Oral cavity detection system

Abstract

An oral cavity detection system includes an image capturing device and a processor. The image capturing device is configured to output a visible light image and an ultraviolet light image. The processor is signal connected to the image capturing device and includes a tooth site recognition module, an image processing module, a tooth status detection module and a display module. The tooth site recognition module defines tooth site regions of the teeth in the visible light image and outputs a tooth site image. The image processing module is configured to convert the ultraviolet light image from an RGB color space to an HSV color space or an HSL color space to generate a fluorescent image, and to extract a fluorescent tooth image having a same range as each tooth site region. The tooth status detection module is configured to find a plaque block or a caries block on each fluorescent tooth image. The display module is configured to display the plaque block or the caries block on each tooth site region of the tooth site image. Thus, the time for manual inspection can be reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to an oral cavity detection system, and more particularly to an oral cavity detection system for detecting dental plaque or dental caries. BACKGROUND

[0002] Generally speaking, when checking whether the teeth have dental caries or other diseases, dentists often use an imaging device to take close-up photos of the oral cavity, and judge the amount of dental plaque on the teeth and whether there is a dental caries condition through the photographed images. In order to improve the efficiency of the dentist's examination, the industry today combines the imaging device with the processor, and displays the dental plaque range on each tooth position in the image according to a deep learning algorithm, and then manually judges by the dentist, which can only improve the efficiency to a limited extent.

[0003] Therefore, an oral cavity examination system that can effectively reduce the time-consuming artificial examination is still the common goal of the current related industry. SUMMARY

[0004] The present application provides an oral cavity detection system, which defines the tooth position of each tooth through a tooth position recognition module, and detects each tooth one by one through a tooth state detection module, and displays the dental plaque block or the dental caries block in each tooth position area with different colors, thereby greatly reducing the time-consuming artificial examination of dentists.

[0005] According to an embodiment of the present application, an oral cavity detection system is provided, which comprises an imaging device and a processor. The imaging device is used to take a photo of an oral cavity and output a plurality of visible light images and a plurality of ultraviolet light images, the visible light images comprising a plurality of tooth images corresponding to a plurality of teeth of the oral cavity, wherein the imaging device is used to take photos from the cheek side, the upper jaw and the lower jaw of the oral cavity to output the visible light images and the ultraviolet light images, and the number of tooth images is equal to the total number of teeth of the oral cavity. The processor is signal connected to the imaging device and receives the visible light images and the ultraviolet light images, and comprises a tooth position recognition module, an image processing module, a tooth state detection module and a display module. The tooth position recognition module defines a tooth position area of each tooth image according to the visible light images and through a bounding box method of an object detection algorithm, and numbers and outputs a tooth position image according to the appearance of each tooth image and the corresponding position characteristics in the oral cavity, the tooth position image comprising each tooth image and each tooth position area. The image processing module is used to convert the ultraviolet light images from the RGB color space to the HSV color space or the HSL color space to generate a plurality of fluorescent images, take out each tooth image corresponding to each tooth position area, and correspond to the fluorescent images to take out a fluorescent tooth image with the same range as each tooth position area. The tooth state detection module finds out a dental plaque block or a dental caries block on each fluorescent tooth image according to the hue, saturation and brightness of each fluorescent tooth image. The display module is used to display the dental plaque block or the dental caries block of each fluorescent tooth image in each tooth position area of the tooth position image with different colors.

[0006] The visible light and ultraviolet light images taken by the oral cavity can be analyzed and defined by the processor to define the tooth area of each tooth and to mark the plaque or caries block in each tooth area, so as to classify the detected decay state of each tooth, thereby greatly reducing the time consumed by the dentist in artificial inspection.

[0007] The oral cavity detection system according to the foregoing embodiment, wherein the image processing module can convert the ultraviolet light image from the RGB color space to the HSV color space to generate a fluorescent image, when a hue range of a fluorescent tooth image is 0°-30° or 330°-360°, a saturation of the fluorescent tooth image is greater than or equal to 65%, and a lightness of the fluorescent tooth image is less than or equal to 40%, the fluorescent tooth image has a caries block.

[0008] The oral cavity detection system according to the foregoing embodiment, wherein the image processing module can convert the ultraviolet light image from the RGB color space to the HSV color space to generate a fluorescent image, when a hue range of a fluorescent tooth image is 0°-30° or 330°-360°, a saturation of the fluorescent tooth image is greater than or equal to 65%, and a lightness of the fluorescent tooth image is less than or equal to 40%, the fluorescent tooth image has a caries block.

[0009] The oral cavity detection system according to the foregoing embodiment, wherein the tooth recognition module can find a tooth image area from the plurality of visible light images, detect the tooth in the tooth image area by implementing a segmentation method, classify the tooth, and output an instance segmentation tooth image; the tooth recognition module performs image normalization adjustment on the instance segmentation tooth image according to a preset brightness value.

[0010] The oral cavity detection system according to the foregoing embodiment, further comprising a database, and the processor outputs a detection record to the database according to the tooth image and the fluorescent tooth image. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 A block diagram of an oral cavity detection system according to an embodiment of the present disclosure is shown;

[0012] Figure 2A A photograph diagram of a visible light image according to an embodiment of the present disclosure is shown; Figure 1

[0013] A photograph diagram of an ultraviolet light image according to an embodiment of the present disclosure is shown; Figure 2B Figure 1 A photograph diagram of an ultraviolet light image according to an embodiment of the present disclosure is shown;

[0014] Figure 3A A photograph diagram of an ultraviolet light image according to an embodiment of the present disclosure is shown; Figure 1 ​A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0015] Figure 3B A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 1 A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0016] Figure 3C A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 1 A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0017] Figure 3D A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 1 A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0018] Figure 3E A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 1 A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0019] Figure 4 A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 2A A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0020] Figure 5 A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 4 A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0021] Figure 6A A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 2A A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0022] Figure 6B A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 2B A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0023] Figure 7 A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 6B A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0024] Figure 8 A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 3D A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0025] Figure 9 A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0026] Figure 10 A visible light image taken from a front view of the buccal side of the mouth of an embodiment; Figure 9 A visible light image taken from a front view of the buccal side of the mouth of an embodiment;

[0027] Legend

[0028] 100: oral cavity detection system

[0029] 110: image capturing device

[0030] 120: processor

[0031] 121: tooth site recognition module

[0032] 122: image processing module

[0033] 123: tooth state detection module

[0034] 124: display module

[0035] 130: display screen

[0036] 140: database

[0037] 210, 310, 320, 330, 340, 350: visible light image

[0038] 211: tooth image region

[0039] 220: ultraviolet light image

[0040] 221: fluorescent region

[0041] 400: instance segmentation tooth image

[0042] 500: tooth site image

[0043] 510, 610a: tooth image

[0044] 520: tooth site region

[0045] 610: fluorescent tooth image

[0046] 611, 611a: plaque patch

[0047] 611b: caries patch

[0048] S100: oral cavity detection method

[0049] S110: image capturing step

[0050] S120: tooth site recognition step

[0051] S130: image processing step

[0052] S140: tooth state detection step

[0053] S150: display step

[0054] S160: Inspection Recording Procedures

[0055] S200: Detailed Steps

[0056] S210, S220, S230, S240, S250, S260, S270, S280, S290: Sub-steps Detailed Implementation

[0057] Please refer to Figure 1 , Figure 2A and Figure 2B ,in Figure 1 A block diagram illustrating an oral cavity detection system 100 according to an embodiment of the present disclosure is shown. Figure 2A Drawing according to Figure 1 A photographic illustration of the visible light image 210 in the embodiment. Figure 2B Drawing according to Figure 1 A schematic diagram of an ultraviolet light image 220 from an embodiment. (See attached image.) Figure 1 , Figure 2A and Figure 2B As shown, the oral cavity examination system 100 includes an imaging device 110 and a processor 120. The imaging device 110 is used to capture images of an oral cavity and output multiple visible light images 210 and multiple ultraviolet light images 220. The visible light images 210 include multiple tooth images 510 (labeled as follows). Figure 5 Each tooth corresponds to multiple teeth in the oral cavity. The processor 120 is signal-connected to the imaging device 110 and receives visible light images 210 and ultraviolet light images 220. It includes a tooth position recognition module 121, an image processing module 122, a tooth state detection module 123, and a display module 124. The tooth position recognition module 121 defines a tooth position region 520 (marked on...) for each tooth image 510 based on the visible light image 210. Figure 5 ), and output a 500-pixel image of one tooth position (marked at). Figure 5 The tooth position image 500 includes individual tooth images 510 and tooth position regions 520. The image processing module 122 is used to convert the ultraviolet image 220 from the RGB color space to the HSV or HSL color space to generate multiple fluorescence images, extract the individual tooth images 510 corresponding to each tooth position region 520, and map them to the fluorescence images to extract a fluorescence tooth image 610 (labeled as shown in the image) within the same range as each tooth position region 520. Figure 6B The tooth condition detection module 123 identifies a plaque patch or a caries patch on each fluorescent tooth image 610 based on the hue, saturation, and brightness. The display module 124 displays the plaque patch or caries patch of each fluorescent tooth image 610 in different colors in each tooth position area 520 of the tooth position image 500.

[0058] The visible light image 210 and the ultraviolet light image 220 taken by the oral cavity are distinguished by image recognition and artificial intelligence to establish the tooth number of the corresponding tooth and the plaque or caries block marked on each tooth site. In this way, the dentist can quickly know the status of each tooth by the display of different colors, which can greatly reduce the time of the dentist manually examining or analyzing each tooth, thereby increasing the efficiency of the dentist's examination. Furthermore, by classifying the detected decay status of the teeth, the accuracy of the diagnosis can be increased.

[0059] Specifically, the imaging device 110 can include a white light source and an ultraviolet light source. When the white light source illuminates the oral cavity with a white light, the imaging device 110 takes a picture of the oral cavity and outputs a visible light image 210; when the ultraviolet light source illuminates the oral cavity with an ultraviolet light, the imaging device 110 takes a picture of the oral cavity and outputs an ultraviolet light image 220, and when the tooth has plaque, the ultraviolet light image 220 will include a fluorescent region 221 to show the location of the plaque on the tooth. In detail, the wavelength of the ultraviolet light is 520 nm, but the present application is not limited thereto. In addition, in order to make the fluorescent region 221 clear, Appendix 1 presents a color chart of Figure 2B Figure 2B

[0060] Please refer to Figures 3A to 3E , wherein Figure 3A illustrates a schematic diagram of a visible light image 310 taken from the front view of the buccal side of the oral cavity according to an Figure 1 embodiment, Figure 3B illustrates a schematic diagram of a visible light image 320 taken from the left view of the buccal side of the oral cavity according to an Figure 1 embodiment, Figure 3C illustrates a schematic diagram of a visible light image 330 taken from the right view of the buccal side of the oral cavity according to an Figure 1 embodiment, Figure 3D illustrates a schematic diagram of a visible light image 340 taken from the upper jaw view of the oral cavity according to an Figure 1 embodiment, Figure 3E illustrates a schematic diagram of a visible light image 350 taken from the lower jaw view of the oral cavity according to an Figure 1 embodiment. As Figures 3A to 3E ​​As shown, the imaging device 110 can capture images of the oral cavity from multiple perspectives and output visible light images 310, 320, 330, 340, 350 and ultraviolet light images (not shown), and the number of each type of image is multiple. Specifically, the imaging device 110 captures images from the buccal side, the upper palate, and the lower palate of the oral cavity to output visible light images 310, 320, 330, 340, 350 and corresponding ultraviolet light images. The tooth position recognition module 121 can increase the accuracy of the tooth position region 520 definition in the tooth position image 500 by using visible light images 310, 320, 330, 340, and 350 from different perspectives.

[0061] Please refer to the following: Figure 4 and Figure 5 ,in Figure 4 Drawing according to Figure 2A This is a schematic diagram of the segmented tooth image 400 after segmentation of the tooth image region 211 in the embodiment. Figure 5 Drawing according to Figure 4 This example illustrates the tooth position image 500 output by selecting a segment from the segmented tooth image 400. (See attached diagram.) Figure 2A , Figure 4 and Figure 5 As shown, the tooth position recognition module 121 can identify a tooth image region 211 from the visible light image 210 based on a deep learning object detection algorithm, such as the Mask R-CNN (Region-based Convolutional Neural Networks) model. It then detects and classifies the teeth within the tooth image region 211 through instance segmentation, thereby outputting an instance-segmented tooth image 400. The tooth position recognition module 121 can determine the average brightness of the instance-segmented tooth image 400 based on a preset brightness value and perform image normalization adjustments to correct overly bright or dark images. Furthermore, the tooth position identification module 121 can select the tooth position region 520 of each individual tooth by using the bounding box method in the object detection algorithm to obtain the tooth image 510. The tooth position identification module 121 then assigns a number to each tooth image 510 based on the tooth appearance and the corresponding position features in the oral cavity, and outputs the tooth position image 500. The numbering can be performed according to the FDI (Fédération Dentaire Internationale, International Dental Federation) tooth position representation.

[0062] Please refer to Figure 6A and Figure 6B ,in Figure 6A Drawing according to Figure 2Aa schematic diagram of a tooth image 510 according to an embodiment, Figure 6B a schematic diagram of a fluorescent tooth image 610 according to an embodiment, Figure 2B a schematic diagram of a fluorescent tooth image 610 according to an embodiment, Figure 6A and Figure 6B As shown, the image processing module 122 converts the ultraviolet light image 220 from the RGB color space to the HSV color space to generate a fluorescent image, extracts the tooth image 510 of the tooth region 520 corresponding to the tooth site numbered 21, and extracts the fluorescent tooth image 610 of the same range as the tooth region 520 from the corresponding fluorescent image. In Figure 7 In the embodiment, the tooth state detection module 123 finds the plaque block 611 on the fluorescent tooth image 610 according to the hue, saturation, and value of the fluorescent tooth image 610. Specifically, the tooth state detection module 123 can divide the decay state of the tooth into four levels according to the hue, saturation, and value of the fluorescent tooth image 610 as shown in Table 1:

[0063]

[0064]

[0065] In detail, when the range of the hue of a block in the fluorescent tooth image 610 is 0°-30° or 330°-360°, the saturation is greater than or equal to 40%, and the value is less than or equal to 40%, the level of the tooth decay state is 0, representing that the fluorescent tooth image 610 has a block with plaque, and is marked as a plaque block; when the range of the hue of a block in the fluorescent tooth image 610 is 0°-30° or 330°-360°, the saturation is greater than or equal to 55%, and the value is less than or equal to 40%, the level of the tooth decay state is 1, representing that the fluorescent tooth image 610 has a block with more plaque than the block of level 0, and is marked as a plaque block; when the range of the hue of a block in the fluorescent tooth image 610 is 0°-30° or 330°-360°, the saturation is greater than or equal to 65%, and the value is less than or equal to 40%, the level of the tooth decay state is 2, representing that the fluorescent tooth image 610 has a block with plaque and signs of caries, and the dentist can further judge the decay condition of the tooth; when the range of the hue of a block in the fluorescent tooth image 610 is 0°-30° or 330°-360°, the saturation is greater than or equal to 65%, and the value is less than or equal to 20%, the level of the tooth decay state is 3, representing that the fluorescent tooth image 610 has a block of caries, and is marked as a caries block. In this way, the dentist can avoid checking each tooth, and the time of manual inspection can be greatly reduced.

[0066] Please refer toFigure 7 and Figure 8 ,in Figure 7 Drawing according to Figure 6B The dental plaque patch 611 in the embodiment is shown in a schematic diagram of the tooth position image 500. Figure 8 Drawing according to Figure 3D The dental plaque patch 611a and caries patch 611b of the embodiment are shown in a schematic diagram of a tooth image 610a in a tooth position image obtained from the perspective of the maxilla of the oral cavity. Figure 7 As shown, the display module 124 can classify the fluorescent dental images 610 after tooth decay status according to the degree of tooth decay, and categorize the plaque patches or caries patches on the fluorescent dental images (in...) Figure 7 In this embodiment, only the plaque patch 611 located at tooth position 21 is displayed in a different color in the tooth position area 520 of the tooth position image 500. Furthermore, as... Figure 8 As shown, the display module 124 can simultaneously display a tooth image 610a with different colors for plaque blocks 611a and caries blocks 611b according to the level of tooth decay detected by the tooth condition detection module 123, and the tooth image 610a is obtained by taking a picture from the perspective of the maxilla. In this way, by classifying and displaying teeth according to the degree of decay, it is helpful for dentists to interpret the decay status of teeth.

[0067] Furthermore, the oral examination system 100 may also include a display screen 130 and a database 140. The display screen 130 is signal-connected to the processor 120 and is used to display tooth position images 500 and corresponding plaque or caries areas 520 of each tooth position. The database 140 is signal-connected to the processor 120, and the processor 120 outputs an examination record to the database 140 based on the tooth position images 500 and the fluorescent tooth images 610. Storing each examination record in the database 140 helps dentists track the patient's dental treatment status.

[0068] Please refer to Figure 9 The diagram illustrates the steps of an oral examination method S100 according to another embodiment of the present invention. Figure 9 In the embodiment, the combination Figure 1The oral cavity detection system 100 of the embodiment is described together, but the present invention is not limited thereto. The oral cavity detection method S100 includes an image acquisition step S110, a tooth position identification step S120, an image processing step S130, a tooth state detection step S140, and a display step S150. In the image acquisition step S110, an image acquisition device 110 captures an oral cavity and outputs multiple visible light images 210 and multiple ultraviolet light images 220. The visible light images 210 include multiple tooth images 510, each corresponding to a multiple tooth in the oral cavity. In the tooth position identification step S120, a tooth position identification module 121 of a processor 120 defines a tooth position region 520 for each tooth image 510 based on the visible light images 210, and outputs a tooth position image 500. The tooth position image 500 includes each tooth image 510 and each tooth position region 520. In image processing step S130, an image processing module 122 of the processor 120 converts the ultraviolet image 220 from the RGB color space to the HSV or HSL color space to generate multiple fluorescent images. Each tooth image 510 corresponding to each tooth position region 520 is extracted and mapped to the fluorescent images to extract a fluorescent tooth image 610 within the same range as each tooth position region 520. In tooth condition detection step S140, a tooth condition detection module 123 of the processor 120 identifies a plaque patch or a caries patch on each fluorescent tooth image 610 based on its hue, saturation, and brightness. In display step S150, a display module 124 of the processor 120 displays the plaque patches or caries patches of each fluorescent tooth image 610 in different colors on each tooth position region 520 of the tooth position image 500.

[0069] By defining tooth position regions 520 for each tooth and examining the decay status of each tooth position region 520 individually and displaying it with different colors, the time spent on manual examination by dentists can be significantly reduced, and dentists can help determine the condition of teeth, thereby increasing the accuracy of diagnosis.

[0070] The oral examination method S100 may further include an examination recording step S160. In the examination recording step S160, the processor 120 outputs an examination record to a database 140 based on the tooth position image 500 and the fluorescent tooth image 610.

[0071] Please refer to Figure 10 See also Figures 1 to 8 Its drawing is based on Figure 9 The detailed steps of the oral cavity detection method S100 in this embodiment are shown in the flowchart of S200. Figure 10As shown, the detailed steps S200 of the oral cavity detection method S100 include sub-steps S210, S220, S230, S240, S250, S260, S270, S280, S290. In the sub-step S210, the imaging device 110 switches the visible light source and the ultraviolet light source to capture the oral cavity to output the visible light image 210 and the ultraviolet light image 220, respectively, and performs the sub-step S220. In the sub-step S220, the tooth position recognition module 121 finds the tooth image region 211 in the visible light image 210 by using the deep learning object detection algorithm, and then outputs an example segmented tooth image 400 by implementing segmentation, and performs the sub-step S230. In the sub-step S290, the image processing module 122 converts the ultraviolet light image 220 from the RGB color space to the HSV color space to generate a fluorescent image, and the sub-step S290 and the sub-step S220 can be performed simultaneously or sequentially. In the sub-step S230, the tooth position recognition module 121 can judge the average brightness of the example segmented tooth image 400 according to a preset brightness value, and perform image normalization adjustment, and perform the sub-step S240. In the sub-step S240, the tooth position recognition module 121 can frame the tooth position region 520 of each single tooth by using the bounding box in the object detection algorithm to obtain each tooth image 510, and sort according to the coordinate position of the tooth image 510, and then number according to the sorted position and the characteristics of the tooth image 510, and perform the sub-step S250. In the sub-step S250, a tooth image 510 is taken out according to the number, and a fluorescent tooth image 610 is taken out according to the same coordinate position corresponding to the aforementioned tooth image 510 in the fluorescent image, and the sub-step S260 is performed. In the sub-step S260, the tooth state detection module 123 classifies the decay state of the tooth according to the hue, saturation and brightness of the fluorescent tooth image 610, and performs the sub-step S270. In the sub-step S270, the blocks of different decay levels are marked in the tooth image 500 with different colors, and another tooth image 510 and the corresponding another fluorescent tooth image 610 are taken out, and the sub-steps S250 to S260 are repeatedly performed, and when all the tooth images 510 in the tooth image 500 have performed the aforementioned sub-steps S250 to S260, the sub-step S280 is performed. In the sub-step S280, the decay state of the tooth is recorded in the form of a table. In detail, the imaging step S110 includes the sub-step S210, the tooth position recognition step S120 includes the sub-steps S220, S230, S240, the image processing step S130 includes the sub-step S290, the tooth state detection step S140 includes the sub-steps S250, S260, the display step S150 includes the sub-step S270, and the detection recording step S160 includes the sub-step S280, but the present application is not limited to the above steps.

[0072] In summary, the present application provides an oral cavity detection system and method, which has the following advantages: first, by converting the ultraviolet light image from the RGB color space to the HSV color space or the HSL color space, the tooth state detection module can find the plaque block or the caries block according to the hue, saturation and brightness of the fluorescent tooth image, thereby reducing the time consumed by manual inspection; second, the tooth can be classified into different decay state levels according to the hue, saturation and brightness of the fluorescent tooth image, which can help dentists interpret the decay state of the tooth; and third, by outputting the detection record to the database, it can help dentists track the treatment status of the patient.

[0073] Although the present application has been disclosed with examples as above, it is not intended to limit the present application, and any person skilled in the art can make various modifications and decorations without departing from the spirit and scope of the present application, and therefore the protection scope of the present application shall be subject to the appended claims.

Claims

1. An oral cavity detection system, characterized by, Comprising: an image capturing device for capturing an oral cavity and outputting a plurality of visible light images and a plurality of ultraviolet light images, the plurality of visible light images comprising a plurality of tooth images corresponding to a plurality of teeth of the oral cavity, wherein the image capturing device is configured to capture the oral cavity from a buccal side, a palate and a mandible to output the plurality of visible light images and the plurality of ultraviolet light images, the plurality of tooth images having a number equal to a total number of teeth of the oral cavity; and a processor connected to the image capturing device and configured to receive the plurality of visible light images and the plurality of ultraviolet light images, the processor comprising: a tooth site recognition module configured to define a tooth site area of each of the tooth images based on the plurality of visible light images and a bounding box method of an object detection algorithm, and to number and output a tooth site image based on a tooth appearance of each of the tooth images and a corresponding location feature in the oral cavity, the tooth site image comprising each of the tooth images and each of the tooth site areas; an image processing module configured to convert the plurality of ultraviolet light images from an RGB color space to an HSV color space or an HSL color space to generate a plurality of fluorescent images, to extract each of the tooth images corresponding to each of the tooth site areas, and to extract a fluorescent tooth image corresponding to each of the tooth site areas from the plurality of fluorescent images; a tooth condition detection module configured to find a plaque block or a caries block on each of the fluorescent tooth images based on a hue, a saturation and a brightness of each of the fluorescent tooth images; and a display module configured to display the plaque block or the caries block of each of the fluorescent tooth images in a different color in each of the tooth site areas of the tooth site image. The image processing module converts the plurality of ultraviolet light images from the RGB color space to the HSV color space to generate the plurality of fluorescent images, the fluorescent tooth image has the plaque block when a range of the hue of the fluorescent tooth image is 0°-30° or 330°-360°, a range of the saturation of the fluorescent tooth image is 40%-65%, and a brightness of the fluorescent tooth image is less than or equal to 40%. The image processing module converts the plurality of ultraviolet light images from the RGB color space to the HSV color space to generate the plurality of fluorescent images, the fluorescent tooth image has the caries block when a range of the hue of the fluorescent tooth image is 0°-30° or 330°-360°, a range of the saturation of the fluorescent tooth image is greater than or equal to 65%, and a brightness of the fluorescent tooth image is less than or equal to 40%. The tooth site recognition module finds a tooth image area from the plurality of visible light images, and detects and classifies the plurality of teeth in the tooth image area by implementing a segmentation method, and then outputs an instance segmentation tooth image. The tooth site recognition module performs image normalization adjustment on the instance segmentation tooth image based on a preset brightness value.

2. The oral cavity detection system of claim 1, wherein, The processor outputs a detection record to a database based on the tooth site image and the fluorescent tooth image.

3. The oral detection system of claim 1, wherein, ​

Images