Intelligent oral hygiene auxiliary monitoring and early warning system and method

Abstract

The invention provides an intelligent oral hygiene auxiliary monitoring and early warning system and method.The system comprises an electric toothbrush, the electric toothbrush comprises a brush handle and a brush head, the brush head is provided with bristles, the system further comprises an oral hygiene auxiliary inspection system, and the oral hygiene auxiliary inspection system comprises a microprocessor, a lighting module, an image acquisition module, a storage module and a display module; the brush head is provided with a lighting module and an image acquisition module, the image acquisition module acquires an original tooth image in an oral cavity and sends the original tooth image to the microprocessor, and the microprocessor analyzes and processes the received original tooth image to obtain tooth image information including a tooth image, a plaque image and position positioning information of the plaque image; the tooth image information is sent to a display module for visual plaque position image early warning; according to the invention, the electric toothbrush is taken as a carrier, and cariogenic dental plaque hidden in the visual blind area in the oral cavity can be automatically identified by acquiring the tooth image information in the oral cavity, so that effective monitoring and identification of the dental plaque are realized.

Description

Technical Field

[0001] The invention relates to an intelligent oral hygiene auxiliary monitoring and early warning system and method, belonging to the technical field of intelligent monitoring and early warning. Background Art

[0002] According to statistics, nearly half of the world's population suffers from oral diseases, among which caries (tooth decay) is the most common. It is an infectious disease that causes chronic and progressive destruction of tooth tissue under the action of multiple factors, mainly bacteria. The simplest and most effective way to prevent caries is to brush your teeth correctly. By brushing your teeth correctly, you can effectively remove plaque and soft scale on the tooth surface and maintain the health of teeth and gums.

[0003] The Bass method is an internationally recognized method of brushing teeth that can help achieve correct and effective toothbrushing. However, due to the failure to strictly follow the toothbrush angle and brushing time during toothbrushing, most toothbrushing effects fail to reach the ideal state, resulting in caries-causing plaque in certain parts of the teeth not being cleaned, increasing the risk of tooth caries. Moreover, caries-causing plaque in these specific parts is often in the blind spot of vision, making it difficult to detect and identify its existence.

[0004] Therefore, based on the current Bass brushing method, an intelligent oral hygiene auxiliary monitoring and early warning system with an electric toothbrush as the carrier is needed to help discover and identify caries-causing plaque hidden in the blind spots of the field of vision and issue early warning information in time to assist in the protection of oral hygiene. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent oral hygiene auxiliary monitoring and early warning system and method to solve the problem in the prior art that plaque on the oral dentition in the blind area of ​​the visual field is difficult to monitor and effectively identify.

[0006] The technical solution of the present invention is: An intelligent oral hygiene auxiliary monitoring and early warning system comprises an electric toothbrush, wherein the electric toothbrush comprises a brush handle and a brush head, wherein the brush head is provided with bristles, and further comprises an oral hygiene auxiliary inspection system, wherein the oral hygiene auxiliary inspection system comprises a microprocessor, a lighting module, an image acquisition module, a storage module and a display module, wherein the brush head is provided with the lighting module and the image acquisition module, wherein the lighting module, the image acquisition module and the storage module are respectively connected to the microprocessor, wherein the image acquisition module obtains an original tooth image in the oral cavity and sends the image to the microprocessor, wherein the microprocessor analyzes and processes the received original tooth image to obtain tooth image information including a tooth image, a plaque image and position information of the plaque image, wherein the tooth image information is sent to the storage module for storage, and wherein the tooth image information is sent to the display module for visualizing a plaque position image early warning.

[0007] Furthermore, the microprocessor includes a visual guidance module, an image segmentation module, an image recognition module and an early warning module. Visualization guidance module: according to the set acquisition sequence in the dental image, the display module visually guides the user to acquire the original dental image of the corresponding set area through the image acquisition module according to the set acquisition sequence; Image segmentation module: Based on the set image acquisition order, the original tooth image is segmented according to the two types of position features of tooth position and tooth surface to obtain the segmented image, the segmented image is numbered with position information to obtain image position positioning information, and the segmented image and the corresponding image position positioning information are sent to the image recognition module; Image recognition module: analyzes and processes the received segmented image and the corresponding image position information to obtain a tooth image, a plaque image and the plaque image position information; Early warning module: receives the plaque image position information from the image recognition module, summarizes it, and classifies it according to the set dentition division area to obtain the dentition area information of the plaque image, and sends the dentition area information of the plaque image to the display module.

[0008] Furthermore, the image segmentation module includes a data preprocessing unit, a feature extraction unit, a model training unit, a model prediction unit and a post-processing unit. Data preprocessing unit: normalizes and denoises the original tooth image to obtain a preprocessed image; Feature extraction unit: uses a deep learning model to extract the features of the tooth image. The deep learning model includes a convolutional neural network (CNN) and a recurrent neural network (RNN). The convolutional neural network (CNN) is used to extract the spatial features of the tooth image, and the recurrent neural network (RNN) is used to extract the sequence features. Model training unit: input the features of the extracted tooth images into the classification and regression models for training. The classification and regression models include support vector machine SVM, naive Bayes NB and multi-task learning MTL. Support vector machine SVM and naive Bayes NB are used as classification models, and multi-task learning MTL is used as regression model. The cross-validation method is used in the training process to obtain the trained classification and regression models. Model prediction unit: Use the trained classification and regression models to segment the original tooth image and obtain the segmentation result; Post-processing unit: Use non-maximum suppression (NMS) to post-process the segmentation result to obtain the segmented image.

[0009] Furthermore, in the image segmentation module, the segmented images are numbered with position information as follows: Assign a unique identifier to each segmented image using either numerical or color coding; Use a label management system to assign unique labels to each region for data management during model training and inference; Clustering algorithms, feature matching, and geometric constraint methods are used to further optimize the numbering of location information.

[0010] Furthermore, in the visualization guidance module, the acquisition order in the maxillary dentition image is set to numbers 11-18, and the corresponding set areas are the labial side of the anterior teeth, the palatal side of the anterior teeth, the buccal side of the right posterior teeth, the maxillary side of the right posterior teeth, the palatal side of the right posterior teeth, the buccal side of the left posterior teeth, the maxillary side of the left posterior teeth and the palatal side of the left posterior teeth.

[0011] Furthermore, in the visualization guidance module, the acquisition order in the dentition image of the mandibular teeth is set to numbers 19, 110-116, and the corresponding set areas are the labial side of the anterior teeth, the palatal side of the anterior teeth, the buccal side of the right posterior teeth, the maxillary side of the right posterior teeth, the palatal side of the right posterior teeth, the buccal side of the left posterior teeth, the maxillary side of the left posterior teeth and the palatal side of the left posterior teeth.

[0012] A method of using any of the above-mentioned intelligent oral hygiene auxiliary monitoring and early warning systems comprises the following steps: After the microprocessor controls the lighting module to be turned on, the oral hygiene auxiliary inspection system visually guides the user to obtain the original tooth image of the corresponding set area through the image acquisition module according to the set acquisition sequence, and sends the original tooth image to the microprocessor; The microprocessor analyzes and processes the received original tooth image to obtain tooth image information including tooth image, plaque image and location information of the plaque image, sends the tooth image information to the storage module for storage, and sends the tooth image information to the display module for visual plaque location image warning.

[0013] The beneficial effects of the present invention are as follows: the intelligent oral hygiene auxiliary monitoring and early warning system and method, using an electric toothbrush as a carrier, can automatically identify caries-causing plaque hidden in the blind area of ​​the oral cavity by acquiring the image information of the teeth in the oral cavity, and achieve effective monitoring, identification and early warning of dental plaque, with the advantages of real-time monitoring, high identification accuracy and timely early warning of the location of plaque. By dividing the dentition into order and regions, the regional positioning of the plaque location can be achieved, so as to facilitate further treatment of the plaque. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a schematic diagram illustrating an intelligent oral hygiene auxiliary monitoring and early warning system according to an embodiment of the present invention; Figure 2 is a schematic diagram illustrating an oral hygiene auxiliary inspection system in an embodiment; Figure 3 is a schematic diagram for explaining a dentition image in a visualization guidance module in an embodiment; Figure 4 It is a flow chart of an intelligent oral hygiene auxiliary monitoring and early warning method of an embodiment; Among them: 1-brush handle, 2-brush head, 3-brush bristles, 4-microprocessor, 5-illumination module, 6-image acquisition module, 7-storage module, 8-display module. DETAILED DESCRIPTION

[0015] The preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0016] The embodiment provides an intelligent oral hygiene auxiliary monitoring and early warning system, such as Figure 1 and Figure 2 , including an electric toothbrush, the electric toothbrush includes a brush handle 1 and a brush head 2, the brush head 2 is provided with bristles 3, and also includes an oral hygiene auxiliary inspection system, the oral hygiene auxiliary inspection system includes a microprocessor 4, a lighting module 5, an image acquisition module 6, a storage module 7 and a display module 8, the brush head 2 is provided with a lighting module 5 and an image acquisition module 6, the lighting module 5, the image acquisition module 6 and the storage module 7 are respectively connected to the microprocessor 4, the image acquisition module 6 obtains the original tooth image in the oral cavity and sends it to the microprocessor 4, the microprocessor 4 analyzes and processes the received original tooth image to obtain tooth image information including tooth image, plaque image and position positioning information of the plaque image, sends the tooth image information to the storage module 7 for storage, and sends the tooth image information to the display module 8 for visual plaque position image warning.

[0017] This intelligent oral hygiene auxiliary monitoring and early warning system uses an electric toothbrush as a carrier. By acquiring the image information of teeth in the oral cavity, it can automatically identify caries-causing plaque hidden in the blind spots of the oral field, thereby achieving effective monitoring, identification and early warning of dental plaque. It has the advantages of real-time monitoring, high-accuracy identification and timely early warning of plaque location.

[0018] The microprocessor 4 includes a visual guidance module, an image segmentation module, an image recognition module and an early warning module.

[0019] Visualization guidance module: Based on the set acquisition sequence in the dental image, the display module 8 visually guides the user to acquire the original dental image of the corresponding set area through the image acquisition module 6 according to the set acquisition sequence.

[0020] like Figure 3In the visualization guidance module, the dentition area is divided and represented by numbers: (i) The maxillary dentition is divided into 8 areas: the labial side of the anterior teeth (number: 11), the palatal side of the anterior teeth (number: 12), the buccal side of the right posterior teeth (number: 13), the maxillary surface of the right posterior teeth (number: 14), the palatal side of the right posterior teeth (number: 15), the buccal side of the left posterior teeth (number: 16), the maxillary surface of the left posterior teeth (number: 17), and the palatal side of the left posterior teeth (number: 18). (ii) The mandibular dentition is divided into 8 areas: the labial side of the anterior teeth (number: 19), the palatal side of the anterior teeth (number: 110), the buccal side of the right posterior teeth (number: 111), the maxillary surface of the right posterior teeth (number: 112), the palatal side of the right posterior teeth (number: 113), the buccal side of the left posterior teeth (number: 114), the maxillary surface of the left posterior teeth (number: 115), and the palatal side of the left posterior teeth (number: 116). The image acquisition sequence adopted in the embodiment is as follows: the images are acquired in the order of the numbers of the dental arch division areas, from front to back and from right to left.

[0021] Image segmentation module: Based on the set image acquisition order, the original tooth image is segmented according to the two types of positional features of tooth position and tooth surface to obtain the segmented image, the segmented image is numbered with position information to obtain the image position positioning information, and the segmented image and the corresponding image position positioning information are sent to the image recognition module.

[0022] The image segmentation module includes a data preprocessing unit, a feature extraction unit, a model training unit, a model prediction unit and a post-processing unit.

[0023] Data preprocessing unit: normalizes the input raw tooth image to eliminate the differences in shooting conditions between devices. Then, denoising is performed, using a bilateral filter to remove image noise while maintaining edge information to obtain a preprocessed image and improve image quality; Feature extraction unit: uses a deep learning model to extract the features of the tooth image. The deep learning model includes a convolutional neural network (CNN) and a recurrent neural network (RNN). The convolutional neural network (CNN) is used to extract the spatial features of the tooth image, and the recurrent neural network (RNN) is used to extract the sequence features. Model training unit: input the features of the extracted tooth images into the classification and regression models for training. The classification and regression models include support vector machine SVM, naive Bayes NB and multi-task learning MTL. Support vector machine SVM and naive Bayes NB are used as classification models, and multi-task learning MTL is used as regression model. The cross-validation method is used in the training process to obtain the trained classification and regression models to evaluate the performance and generalization ability of the models. Model prediction unit: Use the trained classification and regression models to segment the original tooth image and obtain the segmentation result; Post-processing unit: Use non-maximum suppression (NMS) to post-process the segmentation result to obtain the segmented image, thereby reducing mis-segmentation and improving segmentation accuracy.

[0024] In the image segmentation module, the feature extraction unit selects a suitable model to describe the structure of teeth according to the characteristics of teeth, including shape, size, and texture. Common tooth models include round, elliptical, and pointed shapes. After inputting the image into the model and making predictions, the features related to the tooth surface are extracted from the output results. These features include information such as the position, shape, color, and texture of the teeth. To extract features from the image, CNN is used to extract spatial features, and RNN is used to extract sequence features, so as to facilitate the recognition of images of teeth and plaque. The segmentation results can be visualized to display images of teeth and plaque. At the same time, the model performance is evaluated by indicators such as precision, recall, and F1 score.

[0025] In the image segmentation module, the original tooth image is first preprocessed, and then the deep learning model is used to extract features and segment the image. To ensure the accuracy of the segmentation, the model is then trained and post-processed after prediction. The segmented image is numbered with digital or color coding to facilitate subsequent analysis and application.

[0026] In the image segmentation module, the segmented images are numbered with position information, specifically, 1) Assign a unique identifier to each segmented region using numerical or color coding; A digital code is used to assign a unique identifier to each segmented region. Specifically, the labial side of the anterior teeth is numbered 11, the palatal side of the anterior teeth is numbered 12, and so on.

[0027] 2) Use label management systems such as SIFT feature detection, SURF feature detection, and ORB feature detection to assign a unique label to each region for data management during model training and inference.

[0028] Among them, the method of using the ORB feature detector to extract features from the preprocessed image is: For each segmented area, all ORB feature points in the area are extracted and used to generate a unique feature descriptor (i.e., label); the digital code of each area is associated with its ORB feature descriptor and stored in a label management system. The segmented images with digital codes are used as training data for model training to help the model better understand and identify different tooth areas; 3) Clustering algorithms such as K-means are used to cluster the segmented areas, and feature matching (such as FLANN) and geometric constraint methods (such as distance constraints) are used to further optimize the numbering of location information.

[0029] Image recognition module: Analyze and process the received segmented image and the corresponding image position information to obtain the tooth image, plaque image and plaque image position information.

[0030] The image recognition module uses a tooth image recognition model based on a fully connected convolutional neural network (FCN) to obtain tooth images and plaque images. The model uses a binary cross entropy loss function to measure the accuracy of the model output:

[0031] in, is the loss function, which is used to evaluate the difference between the model output and the target true value, where x Represents the probability distribution of the model output; N is the height of the image, M is the width of the image, N×M, that is, the height of the image multiplied by the width, is the total number of pixels in the image; i, j represent the row index and column index of the pixel in the image, respectively, which are used to traverse each pixel in the image; is the true label, which indicates the target object at pixel point (i, j), including the true category of teeth and plaque; is the probability predicted by the model, that is, the probability that the model believes that the pixel point (i, j) belongs to the target category; is the natural logarithm of the model's predicted probability.

[0032] In the tooth image recognition model based on the fully connected convolutional neural network FCN, the input image x and the target label y are first converted into corresponding feature representations. Specifically, the image size is first adjusted to (32, 32), and then a convolution kernel of size (1, 1) is added to each pixel position to extract local features. Next, the feature map size is adjusted to (64, 64), and a convolution kernel of size (1, 1) is added to each pixel position, and so on. Finally, a feature map of size (256, 256) is obtained. This feature map contains the global context information of the image, but because the model only needs to consider the category of the pixel point, a 1×1 convolution kernel is added to the output of the last convolution layer to obtain the probability distribution of each pixel point. Next, this feature map is input into a fully connected layer to obtain the final model output.

[0033] In the model workflow, the input image x is first resized to an appropriate size of 32×32, and then image features are extracted through a series of convolutional layers. In these convolutional layers, convolution kernels of different sizes are used to capture the local spatial features and global contextual information of the image. (1,1) The convolution kernel is mainly used for the deep transformation of the feature map to integrate cross-channel information.

[0034] As the network goes deeper, the size of the feature map is usually gradually reduced through convolution or pooling operations to extract higher-level abstract features. However, in the convolutional neural network FCN, in order to perform pixel-level classification, that is, image segmentation, the feature map is restored to the size of the original image through an upsampling layer or combined with the feature map of the previous convolution layer. Ultimately, the model outputs a feature map of the same size as the input image, where each pixel corresponds to a predicted probability, indicating the possibility that the pixel belongs to the plaque category. This feature map is then fed into a softmax classifier to convert the predicted probability into a normalized probability distribution. By comparing the probability distribution predicted by the model with the true label, the loss function value can be calculated and used for model training and optimization.

[0035] Early warning module: receives the plaque image position positioning information from the image recognition module, summarizes it, and classifies it according to the set dentition division area to obtain the dentition area information of the plaque image, and sends the dentition area information of the plaque image to the display module 8.

[0036] This intelligent oral hygiene auxiliary monitoring and early warning system uses an electric toothbrush as the carrier of the system, which is divided into two parts: a brush handle 1 and a brush head 2: the brush handle 1 has a built-in system power supply, and the brush head 2 is mainly composed of bristles 3, which performs the toothbrushing work; the lighting module 5 is located at the brush head 2 of the electric toothbrush, on the back or side of the brush head 2, and provides the light source required for the system to work; the image acquisition module 6 is located on the back of the bristles 3 of the electric toothbrush, close to the lighting module 5, and collects the image information of the teeth in the oral cavity according to the set image acquisition sequence; the microprocessor 4 includes a visualization guidance module, an image segmentation module, an image recognition module and an early warning module, and the microprocessor 4 is located at the brush handle 1 of the electric toothbrush, and is responsible for receiving and analyzing the tooth image information collected by the image acquisition module 6: the image segmentation module is based on According to the set image acquisition sequence, the original tooth image is segmented according to the two types of position features, tooth position and tooth surface, and the segmented image is numbered with position information; the image recognition module receives the tooth image information with the position information number, detects and classifies the tooth image and plaque image in the image, completes the recognition and position positioning of the plaque image, and finally saves the plaque position information in the storage module 7 and sends it to the early warning module at the same time; the early warning module receives the plaque position information, summarizes the tooth position information where the plaque exists, and classifies it according to the set dentition division area, and finally transmits the information of the dentition area where the plaque is located to the display module 8. The display module 8 can use a mobile phone terminal or a touch screen installed on the brush handle 1, etc. The display module 8 performs a visual plaque position image early warning.

[0037] like Figure 4 The embodiment provides a method of using any of the above-mentioned intelligent oral hygiene auxiliary monitoring and early warning systems, comprising the following steps: After the microprocessor 4 controls to turn on the lighting module 5, the oral hygiene auxiliary inspection system visually guides the user to obtain the original tooth image of the corresponding set area through the image acquisition module 6 according to the set acquisition sequence, and sends the original tooth image to the microprocessor 4; The microprocessor 4 analyzes and processes the received original tooth image to obtain tooth image information including tooth image, plaque image and location information of the plaque image, sends the tooth image information to the storage module 7 for storage, and sends the tooth image information to the display module 8 for visual plaque location image warning.

[0038] This intelligent oral hygiene auxiliary monitoring and early warning system and method can automatically identify caries-causing plaque hidden in the blind spots of the oral field. At the same time, it divides the dentition into regions according to clinical characteristics and determines a specific inspection sequence. Ultimately, the system can issue timely and accurate early warning information on the location of plaque based on the dentition region, assisting users in protecting their oral hygiene.

[0039] The above are only preferred embodiments of the present invention, but do not limit the patent scope of the present invention. Although the present invention is described in detail with reference to the above embodiments, those skilled in the art can still modify the technical solutions recorded in the above embodiments, or replace some of the technical features with equivalent ones. Any equivalent structure made by using the contents of the present invention specification and drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present invention.

Claims

1. An intelligent oral hygiene auxiliary monitoring and early warning system, comprising an electric toothbrush, the electric toothbrush comprising a brush handle and a brush head, the brush head being provided with bristles, characterized in that: It also includes an oral hygiene auxiliary inspection system, which includes a microprocessor, a lighting module, an image acquisition module, a storage module and a display module. The brush head is provided with a lighting module and an image acquisition module, and the lighting module, the image acquisition module and the storage module are respectively connected to the microprocessor. The image acquisition module obtains the original tooth image in the oral cavity and sends it to the microprocessor. The microprocessor analyzes and processes the received original tooth image to obtain tooth image information including tooth image, plaque image and position positioning information of the plaque image, sends the tooth image information to the storage module for storage, and sends the tooth image information to the display module for visual plaque position image warning.

2. The intelligent oral hygiene auxiliary monitoring and early warning system according to claim 1, characterized in that: The microprocessor includes a visual guidance module, an image segmentation module, an image recognition module and an early warning module. Visualization guidance module: according to the set acquisition sequence in the dental image, the display module visually guides the user to acquire the original dental image of the corresponding set area through the image acquisition module according to the set acquisition sequence; Image segmentation module: Based on the set image acquisition order, the original tooth image is segmented according to the two types of position features of tooth position and tooth surface to obtain the segmented image, the segmented image is numbered with position information to obtain image position positioning information, and the segmented image and the corresponding image position positioning information are sent to the image recognition module; Image recognition module: analyzes and processes the received segmented image and the corresponding image position information to obtain a tooth image, a plaque image and the plaque image position information; Early warning module: receives the plaque image position information from the image recognition module, summarizes it, and classifies it according to the set dentition division area to obtain the dentition area information of the plaque image, and sends the dentition area information of the plaque image to the display module.

3. The intelligent oral hygiene auxiliary monitoring and early warning system according to claim 2, characterized in that: The image segmentation module includes a data preprocessing unit, a feature extraction unit, a model training unit, a model prediction unit, and a post-processing unit. Data preprocessing unit: normalizes and denoises the original tooth image to obtain a preprocessed image; Feature extraction unit: uses a deep learning model to extract the features of the tooth image. The deep learning model includes a convolutional neural network (CNN) and a recurrent neural network (RNN). The convolutional neural network (CNN) is used to extract the spatial features of the tooth image, and the recurrent neural network (RNN) is used to extract the sequence features. Model training unit: input the features of the extracted tooth images into the classification and regression models for training. The classification and regression models include support vector machine SVM, naive Bayes NB and multi-task learning MTL. Support vector machine SVM and naive Bayes NB are used as classification models, and multi-task learning MTL is used as regression model. The cross-validation method is used in the training process to obtain the trained classification and regression models. Model prediction unit: Use the trained classification and regression models to segment the original tooth image and obtain the segmentation result; Post-processing unit: Use non-maximum suppression (NMS) to post-process the segmentation result to obtain the segmented image.

4. The intelligent oral hygiene auxiliary monitoring and early warning system according to claim 3, characterized in that: In the image segmentation module, the segmented images are numbered with position information as follows: Assign a unique identifier to each segmented image using either numerical or color coding; Use a label management system to assign unique labels to each region for data management during model training and inference; Clustering algorithms, feature matching, and geometric constraint methods are used to further optimize the numbering of location information.

5. The intelligent oral hygiene auxiliary monitoring and early warning system according to any one of claims 1 to 4, characterized in that: In the visualization guidance module, the acquisition order in the maxillary dentition image is set to numbers 11-18, and the corresponding set areas are the labial side of the anterior teeth, the palatal side of the anterior teeth, the buccal side of the right posterior teeth, the maxillary side of the right posterior teeth, the palatal side of the right posterior teeth, the buccal side of the left posterior teeth, the maxillary side of the left posterior teeth, and the palatal side of the left posterior teeth.

6. The intelligent oral hygiene auxiliary monitoring and early warning system according to any one of claims 1 to 4, characterized in that: In the visualization guidance module, the acquisition order in the mandibular dentition image is set to numbers 19, 110-116, and the corresponding set areas are the labial side of the anterior teeth, the palatal side of the anterior teeth, the buccal side of the right posterior teeth, the maxillary side of the right posterior teeth, the palatal side of the right posterior teeth, the buccal side of the left posterior teeth, the maxillary side of the left posterior teeth, and the palatal side of the left posterior teeth.

7. A method using the intelligent oral hygiene auxiliary monitoring and early warning system according to any one of claims 1 to 6, characterized in that: The following steps are included: After the microprocessor controls the lighting module to be turned on, the oral hygiene auxiliary inspection system visually guides the user to obtain the original tooth image of the corresponding set area through the image acquisition module according to the set acquisition sequence, and sends the original tooth image to the microprocessor; The microprocessor analyzes and processes the received original tooth image to obtain tooth image information including tooth image, plaque image and location information of the plaque image, sends the tooth image information to the storage module for storage, and sends the tooth image information to the display module for visual plaque location image warning.

Images