CN111652839A - Tooth colorimetric detection method and system based on rapid regional full convolution neural network - Google Patents
Tooth colorimetric detection method and system based on rapid regional full convolution neural network Download PDFInfo
- Publication number
- CN111652839A CN111652839A CN202010317099.3A CN202010317099A CN111652839A CN 111652839 A CN111652839 A CN 111652839A CN 202010317099 A CN202010317099 A CN 202010317099A CN 111652839 A CN111652839 A CN 111652839A
- Authority
- CN
- China
- Prior art keywords
- tooth
- neural network
- output
- image
- colorimetric
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 33
- 230000005477 standard model Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000005070 sampling Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 18
- 238000011176 pooling Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 239000002932 luster Substances 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 208000008312 Tooth Loss Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000004737 colorimetric analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000008802 morphological function Effects 0.000 description 1
- 210000000214 mouth Anatomy 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 229910052573 porcelain Inorganic materials 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- 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
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a tooth colorimetric detection method based on a rapid regional full convolution neural network, which comprises the following steps: s1, sampling each standard tooth in the colorimetric plate tooth library for multiple times by using the data information acquisition system to obtain multiple map data to form a tooth colorimetric plate chart library; s2, performing model training and learning on the colorimetric board gallery by using a rapid regional full convolution neural network algorithm and establishing a standard model gallery; and S3, collecting tooth image information of the oral patient on line in real time, and classifying and outputting the tooth image information and the trained standard model library so as to output a tooth colorimetric detection result. The invention establishes a standard tooth colorimetric plate library characteristic information model based on a rapid regional full convolution neural network deep learning algorithm, thereby realizing the purpose of rapid, convenient and accurate tooth colorimetric detection of a patient with tooth restoration, and the invention has the advantages that: on-line real-time monitoring, simplicity, convenience, high accuracy and tooth colorimetric detection.
Description
Technical Field
The invention relates to an artificial intelligent image processing technology and an oral cavity detection method, in particular to a tooth colorimetric detection method and system based on a fast regional full convolution neural network (fast-RCNN).
Background
The fourth national oral health epidemiological survey of the national ministry of health shows that the problem of tooth loss is serious, and tooth restoration becomes a popular oral treatment. The full-ceramic tooth is an ideal prosthesis and is characterized by good morphological function, vivid color and appearance, no deformation, strong breaking resistance, smooth surface, good safety, stable color and luster and strong wear resistance. With the continuous improvement of living standard of people, the requirements on the restoration of the defect of the tooth body are higher and higher, so that not only the restoration of the function is required, but also the color and luster are required to be closer to the natural tooth. Therefore, color selection is particularly important in the tooth restoration process. In clinic, the color selection of the whole porcelain tooth mainly depends on the dentist to select the color model which is matched with the color of the patient tooth on the color shade guide by means of visual perception. This colorimetric approach relies heavily on visual observation and subjective judgment by the dentist, and does not have a reliable, qualitative data analysis. Moreover, in the artificial color selection process, external factors such as subjective impression of human eyes and ambient lighting environment have great influence on the color selection result. Therefore, a standard, simple and accurate means is needed to help dentists to assist in selecting proper colors, so that the color comparison accuracy can be improved, the burden of the dentists is reduced, and the attractiveness of the dental restoration is improved.
With the development of high speed and intelligence of computer technology, artificial intelligence based on big data is gradually widely applied in various industries. Especially, the mode recognition and intelligent detection based on the visual image have wide application value. In the early stage, an image recognition processing algorithm is adopted, and is not applied and developed due to the reasons of poor real-time performance, low recognition degree, complex algorithm and the like. In recent years, image pattern online recognition has been rapidly developed and applied based on development of machine learning and application of a Graphics Processing Unit (GPU). Machine learning algorithms such as local direction histograms, Support Vector Machines (SVMs), neural networks, elastic graph matching and the like are widely applied to artificial intelligence recognition systems. The neural network has good characteristic learning ability, and the network classification recognition graph is formed by simulating the learning process of human without manually setting the characteristics and training and learning the samples of the system. The neural network involved in the learning process of the deep learning method exceeds one hidden layer, so that the characteristics of a learning object can be more accurately obtained, the complex object can be better learned, and excellent performance is shown in pattern recognition and detection.
Disclosure of Invention
The invention provides a tooth colorimetric detection method and system based on a rapid regional full convolution neural network, aiming at rapid, convenient and accurate tooth colorimetric detection.
The invention solves the technical problems through the following technical scheme:
the invention provides a tooth colorimetric detection method based on a rapid regional full convolution neural network, which is characterized by comprising the following steps of:
s1, sampling each standard tooth in the colorimetric plate tooth library for multiple times by using the data information acquisition system to obtain multiple map data to form a tooth colorimetric plate chart library;
s2, performing model training and learning on the colorimetric board gallery by using a rapid regional full convolution neural network algorithm and establishing a standard model gallery;
and S3, collecting tooth image information of the oral patient on line in real time, and classifying and outputting the tooth image information and the trained standard model library so as to output a tooth colorimetric detection result.
Preferably, in step S1, the data information collecting system includes a light source, an optical lens, a camera, an image collecting card, an image processor system, a display and a controller.
Preferably, in step S2, the fast domain full convolution neural network algorithm is a five-layered ZF network, and first a 1 × 3 × 224 raw picture data is input, and after being processed by a convolution kernel of 7 × 7 with a step size set to 2, a characteristic image of 55 × 96 is output through a 2 × 2 pooling layer; after 5 × 5 convolution kernel processing with step size set to 2, a 27 × 256 feature image is output through a 2 × 2 pooling layer; after being processed by a convolution kernel of 3 × 3 with step size set to 1, a feature image of 13 × 384 is output through a 2 × 2 pooling layer; after 3 × 3 convolution kernel processing with the step size set to 1, a 13 × 384 feature image is output, and finally, after 3 × 3 convolution kernel processing with the step size set to 1, a 13 × 256 feature image is output, and then classification modeling is performed.
Preferably, in step S3, the tooth image information of the oral patient is acquired online in real time, image preprocessing is performed, and the preprocessing result is input into the trained standard model library for automatic recognition, classification and output, so as to output the tooth colorimetric detection result.
The invention also provides a tooth colorimetric detection system based on the rapid regional full convolution neural network, which is characterized by comprising a data information acquisition system, a training module and an acquisition and analysis module;
the data information acquisition system is used for sampling each standard tooth in the colorimetric plate tooth library for multiple times so as to obtain multiple map data to form a tooth colorimetric plate chart library;
the training module is used for carrying out model training and learning on the colorimetric plate diagram library by using a rapid regional full convolution neural network algorithm and establishing a standard model library;
the acquisition and analysis module is used for acquiring tooth image information of the oral patient in real time on line and carrying out classified output on the tooth image information and the trained standard model library so as to output a tooth colorimetric detection result.
Preferably, the data information acquisition system comprises a light source, an optical lens, a camera, an image acquisition card, an image processor system, a display and a controller.
Preferably, the fast regional full convolution neural network algorithm is a five-layer ZF network, and first, data of a 1 × 3 × 224 original picture is input, and after being processed by a convolution kernel of 7 × 7 with a step size set to 2, a characteristic image of 55 × 96 is output through a 2 × 2 pooling layer; after 5 × 5 convolution kernel processing with step size set to 2, a 27 × 256 feature image is output through a 2 × 2 pooling layer; after being processed by a convolution kernel of 3 × 3 with step size set to 1, a feature image of 13 × 384 is output through a 2 × 2 pooling layer; after 3 × 3 convolution kernel processing with the step size set to 1, a 13 × 384 feature image is output, and finally, after 3 × 3 convolution kernel processing with the step size set to 1, a 13 × 256 feature image is output, and then classification modeling is performed.
Preferably, the acquisition and analysis module is used for acquiring tooth image information of the oral patient in real time on line, performing image preprocessing, inputting a preprocessing result into a trained standard model library for automatic identification and classification output, and outputting a tooth colorimetric detection result.
On the basis of the common knowledge in the field, the above preferred conditions can be combined randomly to obtain the preferred embodiments of the invention.
The positive progress effects of the invention are as follows:
the invention establishes a standard tooth colorimetric plate library characteristic information model based on a rapid regional full convolution neural network deep learning algorithm, thereby realizing the purpose of rapid, convenient and accurate tooth colorimetric detection of a patient with tooth restoration, and the invention has the advantages that: on-line real-time monitoring, simplicity, convenience, high accuracy and tooth colorimetric detection.
Drawings
Fig. 1 is a flowchart of a tooth colorimetric detection method based on a fast regional full convolution neural network according to this embodiment.
Fig. 2 is a schematic diagram of the data information acquisition system of the present embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, the present embodiment provides a tooth colorimetric detection method based on a fast regional full convolution neural network, which includes the following steps:
Referring to fig. 2, the data information collecting system includes a light source 1, an optical lens 2, a camera 3, an image collecting card 4, an image processor system 5, a display 6 and a controller 7.
Based on 36 tooth colorimetric base colors, the data information acquisition system samples 10 times of images of each standard tooth of a colorimetric plate tooth library by Canon EOS-6D sampled by a camera under the condition of 24-105mm/4L, and acquires 360 kinds of map data to form a tooth colorimetric plate library.
And 102, performing model training and learning on the colorimetric plate gallery by using a rapid regional full convolution neural network algorithm and establishing a standard model gallery.
In step 102, the fast zone full convolution neural network algorithm is a five-layer ZF network, and first, 1 × 3 × 224 raw picture data is input, and after being processed by a convolution kernel of 7 × 7 with a step size set to 2, a characteristic image of 55 × 96 is output through a 2 × 2 pooling layer; after 5 × 5 convolution kernel processing with step size set to 2, a 27 × 256 feature image is output through a 2 × 2 pooling layer; after being processed by a convolution kernel of 3 × 3 with step size set to 1, a feature image of 13 × 384 is output through a 2 × 2 pooling layer; after 3 × 3 convolution kernel processing with the step size set to 1, a 13 × 384 feature image is output, and finally, after 3 × 3 convolution kernel processing with the step size set to 1, a 13 × 256 feature image is output, and then classification modeling is performed.
And 103, acquiring tooth image information of the oral patient in real time on line, and performing classified output on the tooth image information and the trained standard model library so as to output a tooth colorimetric detection result.
In step 103, tooth image information of the oral patient is acquired on line in real time, image preprocessing is performed, and a preprocessing result is input into a trained standard model library for automatic recognition, classification and output, so that a tooth colorimetric detection result is output.
The embodiment also provides a tooth colorimetric detection system based on the rapid regional full convolution neural network, which comprises a data information acquisition system, a training module and an acquisition and analysis module.
The data information acquisition system is used for sampling each standard tooth in the colorimetric plate tooth library for multiple times so as to obtain a plurality of map data to form a tooth colorimetric plate chart library.
The training module is used for carrying out model training and learning on the colorimetric plate diagram base by using a rapid regional full convolution neural network algorithm and establishing a standard model base.
The acquisition and analysis module is used for acquiring tooth image information of the oral patient in real time on line and carrying out classified output on the tooth image information and the trained standard model library so as to output a tooth colorimetric detection result.
The fast-RCNN algorithm directly inputs the whole detection image into the CNN for characteristic extraction; generating suggestion windows by using RPN (region probable network), wherein each image generates suggestion windows with characteristic quantity; mapping the suggestion window to the last layer of convolution characteristic graph of the CNN; generating a feature map of a fixed size for each ROI through the ROI pooling layer; and finally, performing regression joint training on the classification probability and the frame by using a detection classification probability and detection frame regression algorithm. Compared with other algorithms, the RPN is used for replacing the original selective search method to generate the suggestion window; the CNN for generating the suggestion window is shared with the CNN for target detection, so that the detection and identification speed is greatly improved. The method can be applied to tooth colorimetry to realize real-time monitoring, and is simple, convenient, reliable and accurate to realize tooth colorimetric detection.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that these are by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (8)
1. A tooth colorimetric detection method based on a rapid regional full convolution neural network is characterized by comprising the following steps:
s1, sampling each standard tooth in the colorimetric plate tooth library for multiple times by using the data information acquisition system to obtain multiple map data to form a tooth colorimetric plate chart library;
s2, performing model training and learning on the colorimetric board gallery by using a rapid regional full convolution neural network algorithm and establishing a standard model gallery;
and S3, collecting tooth image information of the oral patient on line in real time, and classifying and outputting the tooth image information and the trained standard model library so as to output a tooth colorimetric detection result.
2. The dental colorimetric detection method of claim 1, wherein in step S1, the data information acquisition system comprises a light source, an optical lens, a camera, an image acquisition card, an image processor system, a display and a controller.
3. The tooth colorimetric detection method based on the fast regional full convolution neural network as claimed in claim 1, characterized in that, in step S2, the fast regional full convolution neural network algorithm is a five-layer ZF network, firstly inputting a 1 x 3 x 224 raw picture data, after being processed by a convolution kernel of 7 x 7 with step size set as 2, outputting a characteristic image of 55 x 96 through a 2 x 2 pooling layer; after 5 × 5 convolution kernel processing with step size set to 2, a 27 × 256 feature image is output through a 2 × 2 pooling layer; after being processed by a convolution kernel of 3 × 3 with step size set to 1, a feature image of 13 × 384 is output through a 2 × 2 pooling layer; after 3 × 3 convolution kernel processing with the step size set to 1, a 13 × 384 feature image is output, and finally, after 3 × 3 convolution kernel processing with the step size set to 1, a 13 × 256 feature image is output, and then classification modeling is performed.
4. The tooth colorimetric detection method based on the fast regional full convolution neural network as claimed in claim 1, wherein in step S3, tooth image information of the oral patient is acquired on line in real time, image preprocessing is performed, and the preprocessed result is inputted into a trained standard model library for automatic recognition and classification output, so as to output the tooth colorimetric detection result.
5. A tooth colorimetric detection system based on a rapid regional full convolution neural network is characterized by comprising a data information acquisition system, a training module and an acquisition and analysis module;
the data information acquisition system is used for sampling each standard tooth in the colorimetric plate tooth library for multiple times so as to obtain multiple map data to form a tooth colorimetric plate chart library;
the training module is used for carrying out model training and learning on the colorimetric plate diagram library by using a rapid regional full convolution neural network algorithm and establishing a standard model library;
the acquisition and analysis module is used for acquiring tooth image information of the oral patient in real time on line and carrying out classified output on the tooth image information and the trained standard model library so as to output a tooth colorimetric detection result.
6. The dental colorimetric detection system based on the fast regional full convolutional neural network of claim 5, wherein the data information acquisition system comprises a light source, an optical lens, a camera, an image acquisition card, an image processor system, a display and a controller.
7. The tooth colorimetric detection system based on the fast regional full convolution neural network as claimed in claim 5, characterized in that, the fast regional full convolution neural network algorithm is a five-layer ZF network, firstly, 1 x 3 x 224 original picture data is input, after being processed by convolution kernel of 7 x 7 with step size set as 2, a characteristic image of 55 x 96 is output through a 2 x 2 pooling layer; after 5 × 5 convolution kernel processing with step size set to 2, a 27 × 256 feature image is output through a 2 × 2 pooling layer; after being processed by a convolution kernel of 3 × 3 with step size set to 1, a feature image of 13 × 384 is output through a 2 × 2 pooling layer; after 3 × 3 convolution kernel processing with the step size set to 1, a 13 × 384 feature image is output, and finally, after 3 × 3 convolution kernel processing with the step size set to 1, a 13 × 256 feature image is output, and then classification modeling is performed.
8. The dental colorimetric detection system based on the fast regional full convolution neural network as claimed in claim 5, wherein the collecting and analyzing module is used for collecting dental image information of the oral patient on line in real time, performing image preprocessing, inputting a preprocessing result into a trained standard model library for automatic recognition and classification output, and outputting a dental colorimetric detection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010317099.3A CN111652839A (en) | 2020-04-21 | 2020-04-21 | Tooth colorimetric detection method and system based on rapid regional full convolution neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010317099.3A CN111652839A (en) | 2020-04-21 | 2020-04-21 | Tooth colorimetric detection method and system based on rapid regional full convolution neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111652839A true CN111652839A (en) | 2020-09-11 |
Family
ID=72348228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010317099.3A Pending CN111652839A (en) | 2020-04-21 | 2020-04-21 | Tooth colorimetric detection method and system based on rapid regional full convolution neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111652839A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037913A (en) * | 2020-09-15 | 2020-12-04 | 南昌大学 | Intelligent periodontitis detection method and system based on convolutional neural network |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6206691B1 (en) * | 1998-05-20 | 2001-03-27 | Shade Analyzing Technologies, Inc. | System and methods for analyzing tooth shades |
| JP2002369833A (en) * | 2001-06-15 | 2002-12-24 | J Morita Tokyo Mfg Corp | Tooth color identification method and tooth color judging device based on spectroscopic characteristics of teeth |
| US20050074718A1 (en) * | 2003-10-03 | 2005-04-07 | Pye Graham | Tooth shade scan system and method |
| JP2009053160A (en) * | 2007-08-29 | 2009-03-12 | Olympus Corp | Dental colorimetric device |
| CN106875386A (en) * | 2017-02-13 | 2017-06-20 | 苏州江奥光电科技有限公司 | A kind of method for carrying out dental health detection automatically using deep learning |
| US20170206431A1 (en) * | 2016-01-20 | 2017-07-20 | Microsoft Technology Licensing, Llc | Object detection and classification in images |
| CN107607554A (en) * | 2017-09-26 | 2018-01-19 | 天津工业大学 | A kind of Defect Detection and sorting technique of the zinc-plated stamping parts based on full convolutional neural networks |
| CN110349224A (en) * | 2019-06-14 | 2019-10-18 | 众安信息技术服务有限公司 | A kind of color of teeth value judgment method and system based on deep learning |
| US20190333627A1 (en) * | 2018-04-25 | 2019-10-31 | Sota Precision Optics, Inc. | Dental imaging system utilizing artificial intelligence |
| CN110569792A (en) * | 2019-09-09 | 2019-12-13 | 吉林大学 | Method for detecting front object of automatic driving automobile based on convolutional neural network |
| CN110909756A (en) * | 2018-09-18 | 2020-03-24 | 苏宁 | Convolutional neural network model training method and device for medical image recognition |
-
2020
- 2020-04-21 CN CN202010317099.3A patent/CN111652839A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6206691B1 (en) * | 1998-05-20 | 2001-03-27 | Shade Analyzing Technologies, Inc. | System and methods for analyzing tooth shades |
| JP2002369833A (en) * | 2001-06-15 | 2002-12-24 | J Morita Tokyo Mfg Corp | Tooth color identification method and tooth color judging device based on spectroscopic characteristics of teeth |
| US20050074718A1 (en) * | 2003-10-03 | 2005-04-07 | Pye Graham | Tooth shade scan system and method |
| JP2009053160A (en) * | 2007-08-29 | 2009-03-12 | Olympus Corp | Dental colorimetric device |
| US20170206431A1 (en) * | 2016-01-20 | 2017-07-20 | Microsoft Technology Licensing, Llc | Object detection and classification in images |
| CN106875386A (en) * | 2017-02-13 | 2017-06-20 | 苏州江奥光电科技有限公司 | A kind of method for carrying out dental health detection automatically using deep learning |
| CN107607554A (en) * | 2017-09-26 | 2018-01-19 | 天津工业大学 | A kind of Defect Detection and sorting technique of the zinc-plated stamping parts based on full convolutional neural networks |
| US20190333627A1 (en) * | 2018-04-25 | 2019-10-31 | Sota Precision Optics, Inc. | Dental imaging system utilizing artificial intelligence |
| CN110909756A (en) * | 2018-09-18 | 2020-03-24 | 苏宁 | Convolutional neural network model training method and device for medical image recognition |
| CN110349224A (en) * | 2019-06-14 | 2019-10-18 | 众安信息技术服务有限公司 | A kind of color of teeth value judgment method and system based on deep learning |
| CN110569792A (en) * | 2019-09-09 | 2019-12-13 | 吉林大学 | Method for detecting front object of automatic driving automobile based on convolutional neural network |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037913A (en) * | 2020-09-15 | 2020-12-04 | 南昌大学 | Intelligent periodontitis detection method and system based on convolutional neural network |
| CN112037913B (en) * | 2020-09-15 | 2022-08-30 | 南昌大学 | Periodontitis intelligent detection system based on convolutional neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111563887B (en) | Intelligent analysis method and device for oral cavity image | |
| CN109948476B (en) | Human face skin detection system based on computer vision and implementation method thereof | |
| CN108280426B (en) | Dark light source expression identification method and device based on transfer learning | |
| CN110619301A (en) | Emotion automatic identification method based on bimodal signals | |
| CN109919938B (en) | Method for obtaining optic disc segmentation atlas of glaucoma | |
| KR20200110878A (en) | A system and method for early diagnosing dental caries based on the deep learning | |
| CN111666845B (en) | Small sample deep learning multi-mode sign language recognition method based on key frame sampling | |
| CN112967285A (en) | Chloasma image recognition method, system and device based on deep learning | |
| CN111091109A (en) | Method, system and equipment for predicting age and gender based on face image | |
| CN111145865A (en) | Vision-based hand fine motion training guidance system and method | |
| CN113240647A (en) | Mobile phone shell rear cover defect detection method and system based on deep learning | |
| CN115375991A (en) | Strong/weak illumination and fog environment self-adaptive target detection method | |
| CN117764957A (en) | Glaucoma image feature extraction training system based on artificial neural network | |
| CN111652839A (en) | Tooth colorimetric detection method and system based on rapid regional full convolution neural network | |
| CN110135391A (en) | System is matched using the program and spectacle-frame of computer apolegamy spectacle-frame | |
| CN112488165A (en) | Infrared pedestrian identification method and system based on deep learning model | |
| CN112700409A (en) | Automatic retinal microaneurysm detection method and imaging method | |
| CN115116117A (en) | Learning input data acquisition method based on multi-mode fusion network | |
| CN113673378A (en) | Face recognition method and device based on binocular camera and storage medium | |
| CN112052721A (en) | Wink oscillogram generation method, device and equipment based on deep learning | |
| Lamge et al. | Skin disease detection and classification using image processing algorithm | |
| CN114565506B (en) | Image color migration method, device, equipment and storage medium | |
| CN108939409A (en) | Cloud computing type speed modification method | |
| CN108022246A (en) | A kind of preposition Image Automatic Segmentation system for lingual surface instrument | |
| CN114419711B (en) | Concentration degree identification method based on AI (artificial intelligence) education system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200911 |