CN116912426B - Denture model generation system based on image processing - Google Patents
Denture model generation system based on image processing Download PDFInfo
- Publication number
- CN116912426B CN116912426B CN202311160524.2A CN202311160524A CN116912426B CN 116912426 B CN116912426 B CN 116912426B CN 202311160524 A CN202311160524 A CN 202311160524A CN 116912426 B CN116912426 B CN 116912426B
- Authority
- CN
- China
- Prior art keywords
- image
- resolution
- dental
- denture
- blocks
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000013507 mapping Methods 0.000 claims description 17
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000003709 image segmentation Methods 0.000 claims description 9
- 238000013341 scale-up Methods 0.000 claims description 7
- 238000010191 image analysis Methods 0.000 claims description 5
- 210000000214 mouth Anatomy 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 239000007943 implant Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000010146 3D printing Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000007639 printing Methods 0.000 description 2
- 206010010356 Congenital anomaly Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
- A61C13/00—Dental prostheses; Making same
- A61C13/0003—Making bridge-work, inlays, implants or the like
- A61C13/0004—Computer-assisted sizing or machining of dental prostheses
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
- A61C9/00—Impression cups, i.e. impression trays; Impression methods
- A61C9/004—Means or methods for taking digitized impressions
- A61C9/0046—Data acquisition means or methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30036—Dental; Teeth
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Epidemiology (AREA)
- Dentistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Graphics (AREA)
- Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a false tooth model generating system based on image processing, which comprises a 3D scanner, an image forming system, a false tooth model building module and false tooth generating equipment. According to the denture model generating system based on image processing, the image forming system is arranged, the image receiving module is used for receiving and classifying images, the image processing module is used for adjusting the definition of the images and improving the resolution of the images, the images with improved definition are combined to form a new image, the digital conversion module is used for converting high-resolution image signals into digital signals, the digital signals are input into the denture model building module, and the digital signals are combined to form a 3D denture model, so that the definition and resolution of the images are improved in the image processing process, and the generated 3D denture model is more accurate.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a false tooth model generating system based on image processing.
Background
Because of the factors such as congenital factors, acquired living habits and accidents, etc., the current many people need to carry out medical treatment activities of dental correction and denture installation, in order to improve the working efficiency and quality of the dental correction and denture installation work, the current medical staff is often required to firstly establish a corresponding model for the oral cavity structure of a patient before diagnosis and treatment, and then carry out corresponding denture modeling, installation and dental correction work according to the established model.
Referring to Chinese patent, the patent name is: an implant modeling method and system based on image recognition technology (patent publication No. CN115984470A, patent publication No. 2023.04.18), the method comprises: determining a target tooth position and attribute data thereof according to the first image data, and determining second image data according to the attribute data; according to the method, the curve data corresponding to the target tooth position is determined according to the second image data, the implant modeling is carried out on the target tooth position according to the curve data, the image recognition technology is utilized to extract the image of the oral cavity of the user, the position of the tooth to be implanted and attribute data thereof are automatically recognized, and then the curve data related to the position of the tooth to be implanted are extracted, so that the implant model with higher adaptation to the peripheral teeth can be determined, the adaptation of the implant is greatly improved, and more personalized and more comfortable tooth experience is brought to the user.
In the existing denture model generation process, the denture is generally manufactured by adopting a 3D printing technology, but the following problems still exist:
at present, a denture needs to be matched and customized for a customer, the denture is manufactured through 3D printing, the user needs to be sampled before customization, an image recognition processing is carried out through a scanner to automatically generate a denture model, then the denture model is optimized to obtain an exact model, and on the basis that after image recognition, the obtained image definition has defects in the image processing process, more shadow parts exist in the image, and whether the shadow parts are protruding or recessed entities can not be accurately judged through shadow part comparison, so that the formed denture model has errors in accuracy.
To this end, the present invention provides a denture model generation system based on image processing.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a false tooth model generation system based on image processing, which solves the problem that in the existing 3D false tooth generation operation, the obtained image definition has defects in the process of processing the image, more shadow parts exist in the image, and whether the shadow parts are raised or recessed entities cannot be accurately judged through the shadow part comparison, so that the formed false tooth model precision has errors.
In order to achieve the above purpose, the invention is realized by the following technical scheme: a denture model generation system based on image processing, comprising a 3D scanner, an image forming system, a denture model building module and a denture generating device, wherein the 3D scanner is used for scanning the oral cavity dental site of a custom person and forming image data, the denture model building module is used for combining the data processed by the image forming system to form a denture model, the denture generating device is used for printing the denture model to generate a entity of the denture model, and the 3D scanner, the image forming system, the denture model building module and the denture generating device sequentially realize bidirectional data interaction operation, the image forming system comprises:
the image receiving module is used for receiving the pictures formed by scanning and transmitting the pictures to the image processing module for image processing operation through classification;
the image processing module is used for adjusting the definition of the image, improving the resolution of the image and combining the image with the improved definition to form a new picture;
the digital conversion module is used for converting the image signals of the plurality of new photos into digital signals, inputting the digital signals into the denture model building module, and forming the 3D denture model through the combination of the digital signals.
Preferably, the image processing module includes:
an image segmentation unit for preprocessing the image and segmenting the image according to the gray threshold valueIs divided into a plurality of image blocksRemoving background image blocks by adopting blocks in the segmentation process, and obtaining dental image blocks;
the image enhancement unit is used for expanding channels in the feature images of the low-resolution dental image blocks by inputting the dental image blocks into the scale-expanding model, compensating the expanded errors and obtaining the high-resolution dental image blocks;
the image analysis unit is used for judging the specific information of the dental image block and transmitting the specific information to the next unit by extracting the characteristic part of the high-resolution dental image block and performing threshold comparison operation after the characteristic part is subjected to gray threshold segmentation operation;
and the data summarizing unit is used for forming an obtained amplified image by splicing and combining the amplified high-resolution dental image blocks, and obtaining a 3D false tooth image by mapping the characteristics on each image.
Preferably, the image blocks in the image segmentation unitThe specific operation mode of gray threshold segmentation is as follows:
s1, dividing each image block through background gray level distributionRemoving the background image blocks by the combination of the background image blocks and the dental image blocks, and leaving the dental image blocks;
s2, calculating variances of the dental image blocks, and arranging the variances of the dental image blocks into an ordered sequence from small to largeThen the dental image blocks with the variance of 50% of the ordered sequences from small to large are removed, and the rest of the ordered sequences are removedThe tooth image block of the tooth part is marked;
s3, throughCalculating the average threshold T of the dental image blocks and by sequentially sequencingIn (3) a pixelPerforming S-shaped traversal operation, and traversing the obtained pixel valuesAnd comparing the image characteristics of the dental image blocks with the average threshold T.
Preferably, the variance calculation formula in S2 is:;
the image mean value calculation formula of the dental image block is as follows:
where a is the threshold value of image block X and n is the number of image blocks X.
Preferably, the comparison method of the pixel value in S3 and the average threshold T is as follows:
if the pixel value isThe following condition is satisfied, then the pixels in the dental image block of the ordered sequence GMarked as dental concave profile:；
if the pixel value isThe following condition is satisfied, then the pixels in the dental image block of the ordered sequence GMarked as tooth convex profile:。
preferably, the image enhancement unit enlarges the low-resolution dental image block to a target size by:
z1, according to the 50% ordered sequence from large to smallDispersing the low-resolution dental image blocks, extracting the characteristic parts of the marks of the images, and simultaneously establishing an image scale-up model for amplifying the images;
z2, inputting the extracted characteristic part into a scale-up model, and expanding a channel in a characteristic diagram of the low-resolution dental image block;
and Z3, calculating and compensating errors of the feature map obtained after expansion, and finally obtaining the high-resolution dental image block.
Preferably, the error calculation formula of the feature map obtained after expansion in Z3 is:
where i represents the number of measurements, q represents the number of output channels, and k is the basic constant of the feature map.
Preferably, the resolution calculation formula of the high-resolution dental image block is as follows:
wherein U is the length pixel number; v is the number of width pixels; w is the screen size, i.e. diagonal length.
Preferably, the feature mapping specific mode of the data summarizing unit is as follows: each layer of learning based on the neural network model is oneMapping of (2) instead ofI.e. the initial input is added at the end of each layer, where the input is d and the output isThenThe value of (2) tends to be 0 and as the number of layers increases, the errorAnd the high-resolution mapping image block is obtained without change.
Preferably, the data summarizing unit performs stitching and combining on the high-resolution mapping image blocks with the same resolution obtained through calculation according to the initial sequence of the image blocks to form a plurality of new high-resolution images, and links the high-resolution images to form a three-dimensional high-resolution denture image.
The invention provides a false tooth model generating system based on image processing. Compared with the prior art, the method has the following beneficial effects:
(1) The denture model generating system based on image processing is provided with an image forming system, an image receiving module is used for receiving and classifying images, the image processing module is used for adjusting the definition of the images and improving the resolution of the images, the images with improved definition are combined to form a new image, the digital conversion module is used for converting high-resolution image signals into digital signals, the digital signals are input into a denture model building module, and a 3D denture model is formed through the combination of the digital signals, so that the definition and the resolution of the images are improved in the image processing process, and the generated 3D denture model is more accurate.
(2) The denture model generating system based on image processing comprises an image dividing unit for preprocessing an image, dividing the image according to gray threshold valueIs divided into a plurality of graphsThe image block is used for eliminating the background image block by adopting the block in the segmentation process, obtaining the dental image block, and realizing the condition of primarily judging the image characteristics of the dental image block, thereby judging whether the image elements in the dental image block are concave surfaces or convex surfaces, realizing the marking of uncertain image characteristics, improving the information accuracy in the image processing, reducing the processing workload and carrying out optimization operation on key dental images.
(3) According to the denture model generating system based on image processing, the image enhancement unit is arranged, the channels in the feature images of the low-resolution dental image blocks are enlarged through inputting the dental image blocks into the scale-enlarging model, error calculation and compensation are carried out on the feature images obtained after enlargement, the high-resolution dental image blocks are obtained, the sharpness of the dental image blocks with larger errors is improved, feature identification is carried out after error compensation is completed, and the high-resolution dental image blocks with accurate information are judged again, so that the follow-up denture models are more attached.
Drawings
Fig. 1 is a schematic block diagram of a denture model generating system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides three technical solutions:
an embodiment is a denture model generating system based on image processing, including a 3D scanner, an image forming system, a denture model building module and a denture generating device, wherein the 3D scanner is used for scanning oral cavity teeth of a customized person and forming image data, the denture model building module is used for combining the data processed by the image forming system to form a denture model, the denture generating device is used for printing the denture model to generate a entity of the denture model, and the 3D scanner, the image forming system, the denture model building module and the denture generating device sequentially realize bidirectional data interaction operation, the image forming system includes:
the image receiving module is used for receiving the pictures formed by scanning and transmitting the pictures to the image processing module for image processing operation through classification;
the image processing module is used for adjusting the definition of the image, improving the resolution of the image and combining the image with the improved definition to form a new picture;
the digital conversion module is used for converting the image signals of the plurality of new photos into digital signals, inputting the digital signals into the denture model building module, and forming the 3D denture model through the combination of the digital signals.
The 3D scanner and the denture generating equipment are matched equipment, are in the prior art and are electrically connected with an external power supply, and finish model generating operation after scanning and subsequent data importing.
The image forming system is arranged, the image receiving module is used for receiving and classifying images, the image processing module is used for adjusting the definition of the images and improving the resolution of the images, the images with the improved definition are combined to form a new image, the digital conversion module is used for converting high-resolution image signals into digital signals, the digital signals are input into the denture model building module, and the digital signals are combined to form a 3D denture model, so that the definition and the resolution of the images are improved in the image processing process, and the generated 3D denture model is more accurate.
In an embodiment of the present invention, an image processing module includes:
an image segmentation unit for preprocessing the image and segmenting the image according to the gray threshold valueIs divided into a plurality of image blocksRemoving background image blocks by adopting blocks in the segmentation process, and obtaining dental image blocks;
the image enhancement unit is used for expanding channels in the feature images of the low-resolution dental image blocks by inputting the dental image blocks into the scale-expanding model, compensating the expanded errors and obtaining the high-resolution dental image blocks;
the image analysis unit is used for judging the specific information of the dental image block and transmitting the specific information to the next unit by extracting the characteristic part of the high-resolution dental image block and performing threshold comparison operation after the characteristic part is subjected to gray threshold segmentation operation;
and the data summarizing unit is used for forming an obtained amplified image by splicing and combining the amplified high-resolution dental image blocks, and obtaining a 3D false tooth image by mapping the characteristics on each image.
The output end of the image segmentation unit is connected with the input end of the image enhancement unit, the output end of the image enhancement unit is connected with the input end of the image analysis unit, and the output end of the image analysis unit is connected with the input end of the data summarization unit, so that the image segmentation unit is used for firstly segmenting a plurality of image blocks, removing background image blocks, leaving dental image blocks with small variance, and then traversing pixel values in the image blocksComparing with the average threshold value T to judge the image characteristics of the dental image blocks, knowing whether the marked part is a concave surface or a convex surface, dispersing the dental image blocks with low resolution and large variance, extracting the characteristic parts of the marks of the images, simultaneously establishing an image scale-expanding model for amplifying the images, compensating the resolution of the characteristic images after amplifying the resolution to obtain high-resolution dental image blocks, dividing the dental image blocks again based on the high-resolution dental image blocks, outputting the image blocks with specific information, transmitting the image blocks to a data summarizing unit, and reducing the resolution through the mapping learning of a neural network modelAnd finally, splicing and combining the processed high-resolution mapping image blocks to form a plurality of new high-resolution images, and forming a three-dimensional high-resolution denture image by linking the high-resolution images.
In the embodiment of the invention, the image blocks in the image segmentation unitThe specific operation mode of gray threshold segmentation is as follows:
s1, dividing each image block through background gray level distributionRemoving the background image blocks by the combination of the background image blocks and the dental image blocks, and leaving the dental image blocks;
s2, calculating variances of the dental image blocks, and arranging the variances of the dental image blocks into an ordered sequence from small to largeThen the dental image blocks with the variance of 50% of the ordered sequences from small to large are removed, and the rest of the ordered sequences are removedThe tooth image block of the tooth part is marked;
s3, calculating an average threshold value T of the dental image blocks, and performing sequential sequenceIn (3) a pixelPerforming S-shaped traversal operation, and traversing the obtained pixel valuesAnd comparing the image characteristics of the dental image blocks with the average threshold T.
In the embodiment of the present invention, the variance calculation formula in S2 is:;
the image mean value calculation formula of the dental image block is as follows:
where a is the threshold value of image block X and n is the number of image blocks X.
In the embodiment of the invention, the comparison method of the pixel value in S3 and the average threshold T is as follows:
if the pixel value isThe following condition is satisfied, then the pixels in the dental image block of the ordered sequence GMarked as dental concave profile:；
if the pixel value isThe following condition is satisfied, then the pixels in the dental image block of the ordered sequence GMarked as tooth convex profile:。
wherein, the image segmentation unit is arranged to preprocess the image and then segment the image according to the gray threshold valueDividing the sequence of the tooth image blocks into a plurality of image blocks, removing background image blocks by adopting blocks in the dividing process, obtaining tooth image blocks, and realizing the condition of primarily judging the image characteristics of the tooth image blocks, thereby judging whether the image elements in the tooth image blocks are concave surfaces or convex surfaces, realizing the marking of uncertain image characteristics, and improving the imageInformation accuracy in processing and reduced processing effort, and optimization operations are performed for critical dental images.
The difference between the second embodiment and the first embodiment is that:
in the embodiment of the invention, the operation steps of amplifying the low-resolution dental image block to the target size in the image enhancement unit are as follows:
z1, according to the 50% ordered sequence from large to smallDispersing the low-resolution dental image blocks, extracting the characteristic parts of the marks of the images, and simultaneously establishing an image scale-up model for amplifying the images;
z2, inputting the extracted characteristic part into a scale-up model, and expanding a channel in a characteristic diagram of the low-resolution dental image block;
and Z3, calculating and compensating errors of the feature map obtained after expansion, and finally obtaining the high-resolution dental image block.
In the embodiment of the invention, the error calculation formula of the feature map obtained after expansion in Z3 is as follows:
where i represents the number of measurements, q represents the number of output channels, and k is the basic constant of the feature map.
In the embodiment of the invention, the resolution calculation formula of the high-resolution dental image block is as follows:
wherein U is the length pixel number; v is the number of width pixels; w is the screen size, i.e. diagonal length.
Through being provided with the image enhancement unit, through inputting the tooth image piece into the scale-up model, enlarge the passageway in the feature map of low resolution tooth image piece, carry out the calculation and the compensation of error to the feature map that obtain after the enlargement to obtain high resolution tooth image piece, with this improvement to the great tooth image piece of error carries out the definition in the completion, thereby carry out the feature identification again after accomplishing the compensation to the error, judge again and obtain the high resolution tooth image piece of accurate information, make subsequent artificial tooth model more laminate.
The difference between the third embodiment and the first embodiment is that:
in the embodiment of the invention, the characteristic mapping specific mode of the data summarizing unit is as follows: each layer of learning based on the neural network model is oneMapping of (2) instead ofI.e. the initial input is added at the end of each layer, where the input is d and the output isThenThe value of (2) tends to be 0 and as the number of layers increases, the errorAnd the high-resolution mapping image block is obtained without change.
In the embodiment of the invention, the data summarizing unit splices and combines the high-resolution mapping image blocks with the same resolution obtained by calculation according to the initial sequence of the image blocks to form a plurality of new high-resolution images, and links the high-resolution images to form a three-dimensional high-resolution denture image.
And all that is not described in detail in this specification is well known to those skilled in the art.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The utility model provides a denture model generation system based on image processing, including 3D scanner, image forming system, denture model establishment module and denture generation equipment, and the 3D scanner is used for scanning the oral cavity tooth position portion of customization personnel and forms image data, and denture model establishment module is used for combining the data after the image forming system processing and forming the denture model, denture generation equipment is used for the entity of generating the denture model with the denture model print, and realize two-way data interaction operation in proper order between 3D scanner, image forming system, denture model establishment module and the denture generation equipment, its characterized in that: the image forming system includes:
the image receiving module is used for receiving the pictures formed by scanning and transmitting the pictures to the image processing module for image processing operation through classification;
the image processing module is used for adjusting the definition of the image, improving the resolution of the image and combining the image with the improved definition to form a new picture;
the digital conversion module is used for converting image signals of a plurality of new photos into digital signals, inputting the digital signals into the denture model building module and forming a 3D denture model through the combination of the digital signals;
the image processing module includes:
an image segmentation unit for preprocessing the image and segmenting the image according to the gray threshold valueIs divided into a plurality of image blocks +.>Removing background image blocks by adopting blocks in the segmentation process, and obtaining dental image blocks;
the image enhancement unit is used for expanding channels in the feature images of the low-resolution dental image blocks by inputting the dental image blocks into the scale-expanding model, compensating the expanded errors and obtaining the high-resolution dental image blocks;
the image analysis unit is used for judging the specific information of the dental image block and transmitting the specific information to the next unit by extracting the characteristic part of the high-resolution dental image block and performing threshold comparison operation after the characteristic part is subjected to gray threshold segmentation operation;
the data summarizing unit is used for splicing and combining the enlarged high-resolution dental image blocks to form an enlarged image, and mapping the characteristics on each image to obtain a 3D false tooth image;
image blocks in the image segmentation unitThe specific operation mode of gray threshold segmentation is as follows:
s1, dividing each image block through background gray level distributionRemoving the background image blocks by the combination of the background image blocks and the dental image blocks, and leaving the dental image blocks;
s2, calculating variances of the dental image blocks, and arranging the variances of the dental image blocks into an ordered sequence from small to largeThen the variance is reduced from small to large to 50% ordered sequenceRemoving dental image blocks and removing the remaining ordered sequenceThe tooth image block of the tooth part is marked;
s3, calculating an average threshold value T of the dental image blocks, and performing sequential sequencePixels in->Performing S-shaped traversal operation to obtain pixel value +.>And comparing the image characteristics of the dental image blocks with the average threshold T.
2. A denture model generating system based on image processing according to claim 1, wherein: the variance calculation formula in S2 is:
；
the image mean value calculation formula of the dental image block is as follows:
；
wherein the method comprises the steps ofFor image block->Threshold of->For image block->Is a number of (3).
3. A denture model generating system based on image processing according to claim 1, wherein: the comparison method of the pixel value in the S3 and the average threshold T is as follows:
if the pixel value isThe following condition is satisfied, the ordered sequence +.>Pixels in dental image blocks +.>Marked as dental concave profile: />；
If the pixel value isThe following condition is satisfied, the ordered sequence +.>Pixels in dental image blocks +.>Marked as tooth convex profile: />。
4. A denture model generating system based on image processing according to claim 1, wherein: the image enhancement unit enlarges the low-resolution dental image block to a target size by the following operation steps:
z1, according to the 50% ordered sequence from large to smallDispersing the low-resolution dental image blocks, extracting the characteristic parts of the marks of the images, and simultaneously establishing an image scale-up model for amplifying the images;
z2, inputting the extracted characteristic part into a scale-up model, and expanding a channel in a characteristic diagram of the low-resolution dental image block;
and Z3, calculating and compensating errors of the feature map obtained after expansion, and finally obtaining the high-resolution dental image block.
5. An image processing-based denture model generating system according to claim 4, wherein: the error calculation formula of the feature map obtained after expansion in the Z3 is as follows:
；
where i represents the number of measurements, q represents the number of output channels, and k is the basic constant of the feature map.
6. An image processing-based denture model generating system according to claim 5, wherein: the resolution calculation formula of the high-resolution dental image block is as follows:
；
wherein U is the length pixel number; v is the number of width pixels; w is the screen size, i.e. diagonal length.
7. A denture model generating system based on image processing according to claim 1, wherein: the characteristic mapping specific mode of the data summarizing unit is as follows: each layer of learning based on the neural network model is oneMapping of->I.e. the initial input is added at the end of each layer, where the input is +.>The output is +.>Then->The value of (2) tends to be 0 and as the number of layers increases, the error is +.>And the high-resolution mapping image block is obtained without change.
8. A denture model generating system based on image processing according to claim 7, wherein: the data summarizing unit is used for splicing and combining the high-resolution mapping image blocks with the same resolution obtained through calculation according to the initial sequence of the image blocks to form a plurality of new high-resolution images, and forming a three-dimensional high-resolution denture image by linking the high-resolution images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311160524.2A CN116912426B (en) | 2023-09-11 | 2023-09-11 | Denture model generation system based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311160524.2A CN116912426B (en) | 2023-09-11 | 2023-09-11 | Denture model generation system based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116912426A CN116912426A (en) | 2023-10-20 |
| CN116912426B true CN116912426B (en) | 2023-11-21 |
Family
ID=88360561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311160524.2A Active CN116912426B (en) | 2023-09-11 | 2023-09-11 | Denture model generation system based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116912426B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017219263A1 (en) * | 2016-06-22 | 2017-12-28 | 中国科学院自动化研究所 | Image super-resolution enhancement method based on bidirectional recursion convolution neural network |
| CN110363750A (en) * | 2019-06-28 | 2019-10-22 | 福建师范大学 | A kind of canalis radicis dentis form extraction method based on multi-modal data fusion |
| KR20200023225A (en) * | 2018-08-24 | 2020-03-04 | 이재우 | Methods for Segmentation and Processing of Dental Images for Diagnosing, Predicting, or Managing Oral Conditions |
| CN113116572A (en) * | 2021-03-01 | 2021-07-16 | 北京联袂义齿技术有限公司 | False tooth model forming system and forming method based on cloud computing |
| CN114170090A (en) * | 2021-12-16 | 2022-03-11 | 南京协奏网络科技有限公司 | Method and system for reconstructing high-resolution image from fuzzy monitoring video |
| CN115115520A (en) * | 2022-07-20 | 2022-09-27 | 晨星基因(北京)智能科技有限公司 | Image imaging method capable of improving image definition and resolution |
| KR102461343B1 (en) * | 2022-02-24 | 2022-10-31 | 서울대학교산학협력단 | Automatic tooth landmark detection method and system in medical images containing metal artifacts |
-
2023
- 2023-09-11 CN CN202311160524.2A patent/CN116912426B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017219263A1 (en) * | 2016-06-22 | 2017-12-28 | 中国科学院自动化研究所 | Image super-resolution enhancement method based on bidirectional recursion convolution neural network |
| KR20200023225A (en) * | 2018-08-24 | 2020-03-04 | 이재우 | Methods for Segmentation and Processing of Dental Images for Diagnosing, Predicting, or Managing Oral Conditions |
| CN110363750A (en) * | 2019-06-28 | 2019-10-22 | 福建师范大学 | A kind of canalis radicis dentis form extraction method based on multi-modal data fusion |
| CN113116572A (en) * | 2021-03-01 | 2021-07-16 | 北京联袂义齿技术有限公司 | False tooth model forming system and forming method based on cloud computing |
| CN114170090A (en) * | 2021-12-16 | 2022-03-11 | 南京协奏网络科技有限公司 | Method and system for reconstructing high-resolution image from fuzzy monitoring video |
| KR102461343B1 (en) * | 2022-02-24 | 2022-10-31 | 서울대학교산학협력단 | Automatic tooth landmark detection method and system in medical images containing metal artifacts |
| CN115115520A (en) * | 2022-07-20 | 2022-09-27 | 晨星基因(北京)智能科技有限公司 | Image imaging method capable of improving image definition and resolution |
Non-Patent Citations (3)
| Title |
|---|
| 一种新颖的单幅图像超分辨率重建;刘少鹏;王晓明;;计算机仿真(第05期);全文 * |
| 利用工业CT扫描图像重建牙列缺损的几何模型;吴琳;闫海鑫;杨民;;上海口腔医学(第05期);全文 * |
| 铸造三臂卡环固位臂动态应力分析方法的探讨;王淑英, 张振庭, 白保晶, 蒋向华, 王延荣;口腔颌面修复学杂志(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116912426A (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1475969B (en) | Method and system for intensify human image pattern | |
| US7907768B2 (en) | Method and apparatus for probabilistic atlas based on shape modeling technique | |
| CN110599528A (en) | Unsupervised three-dimensional medical image registration method and system based on neural network | |
| US7881515B2 (en) | Cephalogram image analysis method | |
| KR20170088174A (en) | Method for providing information on scalp diagnosis based on image | |
| CN107909622A (en) | Model generating method, the scanning planing method of medical imaging and medical image system | |
| CN114424246A (en) | Method, system and computer-readable storage medium for registering intraoral measurements | |
| CN110008992B (en) | Deep learning method for prostate cancer auxiliary diagnosis | |
| CN110853119B (en) | Reference picture-based makeup transfer method with robustness | |
| CN112381811B (en) | Method, device and equipment for realizing medical image data annotation | |
| JPH11126256A (en) | Method for recoverying radiation distortion parameter from single camera image | |
| CN114119968B (en) | Paper electrocardiogram signal region extraction method and system based on deep neural network | |
| CN110868913A (en) | Tool for tracking gum line and displaying periodontal measurements using intraoral 3D scan | |
| CN116912426B (en) | Denture model generation system based on image processing | |
| CN117611542B (en) | Fetal intrauterine craniocerebral image-based detection method and system | |
| CN110348339B (en) | Method for extracting handwritten document text lines based on case segmentation | |
| George et al. | Dental radiography analysis and diagnosis using YOLOv8 | |
| CN112651962A (en) | AI intelligent diagnosis system platform | |
| KR20220014933A (en) | Age estimation method and system from PMCT scan image | |
| JPH11306325A (en) | Method and device for object detection | |
| CN114677516A (en) | Automatic oral mandibular canal segmentation method based on deep neural network | |
| CN114708237A (en) | Detection algorithm for hair health condition | |
| CN112927225A (en) | Wisdom tooth growth state auxiliary detection system based on artificial intelligence | |
| CN112700430A (en) | Orthodontic image picture intelligent identification method based on deep learning | |
| CN113496536B (en) | Cartoon figure modeling system based on image acquisition |
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 |