810435287A CN108615223A CN 108615223 A CN108615223 A CN 108615223A CN 201810435287 A CN201810435287 A CN 201810435287A CN 108615223 A CN108615223 A CN 108615223A
- Authority
- CN
- China
- Prior art keywords
- image
- lip
- tooth
- buccal side
- cheek
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000005457 optimization Methods 0.000 title claims abstract description 10
- 230000009466 transformation Effects 0.000 claims abstract description 8
- 238000012216 screening Methods 0.000 claims abstract 2
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 239000000284 extract Substances 0.000 abstract 1
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000003796 beauty Effects 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 210000000214 mouth Anatomy 0.000 description 2
- 206010044565 Tremor Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 210000003254 palate Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- 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
- H04N23/698—Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses the tooth lip buccal side Panorama Mosaic methods based on Local Optimization Algorithm, are scanned the scan video that formula shoots and obtains tooth lip (cheek) side to tooth lip (cheek) side by setting up video camera in orbit first.Interframe screening, the image that rejecting repeats or redundancy is more are carried out to scan video.Image is grouped by gyroscope information simultaneously.Each group of picture inputs stitching algorithm, extracts all image characteristic points and the optimization carried out between any two calculates, splice required parameter to obtain, and calculate the axial-rotation angle of image by these parameters.When accumulating axial-rotation angle less than angle threshold, sequential concatenation is carried out to image sequence according to the transformation parameter being calculated, and then obtain the stitching image of tooth lip (cheek) side.It is simple that the beneficial effects of the invention are as follows methods, easily operated, and stability is high.
Description
Technical field
The invention belongs to image procossings and technical field of oral medicine, are related to a kind of panorama sketch being based on tooth lip (cheek) side
Generation method.
Background technology
Traditional tooth detection needs user to go to clinic.Dentist needs to be observed per a moment tooth with stomatology endoscope
Tooth.Another way is that the shooting to patient oral cavity panorama sketch is completed under the assistance of nurse.This image pickup method is of high cost
(time cost and expense cost), less efficient, Patient Experience is bad.Occlusal surface, lip are usually also classified into for the shooting of tooth
(cheek) face and tongue (palate) three, face part.Lip (cheek) side tooth is clean and tidy as beautiful teeth has directly been reacted, and is contemporary people life
The embodiment of level and level.Therefore shooting tooth lip (cheek) side form, has booster action for tooth lesion or correction beauty.
Invention content
The purpose of the present invention is to provide the tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm, this hairs
Bright advantageous effect is that method is simple, easily operated, and stability is high.Tooth lip (cheek) side form can be intuitively reacted, for
Tooth lesion or correction beauty have booster action.
The technical solution adopted in the present invention is to follow the steps below：
1. the panoramic picture of lip (cheek) side is acquired by macro head.Camera, which is fixed on, defaults in lip (cheek) side
On the track of top, camera is slided along track when shooting.In shooting process, camera optical axis and tooth lip (cheek) side place
Plane angulation keeps approximate and stablizes.
2. tooth lip (cheek) side video acquired in saves as discrete picture according to its frame per second.In plane right-angle coordinate and
Discrete picture is screened in polar coordinate system in the plane.It is to set up relevance threshold value to screen principle, deletes the degree of association higher than association
The image of property threshold value.
3. being based on gyroscope information, according to rotation angle, shooting image is roughly divided into three portions according to shooting time axis
Point.It is left cheek side respectively, lip side and right cheek side.(" left side " " right side " instigates the left and right directions of user itself here)
4. respectively for left cheek side, lip side and right cheek side calculate adjacent two lips (cheek) side using adaptive sift algorithms
The feature point coordinates of image, and its corresponding description.And carry out Feature Points Matching according to these information.In matching process, utilize
Characteristic point coordinate information rejects the excessively close matching characteristic point pair leaned on.
5. between two lip (cheek) side images, according to the match condition of its characteristic point, part (between two figures) light is utilized
Beam adjustment method carries out the calculating (perspective transform parameter) of image transformation parameter.
6. in the parameter obtained by the 5th step, calculating the angle of axial-rotation between image, and added up.What accumulation obtained
Angle is denoted as θ.
7. when θ is less than this corresponding angle threshold in part (left cheek side, lip side, right cheek side), then the 8th, 9 step is executed；It is no
Then stop algorithm, and exports the panorama sketch of this part.
8. will obtain two tooth lip (cheek) side images is spliced into an image according to the transformation parameter being calculated.
9. based on this obtained local lip (cheek) side, step 4-7 is repeated, subsequent image is spliced to office successively
On portion's figure, until all images are all completed to splice.Eventually form the panorama sketch of tooth lip (cheek) side.
Further, illustrate in aforesaid clause, two kinds of threshold value determination methods：
It is realized by following procedure 1. relevance threshold value is chosen:A. it gives one group and is continuously shot occlusal surface image, it is arbitrary to select
A certain picture is selected as reference base picture, calculates the relating value size of adjacent image and it；B. from the size according to relating value, by height
Corresponding image is spliced two-by-two with benchmark image to low, it is at this moment right until apparent distortion or mistake occur for stitching image
The relating value answered is labeled as threshold value to be selected；C. it repeats above procedure several times, obtains several threshold values to be selected, maximum value is selected to make
For the threshold value of algorithm.
It is demarcated by following procedure 2. angle threshold is chosen:A. a tooth model target is chosen in advance.Camera is fixed
Except model, visual field face tooth model outer surface；B. respectively to three sides of tooth model (left cheek side, lip side, right cheek side),
The angle of video camera rotation when respectively shooting one group of image, and recording shooting.C. one of which image sequence is spliced, until spelling
Until apparent distortion or mistake occur for map interlinking picture, the angle value that at this moment corresponding camera turns over is angle threshold in this case
Value.
Description of the drawings
Fig. 1 is the method for the present invention flow diagram.
Specific implementation mode
The present invention is described in detail With reference to embodiment.
The present invention is as shown in Figure 1, the first step：The panoramic picture of lip (cheek) side is acquired by macro head.Camera
It is fixed on and defaults on the track by tooth lip (cheek) side, camera is slided along track when shooting.In sliding process, it should ensure that
Camera is stablized, and does not occur violent visual field variation.Steady shot refers to：Camera optical axis and plane where tooth lip (cheek) side
Angulation approximation is constant.Such as occur it is unstable shake (such as：It is unstable caused by because of patient teeth form deformity to tremble
It is dynamic), shake data should be captured by inertial sensor, and be fed back in algorithm.
Second step：Acquired tooth lip (cheek) side video saves as discrete picture according to its frame per second.It is sat in flat square
In mark system and polar coordinate system in the plane, discrete picture is screened.Specific practice is：It is previously set under the two coordinate systems
Set degree of association threshold value.This two figures phase in plane right-angle coordinate and polar coordinate system in the plane is calculated using phase association algorithm
The associated maximum value in position.In same coordinate system, obtained phase association maximum value degree of being associated with threshold value is compared.Appoint when having
When one value of meaning is more than degree of association threshold value, then the picture of serial number bigger is deleted.
Third walks：Gyroscope is demarcated first, and user should keep flat equipment as possible first, at this moment determine gyroscope perpendicular to tooth
The axis of tooth plane.It reuses the equipment to shoot tooth, when marking shooting according to the rotation angle for the axis demarcated
Between, and it is classified as three parts.It is left cheek side respectively, lip side and right cheek side.(" left side " " right side " instigates user's itself here
Left and right directions).Provide the angle threshold in this three faces.
Since the 4th step, we illustrate by certain side image mosaic flow in the 3rd step.This method is applied to whole three
A part.
4th step：Using adaptive SIFT algorithms, calculate adjacent two lips (cheek) side image (be respectively labeled as i-th and
I+1) feature point coordinates and its corresponding description.And carry out Feature Points Matching according to these information.Matched principle is,
It calculates between each characteristic point and other feature point in the Euclidean distance of the corresponding vector of description, one of chosen distance minimum
As matched characteristic point.In addition, when matching finishes, it is also necessary to screen out the ratio that same lip (cheek) side image spatial location is leaned on
Closer Feature Points Matching pair.This process is completed by setpoint distance threshold value, usually 8 pixels.
5th step：Between two lip (cheek) side images, according to the match condition of its characteristic point, part (two figures are utilized
Between) light-stream adjustment carry out image transformation parameter calculating (perspective transform parameter).Specifically it is segmented into two steps：The first,
A thick match parameter is obtained using RANSAC algorithms, it is corresponding with similar geometry consistency at the same time to obtain this parameter
Feature point set；The second, the point screened according to these is completed the essence between two images using light-stream adjustment and was matched
Journey.
6th step：The match information (showing as transformation matrix) being calculated according to the 5th step, calculates the axis of adjacent image
It to rotation angle, and is accumulated, the angle being accumulated by is θ.
7th step：When θ is less than this corresponding angle threshold in part (left cheek side, lip side and right cheek side), then execution the 8th, 9
Step；Otherwise stop algorithm, and export the panorama sketch of this part.
8th step：Two lip (cheek) side images of the match parameter pair obtained using the 4th step are spliced.The flow of splicing
It is：First, generate with the big splicing masterplate such as picture size, in masterplate the size of each pixel by this pixel positional distance
The distance of center determines；Secondly, i+1 figure and its corresponding masterplate are reflected according to the transformation parameter obtained in the 4th step
Being mapped to will be in i figures and its corresponding coordinate space；The numerical values recited for comparing each pixel in two width masterplates retains big that
It is a.Finally, summation is weighted to pixel in the image of lip (cheek) side according to the numerical value of masterplate, obtained by i and to by i+1
Panorama sketch MI, i+1。
9th step：The above 4-7 steps are repeated to i+1 and i+2 figures.I+2 figures are mapped to panorama sketch MI, i+1In,
And bonded, acquire panorama sketch MI, i+2, this process of repetition obtains the panorama sketch of all images.
Tooth inspection report-generating method proposed by the present invention based on oral cavity panoramic picture can effectively simplify the shooting of lip (cheek) side
Process, allow patient that can complete the shooting and splicing of lip (cheek) side panoramic picture at home.This simplifies obtain lip (cheek) side
The procurement cost of panorama sketch, while also improving the diagnosis efficiency of dentist.
The above is only the better embodiment to the present invention, not makees limit in any form to the present invention
System, every any simple modification that embodiment of above is made according to the technical essence of the invention, equivalent variations and modification,
Belong in the range of technical solution of the present invention.
Claims (5)
1. the tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm, it is characterised in that according to the following steps into
Row：
1) panoramic picture of lip buccal side is acquired by macro head, and camera is fixed on the track defaulted in above lip buccal side
On, camera is slided along track when shooting, in shooting process, camera optical axis and plane angulation where tooth lip buccal side
It keeps approximate to stablize；
2) the tooth lip buccal side video acquired in saves as discrete picture according to its frame per second, in plane right-angle coordinate and plane pole
Discrete picture is screened in coordinate system；
3) it is based on gyroscope information, according to rotation angle, shooting image is roughly divided into three parts according to shooting time axis：It is left
Cheek side, lip side and right cheek side；
4) respectively for left cheek side, lip side and right cheek side, the feature point coordinates of adjacent two lip buccal side images is calculated, and its corresponding
Description, and Feature Points Matching is carried out according to these information, in matching process, leaned on using the rejecting of characteristic point coordinate information excessively close
Matching characteristic point pair；
5) between two lip buccal side images, according to the match condition of its characteristic point, image is carried out using local light-stream adjustment
The calculating of transformation parameter；
6) in the parameter obtained by step 5), the angle of axial-rotation between image is calculated, and is added up, the angle accumulated
It is denoted as θ；
8) and 9) 7) when θ is less than left cheek side, the corresponding angle threshold in lip side or right cheek side, then follow the steps；Otherwise stop algorithm,
And export the panorama sketch of this part；
8) two tooth lip buccal side images will be obtained and is spliced into an image according to the transformation parameter being calculated；
9) based on this obtained local lip buccal side, step 4) is repeated to 7), subsequent image is spliced to Local map successively
On, until all images are all completed to splice, eventually form the panorama sketch of tooth lip buccal side.
2. according to the tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm described in claim 1, feature exists
In：Screening principle is for setting up relevance threshold value in the step 2), deletes the image that the degree of association is higher than set relevance threshold value.
3. according to the tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm described in claim 1, feature exists
In：Refer to locally between adjacent two figures in the step 5).
4. according to the tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm described in claim 2, feature exists
In：The relevance threshold value is chosen to be realized by following procedure:A. it gives one group and is continuously shot occlusal surface image, arbitrarily select certain
One picture calculates the relating value size of adjacent image and it as reference base picture；B. from the size according to relating value, from high to low
Corresponding image is spliced two-by-two with benchmark image, it is at this moment corresponding until apparent distortion or mistake occur for stitching image
Relating value is labeled as threshold value to be selected；C. it repeats above procedure several times, obtains several threshold values to be selected, select maximum value as calculation
The threshold value of method.
5. according to the tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm described in claim 2, feature exists
In：Angle threshold is chosen in the step 7) is demarcated by following procedure:A. a tooth model target, camera are chosen in advance
It is fixed on except model, visual field face tooth model outer surface；B. respectively to three sides of tooth model：Left cheek side, lip side, right cheek
Side, respectively shoots one group of image, and when recording shooting video camera rotation angle；C. one of which image sequence is spliced, directly
Until apparent distortion or mistake occur for stitching image, the angle value that at this moment corresponding camera turns over is angle in this case
Threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810435287.9A CN108615223A (en) | 2018-05-08 | 2018-05-08 | Tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810435287.9A CN108615223A (en) | 2018-05-08 | 2018-05-08 | Tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108615223A true CN108615223A (en) | 2018-10-02 |
Family
ID=63662281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810435287.9A Pending CN108615223A (en) | 2018-05-08 | 2018-05-08 | Tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108615223A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114626991A (en) * | 2022-05-13 | 2022-06-14 | 深圳思谋信息科技有限公司 | Image stitching method, device, equipment, medium and computer program product |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102420898A (en) * | 2011-09-27 | 2012-04-18 | 惠州Tcl移动通信有限公司 | Mobile phone-based panoramic photographing realization method and mobile phone |
| US20130286174A1 (en) * | 2011-01-11 | 2013-10-31 | Kabushiki Kaisya Advance | Intraoral video camera and display system |
| CN104574421A (en) * | 2015-01-29 | 2015-04-29 | 北方工业大学 | Large-breadth small-overlapping-area high-precision multispectral image registration method and device |
| CN104966270A (en) * | 2015-06-26 | 2015-10-07 | 浙江大学 | Multi-image stitching method |
| CN106530214A (en) * | 2016-10-21 | 2017-03-22 | 微景天下（北京）科技有限公司 | Image splicing system and image splicing method |
| US20170195570A1 (en) * | 2015-01-19 | 2017-07-06 | Ricoh Company, Ltd. | Preview Image Acquisition User Interface for Linear Panoramic Image Stitching |
| CN107682621A (en) * | 2017-09-06 | 2018-02-09 | 深圳天珑无线科技有限公司 | Rotate photographic method, device, mobile terminal and computer-readable recording medium |
| CN107798656A (en) * | 2017-11-09 | 2018-03-13 | 南京齿贝犀科技有限公司 | A kind of oral cavity Panorama Mosaic method based on range sensor and gyroscope |
-
2018
- 2018-05-08 CN CN201810435287.9A patent/CN108615223A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130286174A1 (en) * | 2011-01-11 | 2013-10-31 | Kabushiki Kaisya Advance | Intraoral video camera and display system |
| CN102420898A (en) * | 2011-09-27 | 2012-04-18 | 惠州Tcl移动通信有限公司 | Mobile phone-based panoramic photographing realization method and mobile phone |
| US20170195570A1 (en) * | 2015-01-19 | 2017-07-06 | Ricoh Company, Ltd. | Preview Image Acquisition User Interface for Linear Panoramic Image Stitching |
| CN104574421A (en) * | 2015-01-29 | 2015-04-29 | 北方工业大学 | Large-breadth small-overlapping-area high-precision multispectral image registration method and device |
| CN104966270A (en) * | 2015-06-26 | 2015-10-07 | 浙江大学 | Multi-image stitching method |
| CN106530214A (en) * | 2016-10-21 | 2017-03-22 | 微景天下（北京）科技有限公司 | Image splicing system and image splicing method |
| CN107682621A (en) * | 2017-09-06 | 2018-02-09 | 深圳天珑无线科技有限公司 | Rotate photographic method, device, mobile terminal and computer-readable recording medium |
| CN107798656A (en) * | 2017-11-09 | 2018-03-13 | 南京齿贝犀科技有限公司 | A kind of oral cavity Panorama Mosaic method based on range sensor and gyroscope |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114626991A (en) * | 2022-05-13 | 2022-06-14 | 深圳思谋信息科技有限公司 | Image stitching method, device, equipment, medium and computer program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101238608B1 (en) | A system and method for 3D space-dimension based image processing | |
| US7024053B2 (en) | Method of image processing and electronic camera | |
| JP5739409B2 (en) | Method for determining the relative position of a first image device and a second image device and these devices | |
| CN110782394A (en) | Panoramic video rapid splicing method and system | |
| CN102316247B (en) | Image processing apparatus | |
| CN107680688B (en) | Pelvic cavity simulation minimally invasive surgery visual navigation verification method based on 3D printing | |
| JPH067289A (en) | Endoscopic image processor | |
| JPH05108819A (en) | Picture processor | |
| CN103198501B (en) | A kind of tooth panoramic picture automatic reconstruction | |
| CN104883948B (en) | Image processing device and image processing method | |
| CN113902657A (en) | Image splicing method and device and electronic equipment | |
| CN109889799B (en) | Monocular structure light depth perception method and device based on RGBIR camera | |
| CN107493427A (en) | Focusing method, device and the mobile terminal of mobile terminal | |
| CN107507230A (en) | Method for tracking target and panorama camera applied to panoramic picture | |
| JP2003179800A (en) | Device for generating multi-viewpoint image, image processor, method and computer program | |
| CN107798656A (en) | A kind of oral cavity Panorama Mosaic method based on range sensor and gyroscope | |
| CN107437268A (en) | Photographic method, device, mobile terminal and computer-readable storage medium | |
| CN108597004A (en) | Occlusal surfaces of teeth Panorama Mosaic method based on Local Optimization Algorithm | |
| CN108615223A (en) | Tooth lip buccal side Panorama Mosaic method based on Local Optimization Algorithm | |
| CN110035687B (en) | Method and device for image stitching of images captured by capsule camera | |
| JP7179837B2 (en) | Endoscope device, endoscope image display method, and operation method of endoscope device | |
| JP2005063041A (en) | Three-dimensional modeling apparatus, method, and program | |
| KR20140052769A (en) | Apparatus and method for correcting distored image | |
| JP2005141655A (en) | Three-dimensional modeling apparatus and three-dimensional modeling method | |
| CN108648146A (en) | Tooth tongue palate side Panorama Mosaic method based on Local Optimization Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181002 |
|
| RJ01 | Rejection of invention patent application after publication |