Method, device, equipment, system, medium and product for processing images of the inner and outer genitals

Abstract

This invention discloses a method, apparatus, device, system, medium, and product for processing images of the vulva and external genitalia. The method includes: acquiring original images of the vulva and external genitalia; using original images of the vulva and external genitalia that meet certain clarity requirements as images to be processed; inputting the images to be processed into an image recognition model to obtain regions of interest (ROI) images corresponding to the images; grouping the ROI images according to a preset mapping relationship between vulvar and external genitalia state recognition dimensions and vulvar and external genitalia locations to obtain ROI image groups; inputting the ROI image groups into corresponding image analysis models to obtain information recognition results for the preset vulvar and external genitalia state recognition dimensions; and displaying the information recognition results. The technical solution of this invention solves the problems of low efficiency and significant subjective influence in manual vulvar and external genitalia state recognition, improving the efficiency of vulvar and external genitalia state recognition and obtaining more objective information recognition results.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer technology, and in particular to a method, apparatus, device, system, medium and product for processing internal and external vaginal images. Background Technology

[0002] Currently, in clinical gynecological examinations or genital aesthetic / plastic surgery, most vulvar image-based assessment and analysis systems rely on manual image reading and analysis, with the results of vulvar and genital condition identification being entered item by item. However, this analysis process is inefficient and depends on the analyst's knowledge level, resulting in highly subjective information identification results. Summary of the Invention

[0003] This invention provides a method, apparatus, device, system, medium, and product for processing images of the vulva and genitalia, which can improve the efficiency of vulvar and genitalia state analysis, obtain more objective information identification results, and provide greater convenience for relevant personnel in the process of performing vulvar and genitalia state analysis.

[0004] In a first aspect, embodiments of the present invention provide a method for processing images of the vulva and an anal genitalia, the method comprising: Obtain the original internal and external vulva images, identify the clarity of the original internal and external vulva images, and use the original internal and external vulva images whose clarity meets the preset image clarity conditions as the internal and external vulva images to be processed. The images of the vulva and genitalia to be processed are input into a pre-trained image recognition model to obtain the region of interest images of the vulva and genitalia corresponding to the images of the vulva and genitalia to be processed. Based on the mapping relationship between the preset internal and external vulvar state recognition dimensions and the internal and external vulvar parts, the region of interest images are grouped to obtain the region of interest image group corresponding to each preset internal and external vulvar state recognition dimension; The image group of the region of interest is input into the image analysis model corresponding to the preset internal and external vulvar state recognition dimension to obtain the information recognition result of the preset internal and external vulvar state recognition dimension, and the information recognition result is displayed.

[0005] In a second aspect, embodiments of the present invention provide an internal and external vaginal image processing apparatus, the apparatus comprising: The image acquisition module is used to acquire original internal and external vulvar images, identify the clarity of the original internal and external vulvar images, and use the original internal and external vulvar images whose clarity meets the preset image clarity conditions as the internal and external vulvar images to be processed. The image recognition module is used to input the images of the vulva and genitalia to be processed into a pre-trained image recognition model to obtain the region of interest image of the vulva and genitalia corresponding to the images of the vulva and genitalia to be processed. The image grouping module is used to group the region of interest images according to the preset mapping relationship between the internal and external vulva state recognition dimensions and the internal and external vulva parts, so as to obtain the region of interest image group corresponding to each preset internal and external vulva state recognition dimension. The image analysis module is used to input the image group of the region of interest into the image analysis model corresponding to the preset internal and external vulvar state recognition dimension, obtain the information recognition result of the preset internal and external vulvar state recognition dimension, and display the information recognition result.

[0006] Thirdly, embodiments of the present invention provide an internal and external vulvar image processing system, the system comprising: An image acquisition device, at least one image display device, and an image processing device; Among them, the image acquisition device is used to acquire raw internal and external vulvar images and synchronize the raw internal and external vulvar images to the image processing device; The image processing device is used to acquire original internal and external vulvar images and display the original internal and external vulvar images through an image display device; it is also used to perform image processing on the internal and external vulvar images to be processed in the original internal and external vulvar images as provided in any embodiment of the present invention.

[0007] Fourthly, embodiments of the present invention also provide a computer device, the computer device comprising: One or more processors; Memory, used to store one or more programs; When one or more of the above programs are executed by one or more processors, the one or more processors implement the internal and external vulvar image processing method provided in any embodiment of the present invention.

[0008] Fifthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the internal and external vaginal image processing method provided in any embodiment of the present invention.

[0009] Sixthly, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the internal and external vulvar image processing method provided in any embodiment of the present invention.

[0010] The embodiments of the above invention have the following advantages or beneficial effects: This invention, in its embodiments, acquires original images of the vulva and anterior vagina, identifies the clarity of these images, and designates those images whose clarity meets preset image clarity conditions as images to be processed. These images are then input into a pre-trained image recognition model to obtain regions of interest (ROI) images of the vulva and anterior vagina corresponding to the images. Based on a preset mapping relationship between vulvar and anterior vaginal state recognition dimensions and the vulvar and anterior vaginal regions, the ROI images are grouped to obtain ROI image groups corresponding to each preset vulvar and anterior vaginal state recognition dimension. These ROI image groups are then input into an image analysis model corresponding to the preset vulvar and anterior vaginal state recognition dimension to obtain the corresponding information recognition results for that dimension, and these results are then displayed. This invention solves the problems of low efficiency and significant subjective influence in manual vulvar and anterior vaginal state analysis, improving the efficiency of analysis, obtaining more objective information recognition results, and providing greater convenience for relevant personnel during vulvar and anterior vaginal state analysis. Attached Figure Description

[0011] Figure 1 This is a flowchart of an internal and external vulvar image processing method provided in an embodiment of the present invention; Figure 2 This is a flowchart of an internal and external vulvar image processing method provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of an image acquisition interactive interface provided in an embodiment of the present invention; Figure 4 This is a flowchart of an internal and external vulvar image processing method provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of an information recognition result display page provided in an embodiment of the present invention; Figure 6 This is a flowchart of an internal and external vulvar image processing method provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of an internal and external vaginal image processing device provided in an embodiment of the present invention; Figure 8 This is a schematic diagram of the structure of an internal and external vulva image processing system provided in an embodiment of the present invention; Figure 9 This is a schematic diagram of the structure of an internal and external vulva image processing system provided in an embodiment of the present invention; Figure 10 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0012] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0013] Furthermore, it should be noted that any of the internal and external vulvar image processing methods provided by the present invention, in the process of implementation, includes a process of processing only the internal vulvar image, a process of processing only the external vulvar image, and a process of processing both the internal vulvar image and the external vulvar image simultaneously.

[0014] Figure 1 This is a flowchart illustrating an image processing method for the vulva and external genitalia provided in this embodiment of the invention. This embodiment is applicable to scenarios where the internal and external genitalia are identified based on images, particularly in clinical gynecological colposcopy and vaginal cosmetic / plastic surgery, where colposcopy image processing or vulvar and external genitalia image processing is required. This method can be executed by a vulvar and external genitalia image processing device, which can be implemented in software and / or hardware and integrated into a computer device with application development capabilities, such as an vulvar and external genitalia examination device or a colposcopy image acquisition and processing device.

[0015] like Figure 1 As shown, the internal and external vulvar image processing method of this embodiment includes the following steps: S110. Obtain the original internal and external vulvar images and identify the clarity of the original internal and external vulvar images. Use the original internal and external vulvar images whose clarity meets the preset image clarity conditions as the internal and external vulvar images to be processed.

[0016] The raw images of the vulva and vagina are images acquired by an image acquisition device. These can be real-time images or images pre-acquired and saved to a specified storage path. The image acquisition device can be a device used to acquire images of the vulva and vagina, such as a colposcope or other vulvar examination equipment. The raw images of the vulva and vagina can include images of various parts of the vulva and vagina used for vulvar status analysis, and can also include images of each vulvar part in different states (such as open or closed).

[0017] Specifically, the original images of the vulva and genitalia can be grouped according to the dimensions of the vulva and genitalia. For example, the original images of the vulva and genitalia can include at least one of the following: an overall image of the vulva, an image of the mons pubis, an image of the labia majora, an image of the labia minora, and an image of pubic hair. The original images of the vulva and genitalia can include at least one of the following: an image of the vaginal opening, an image of the vaginal wall, an image of the vagina, and an image of the cervix.

[0018] The images of the vulva to be processed are those of the original vulva images that have been filtered for image sharpness. Identifying the sharpness of the original vulva images can be achieved by extracting image sharpness-related parameters such as resolution, edge sharpness, signal-to-noise ratio, and the proportion of unblurred areas. Then, the identified image sharpness features are compared with preset image sharpness conditions (thresholds or conditions for a certain parameter). Finally, the original vulva images whose sharpness meets the preset image sharpness conditions are selected as the images of the vulva to be processed.

[0019] S120. Input the images of the vulva and genitalia to be processed into the pre-trained image recognition model to obtain the region of interest images of the vulva and genitalia corresponding to the images of the vulva and genitalia to be processed.

[0020] The image recognition model can be a pre-trained neural network model, which can be used to identify and extract key areas that affect vaginal condition analysis in the images of the vulva and genitalia to be processed. Therefore, each image of the vulva and genitalia to be processed can be input into the image recognition model corresponding to its respective vulva and genitalia area to obtain the region of interest image of the vulva and genitalia area corresponding to the image of the vulva and genitalia to be processed.

[0021] The region of interest image can be a lesion point in the corresponding internal and external vulva image to be processed, a tissue area that is different from the normal state, or a key part that affects the recognition result of the corresponding internal and external vulva state.

[0022] S130. Based on the preset mapping relationship between the internal and external vulvar state recognition dimensions and the internal and external vulvar parts, the region of interest images are grouped to obtain the region of interest image group corresponding to each preset internal and external vulvar state recognition dimension.

[0023] There are multiple preset dimensions for recognizing the internal and external vulva states, corresponding to the grouping of internal and external vulva. Both internal and external vulva have multiple preset dimensions for recognizing their states. Specifically, for the external vulva, the preset dimensions for recognizing the internal and external vulva states may include one or more dimensions such as health, aesthetics, fullness, sensitivity, moisturization, and control. For the internal vulva, the preset dimensions for recognizing the internal and external vulva states may include dimensions such as health, moisturization, and fullness.

[0024] Different preset dimensions for identifying the external and internal vulvar states can be analyzed based on images of at least one vaginal region. For example, the aesthetics of the vulva require comprehensive analysis of images of multiple vulvar areas, including pubic hair, mons pubis, labia majora, clitoris, and labia minora, to obtain an aesthetics assessment result. Health, on the other hand, requires feature analysis of the overall vulvar image to obtain a health assessment result. Therefore, before obtaining the analysis results of the external and internal vulvar states, the images of regions of interest (ROIs) can be grouped according to the mapping relationship between the preset external and internal vulvar state identification dimensions and the vulvar regions, resulting in ROI image groups corresponding to each preset external and internal vulvar state identification dimension. It is understood that each ROI image group includes one or more ROI images.

[0025] The image group of the region of interest corresponding to each preset internal and external vulvar state recognition dimension is the basis for analysis when performing the corresponding internal and external vulvar state recognition dimension analysis.

[0026] S140. Input the image group of the region of interest into the image analysis model corresponding to the preset internal and external vulvar state recognition dimension, obtain the information recognition result of the preset internal and external vulvar state recognition dimension, and display the information recognition result.

[0027] The image analysis model is a pre-trained neural network model that can extract high-dimensional image features from each image in a group of images in the region of interest. Based on the extracted features, it can obtain information recognition results for the corresponding preset internal and external genital states and display the information recognition results.

[0028] Furthermore, the information recognition result for each preset internal and external genitalia state recognition dimension can be the information content corresponding to one or more information recognition items in the corresponding internal and external genitalia state recognition dimension, or the corresponding state analysis score.

[0029] For example, corresponding to the aesthetics of the vulva as a preset dimension for identifying the internal and external vulvar states, the information recognition results can include the recognition results corresponding to shape and color.

[0030] In one optional implementation, a mapping relationship is established between the recognition results of different information identification items and the corresponding internal and external vulvar state assessment scores. The internal and external vulvar state assessment scores for preset internal and external vulvar state identification dimensions can be obtained by mapping based on the information recognition results. Displaying the information recognition results can show the vaginal state analysis results determined comprehensively based on the information recognition results of all preset internal and external vulvar state identification dimensions.

[0031] The technical solution of this embodiment involves acquiring original images of the vulva and anterior vagina, identifying the clarity of these images, and selecting those images whose clarity meets preset image clarity conditions as the vulva images to be processed. These images are then input into a pre-trained image recognition model to obtain regions of interest (ROI) images of the vulva and anterior vagina corresponding to the images. Based on a preset mapping relationship between vulvar and anterior vaginal state recognition dimensions and the vulvar and anterior vaginal regions, the ROI images are grouped to obtain ROI image groups corresponding to each preset vulvar and anterior vaginal state recognition dimension. These ROI image groups are then input into an image analysis model corresponding to the preset vulvar and anterior vaginal state recognition dimension to obtain the corresponding information recognition results for that dimension, and these results are then displayed. This technical solution solves the problems of low efficiency and significant subjective influence in manual vulvar and anterior vaginal state analysis, improving the efficiency of vulvar and anterior vaginal state analysis, obtaining more objective information recognition results, and providing greater convenience for relevant personnel during vulvar and anterior vaginal state analysis.

[0032] Figure 2 This is a flowchart illustrating a method for processing internal and external vulvar images according to an embodiment of the present invention. This embodiment belongs to the same inventive concept as the internal and external vulvar image processing methods described in the above embodiments, and further describes the process of acquiring images of the internal and external vulvas to be processed. This method can be executed by an internal and external vulvar image processing device, which can be implemented in software and / or hardware and integrated into a computer device with application development capabilities.

[0033] like Figure 2 As shown, the internal and external vulvar image processing method of this embodiment includes the following steps: S210, In response to the first trigger operation of any internal or external vulva control in the image acquisition interactive interface, enter the state of image acquisition of the target internal or external vulva corresponding to the internal or external vulva control.

[0034] The image acquisition interactive interface can be an interactive page in the internal and external vulvar image processing system. After the internal and external vulvar image acquisition device is connected and the image acquisition initialization settings are completed, the image acquisition interactive interface can be accessed.

[0035] The image acquisition initialization settings include configuring parameters such as focal length, brightness, saturation, and hue. During the image acquisition initialization configuration process, or during the acquisition of internal and external vulvar images, the image acquisition parameter configuration operation can be performed to configure at least one of the parameters of focal length, brightness, saturation, and hue of the image acquisition device for acquiring the original internal and external vulvar images.

[0036] The image acquisition interface can display controls for the internal and external vulva areas, respectively.

[0037] The internal and external vulva controls are designed to guide image acquisition during the co-acquisition of internal and external vulva images. When any internal or external vulva control is triggered for the first time, image acquisition will enter the state of acquiring images of the target internal and external vulva areas corresponding to the control. The first trigger operation of any internal or external vulva control in the image acquisition interface indicates the start of acquiring images of the internal and external vulva of that vaginal area, entering the state of acquiring images of the target internal and external vulva areas corresponding to the control.

[0038] The layout of the image acquisition interface can be referenced. Figure 3 The structure shown. In Figure 3 In the image, the black area can display real-time image information captured by the image acquisition device, or it can display images of the internal and external genitalia of any target. Figure 3 The rightmost column displays controls for the vulva and genitalia. The entire vulva, the labia minora in close proximity (closed), and the labia minora in close proximity (open) are the target vulva and genitalia areas for data collection. You can also switch from "Vulva" to "Vulva," which will change the display of the corresponding internal and external vulva controls in the rightmost column.

[0039] When a person triggers any internal or external vulva control, the internal and external vulva image processing system can obtain the first trigger operation of any internal or external vulva control in the image acquisition interface, respond, and enter the state of image acquisition of the target internal or external vulva corresponding to the internal or external vulva control.

[0040] In one optional implementation, after entering the state of image acquisition of the target internal and external vulva corresponding to the vulva control, preset prompts for image acquisition of the target internal and external vulva can be displayed. The preset prompts may include descriptions of the corresponding target internal and external vulva, precautions or requirements for image acquisition of the corresponding target internal and external vulva, etc.

[0041] Furthermore, during the image acquisition process of the target's internal and external genitalia, the acquired images can be analyzed in real time to confirm whether the currently acquired images meet the image acquisition standards for the target's internal and external genitalia. If they do not meet the standards, a prompt can be given. Image acquisition standards can be standards such as sharpness standards or the proportion of the target's internal and external genitalia in the overall image.

[0042] S220, In response to the second trigger operation of the vulva control, obtain the original vulva image corresponding to the target vulva, and add the corresponding vulva identification to the original vulva image.

[0043] The second trigger operation for the internal and external vulva controls can be triggered by relevant personnel through an image acquisition device during operation. The second trigger operation after the first trigger operation on an internal or external vulva control can be considered as the completion of the processing of the corresponding target internal or external vulva image.

[0044] During the acquisition of images of the target vulva and genitalia, the clarity of the original vulva and genitalia images acquired in real time can be analyzed. Based on the clarity of the original vulva and genitalia images, the images that meet the preset clarity conditions are selected as vulva and genitalia images to be processed. For images that do not meet the clarity conditions, the system prompts the user to re-acquire the original vulva and genitalia images of the target vulva and genitalia until the acquired images meet the preset clarity requirements.

[0045] In one case, the original images of the target vulva and genitalia can be directly used as the images of the corresponding vulva and genitalia to be processed.

[0046] In an optional implementation, in response to the triggering operation of the image acquisition process recording function, the image information acquired by the image acquisition device for acquiring original internal and external vulvar images can be acquired and saved until all original internal and external vulvar images are acquired. That is, video information is acquired from the acquisition of the first vaginal area image to the acquisition of the last vaginal area image, which can be used for information backtracking.

[0047] Furthermore, the image acquisition interface can also be equipped with image editing function controls such as image zooming, image zooming, rotation, marking, taking photos, freezing video frames, image export, image page turning, and image order adjustment, allowing relevant personnel to operate according to image processing needs. In the display interface of any internal or external image to be processed, in response to any image editing operation or the triggering of any image editing function control, the corresponding image editing result can be obtained; among these, image editing operations include at least one of image rotation, marking, deletion, and image order adjustment.

[0048] S230. The original internal and external vulva images with clarity that meet the preset image clarity conditions are taken as the internal and external vulva images to be processed, and the internal and external vulva images to be processed are input into the pre-trained image recognition model to obtain the region of interest image of the vaginal area corresponding to the internal and external vulva images to be processed.

[0049] S240. Based on the preset mapping relationship between the internal and external vulvar state recognition dimensions and the vaginal location, the region of interest images are grouped to obtain a region of interest image group corresponding to each preset internal and external vulvar state recognition dimension.

[0050] S260. Input the image group of the region of interest into the image analysis model corresponding to the preset internal and external vulvar state recognition dimension, obtain the information recognition result of the preset internal and external vulvar state recognition dimension, and display the information recognition result.

[0051] The technical solution of this embodiment, in response to a first trigger operation on any internal or external vulva control in the image acquisition interactive interface, enters a state of image acquisition of the target internal or external vulva corresponding to the internal or external vulva control; in response to a second trigger operation on the internal or external vulva control, the original internal or external vulva image corresponding to the target internal or external vulva is obtained, and the corresponding internal or external vulva identification is added to the original internal or external vulva image; after obtaining the original internal or external vulva images of all preset vaginal areas, the images to be processed are input into a pre-trained image recognition model to obtain the region of interest (ROI) image of the vaginal area corresponding to the images to be processed; according to the mapping relationship between the preset internal or external vulva state recognition dimension and the vaginal area, the ROI images are grouped to obtain the ROI image group corresponding to each preset internal or external vulva state recognition dimension; the ROI image group is input into the image analysis model corresponding to the preset internal or external vulva state recognition dimension to obtain the information recognition result of the preset internal or external vulva state recognition dimension, and the information recognition result is displayed. The technical solution of this invention solves the problems of low efficiency and significant subjective influence in manual analysis of the internal and external vulva. It also solves the problem of how to obtain images of the internal and external vulva to be processed. It can not only obtain images of the internal and external vulva at various parts, but also improve the efficiency of internal and external vulva state analysis, obtain more objective information recognition results, and provide greater convenience for relevant personnel in the process of analyzing the internal and external vulva state.

[0052] Figure 4 This is a flowchart illustrating an image processing method for the vulva and an external genitalia provided in this embodiment of the invention. This embodiment belongs to the same inventive concept as the vulva and an external genitalia image processing methods described above, and further describes the process of modifying the automatic recognition results. This method can be executed by a vulva and an external genitalia image processing device, which can be implemented in software and / or hardware and integrated into a computer device with application development capabilities.

[0053] like Figure 4 As shown, the internal and external vulvar image processing method of this embodiment includes the following steps: S310. Obtain the original internal and external vulvar images and identify the clarity of the original internal and external vulvar images. Use the original internal and external vulvar images whose clarity meets the preset image clarity conditions as the internal and external vulvar images to be processed.

[0054] S320. Input the images of the vulva and genitalia to be processed into a pre-trained image recognition model to obtain the region of interest image of the vaginal area corresponding to the images of the vulva and genitalia to be processed.

[0055] S330. Based on the preset mapping relationship between the internal and external vulvar state recognition dimensions and the vaginal location, the region of interest images are grouped to obtain a region of interest image group corresponding to each preset internal and external vulvar state recognition dimension.

[0056] S340. Input the image group of the region of interest into the image analysis model corresponding to the preset internal and external vulvar state recognition dimension, obtain the information recognition result of the preset internal and external vulvar state recognition dimension, and display the information recognition result.

[0057] S350. On the information recognition result display page, in response to any modification operation of the information recognition result for any preset internal and external genital state recognition dimension, update the information recognition result corresponding to the modification operation.

[0058] The information recognition results display page can show the vaginal state analysis results determined by the comprehensive information recognition results based on all preset internal and external vulvar state recognition dimensions, or it can show each information recognition item of all preset internal and external vulvar state recognition dimensions separately.

[0059] The page displaying the information recognition results can be found here. Figure 5 The page layout information shown. The information recognition results display page can include the recognition results for each preset internal and external vulva status recognition dimension and / or the information recognition items for the internal and external vulva areas (vulva as a whole, pubic hair, mons pubis, labia majora, and labia minora, etc.). The content within the dashed box indicates content that can be switched during display.

[0060] When relevant personnel believe that the automatic identification result differs significantly from the comparison result of their observation of the corresponding internal and external vulvar images, they can modify the information identification result accordingly. The internal and external vulvar image processing system can then respond to the modification operation of the information identification result for any preset internal and external vulvar state identification dimension and update the information identification result corresponding to the modification operation. For example, the identification result of white patches on the vulva as a whole can be modified to redness and swelling.

[0061] In one alternative implementation, when a user modifies a specific information identification item, the system senses the hovering position of the mouse cursor and displays the information analysis standards or reference information corresponding to that hovering position. For example, when modifying the information identification item related to the shape of the labia minora, the system can provide a description of the normal shape of the labia minora for the user's reference.

[0062] S360, on the information recognition result display page, in response to the evaluation information input operation, obtain and display the internal and external genital status evaluation input information.

[0063] The input information for assessing the state of the vulva is not the assessment information corresponding to the preset vulva state recognition dimension determined based on the vulva images to be processed.

[0064] Evaluation information not based on the preset vulvar state recognition dimensions determined by the images of the vulva to be processed, such as evaluation information on the blood supply, temperature, and control of the vagina, are analysis results obtained from other test and analysis methods. Relevant personnel can input information to increase the information content of more vaginal state analysis dimensions obtained through other methods.

[0065] Furthermore, the comprehensive analysis results of the internal and external genitalia status analysis can be updated by combining the information recognition results based on image recognition and the evaluation input information of the internal and external genitalia status input by relevant personnel.

[0066] The technical solution of this embodiment acquires original images of the vulva and anterior vagina, identifies the clarity of these images, and selects those images whose clarity meets preset image clarity conditions as images to be processed. These images are then input into a pre-trained image recognition model to obtain regions of interest (ROI) images of the vaginal area corresponding to the images. Based on a preset mapping relationship between vulvar and anterior vaginal state recognition dimensions and vaginal areas, the ROI images are grouped to obtain ROI image groups corresponding to each preset vulvar and anterior vaginal state recognition dimension. These ROI image groups are then input into an image analysis model corresponding to the preset vulvar and anterior vaginal state recognition dimension to obtain the corresponding information recognition results for that dimension, and these results are displayed. This embodiment solves the problems of low efficiency and significant subjective influence in manual vaginal state analysis. It also addresses how to correct or add information to the vulvar and anterior vaginal state analysis, resulting in more comprehensive information across the dimensions of vulvar and anterior vaginal state analysis. This improves the accuracy and efficiency of vulvar and anterior vaginal state analysis, yields more objective information recognition results, and provides greater convenience for personnel conducting vulvar and anterior vaginal state analysis.

[0067] Figure 6 This is a flowchart illustrating a method for processing internal and external vulvar images according to an embodiment of the present invention. This embodiment belongs to the same inventive concept as the internal and external vulvar image processing methods described above, and further describes the process of processing the internal and external vulvar images to be processed. This method can be executed by an internal and external vulvar image processing device, which can be implemented in software and / or hardware and integrated into a computer device with application development capabilities.

[0068] like Figure 6 As shown, the internal and external vulvar image processing method of this embodiment includes the following steps: S410. Obtain the images of the inner and outer vulva to be processed, and perform image enhancement processing on the images of the inner and outer vulva to be processed to obtain the target images of the inner and outer vulva.

[0069] The images of the vulva to be processed can be the original images of the vulva captured by the image acquisition device, or the original images of the vulva after the clarity has been filtered.

[0070] Image enhancement processing of internal and external images can improve the visual effect of the image, highlight the parts of interest in the image, or weaken noise, blur and other interfering information, thus providing image preprocessing for subsequent image recognition and segmentation.

[0071] Image enhancement can be achieved by adjusting the contrast of an image by changing the grayscale values ​​of its pixels. Alternatively, it can be enhanced through filtering, which uses spatial filtering and a template (convolution kernel) to perform neighborhood operations on the image pixels.

[0072] In one optional implementation, image processing of images of the internal and external genitalia, which are characterized by privacy, anatomical specificity, and the complexity of the shooting scene, can be performed through the following steps: Step 1: Input the images of the vulva and genitalia to be processed into a pre-trained semantic segmentation model for private parts to obtain the effective and invalid pixel regions in the images to be processed. Then, remove the invalid pixel regions from the images of the vulva and genitalia to be processed to obtain new images of the vulva and genitalia to be processed.

[0073] The goal of this step is to remove areas in the image that are unrelated to the vulva (i.e., invalid pixel areas), to avoid interference from clothing, camera equipment, and background clutter, and to retain only the valid areas of the genitals.

[0074] The pre-trained semantic segmentation sub-model for private parts can be a non-general segmentation model trained on the anatomical features of the vulva and genitals. It can identify two types of regions: one is the effective region (the vulva and genital body, including the labia majora, labia minora, clitoris, perineum, vaginal opening, etc.), and the other is the redundant region (clothing, disposable pads, camera probes, background desktops, etc.).

[0075] After identifying the valid and invalid pixel regions, a black mask can be generated to cover the invalid pixel regions, retaining only the pixel information of the valid regions. This allows the invalid pixel regions in the internal and external images to be processed to be removed, resulting in new internal and external images to be processed.

[0076] In one alternative implementation, a threshold for the percentage of effective pixel areas can also be set. For example, the effective area percentage is required to be ≥70%. If the effective area percentage is insufficient after removing invalid pixel areas, the current inner and outer negative images to be processed can be marked as "invalid images" to avoid subsequent white processing. Otherwise, proceed to the next step.

[0077] Step 2: Based on the standard coordinate system of the internal and external vulva, perform adaptive correction on the new internal and external vulva images to be processed, and obtain the corrected internal and external vulva images to be processed.

[0078] During the acquisition of images of the vulva and genitalia, image shift may occur due to factors such as tilting of the acquisition device or different body positions of the subject. To address this image shift issue, adaptive correction can be performed on new images of the vulva and genitalia to be processed, based on a standard coordinate system for the vulva and genitalia. During the correction process, the standard coordinate system for the vulva and genitalia can be determined based on anatomical reference points of the vulva and genitalia. These reference points can be the midpoint of the perineum or the midpoint of the line connecting the tips of the labia minora.

[0079] The angular deviation between the new image of the vulva to be processed and the reference points of the anatomical features of the vulva can be calculated. The deviation can be corrected by rigid radiometric transformation. The offset image is rotated and translated to the standard coordinate system to obtain the corrected image of the vulva to be processed.

[0080] Step 3: Perform light compensation on the corrected internal and external vulvar images to obtain the target internal and external vulvar images.

[0081] In this step, the effective pixel area of ​​the corrected vulva image to be processed can be divided into three sub-regions according to the anatomical structure (including the vulva region, vaginal opening region, and perineum region), and the average brightness and contrast of each region are detected respectively.

[0082] For underexposed areas (average brightness < preset threshold) in the three sub-regions, adaptive gamma correction (gamma value 0.6-0.8, dynamically adjusted according to darkness) can be used to enhance brightness while preserving mucosal texture and avoid whitening. For overexposed areas (average brightness > preset threshold, such as reflective points), a multi-scale Retinex algorithm can be used to restore pigment and texture details in overexposed areas (such as avoiding misjudgment of "false pigment loss" caused by reflection). For areas with uneven lighting (contrast difference between areas > preset value), local histogram equalization (rather than global equalization) can be used to balance the brightness of each sub-region and avoid loss of details in some areas due to global processing. Differential compensation processing can be applied to areas with the same brightness level, with regional adaptation based on private parts for more targeted results.

[0083] In addition, secretions in the target vulva image can be identified based on the pixel attribute features of the secretions; the secretions can be removed from the target vulva image, and the target vulva image can be repaired based on the pixel information around the secretions to obtain a new target vulva image.

[0084] The secretions, such as vaginal discharge or stains, can obscure the mucosal texture and may also introduce noise from the imaging device (e.g., noise from portable detectors), leading to misdiagnosis of inflammation or missed detection of growths. The pixel attributes of the secretions can be detailed, such as the grayscale range corresponding to each type of secretion, irregular textures, or blurred boundaries with the mucosa. The areas obscured by the secretions can be identified through threshold segmentation, texture matching, or a combination of both. Then, using the surrounding mucosal / skin texture and pigmentation as a reference, the obscured area is filled in to restore the possible true features underneath.

[0085] Furthermore, the Laplacian operator can be used to sharpen the image, focusing on enhancing the edges of the labia, the texture of the vaginal wall mucosa, and the boundaries of growths, while not sharpening smooth areas of the skin (to avoid over-sharpening and artifacts), in order to highlight the contours of different internal and external vulva areas.

[0086] S420. Input the target internal and external vulva images into the pre-trained image recognition model to obtain the region of interest images of the internal and external vulva areas corresponding to the images to be processed.

[0087] Pre-trained image recognition models can include U-Net modules. The network structure is U-shaped, consisting of a contraction path (downsampling) and an expansion path (upsampling). Skip connections fuse feature maps from different levels, allowing the network to capture more low-level details during upsampling, thus improving segmentation. U-Net performs well on small sample data and has relatively fast training speed. After training, the image recognition model can extract the region of interest (ROI) images of the corresponding internal and external vulva areas from the target internal and external vulva image.

[0088] S430. Based on the preset mapping relationship between the internal and external vulvar state recognition dimensions and the vaginal location, the region of interest images are grouped to obtain a region of interest image group corresponding to each preset internal and external vulvar state recognition dimension.

[0089] S440. Input the image group of the region of interest into the image analysis model corresponding to the preset internal and external vulvar state recognition dimension, obtain the information recognition result of the preset internal and external vulvar state recognition dimension, and display the information recognition result.

[0090] Before inputting the region of interest (ROI) image group into the image analysis model, the images are preprocessed. The size of each image in the ROI image group is adjusted to the size expected by the network, and the pixel values ​​are normalized so that their range matches the data range of the image analysis model during training, so as to better match the input distribution during model training.

[0091] The preprocessed data is input into the image analysis model for forward propagation. The data passes through various layers in the model, including convolutional layers, pooling layers, and fully connected layers, ultimately yielding the output. The output can be the probability values ​​of each outcome corresponding to the information recognition result. The category with the highest probability is selected from the output vector as the corresponding information recognition result.

[0092] The technical solution of this embodiment involves acquiring images of the vulva and genitalia to be processed, and performing image enhancement processing on these images to obtain target images of the vulva and genitalia. These target images are then input into a pre-trained image recognition model to obtain regions of interest (ROI) images of the vulva and genitalia corresponding to the images to be processed. Based on a preset mapping relationship between vulvar and genitalia state recognition dimensions and vulvar and genitalia locations, the ROI images are grouped to obtain ROI image groups corresponding to each preset vulvar and genitalia state recognition dimension. These ROI image groups are then input into an image analysis model corresponding to the preset vulvar and genitalia state recognition dimension to obtain the corresponding information recognition results for that dimension, and these results are then displayed. This technical solution solves the problems of low efficiency and significant subjective influence in manual vulvar and genitalia state analysis, improving the efficiency of vulvar and genitalia state analysis, obtaining more objective information recognition results, and providing greater convenience for relevant personnel during vulvar and genitalia state analysis.

[0093] Figure 7 This is a schematic diagram of a vulvar image processing device according to an embodiment of the present invention. This embodiment is applicable to scenarios involving vulvar image processing. The vulvar image processing device can be implemented in software and / or hardware and integrated into a computer terminal device with application development capabilities.

[0094] like Figure 7 As shown, the internal and external vaginal image processing device includes: an image acquisition module 510, an image recognition module 520, an image grouping module 530, and an image analysis module 540.

[0095] The system includes the following modules: an image acquisition module 510, which acquires original images of the vulva and identifies the clarity of these images, selecting those that meet preset clarity requirements as the vulva images to be processed; an image recognition module 520, which inputs the vulva images to be processed into a pre-trained image recognition model to obtain the region of interest (ROI) images of the vulva and genitals corresponding to the images; an image grouping module 530, which groups the ROI images according to the preset mapping relationship between vulva and genital state recognition dimensions and vulva and genital areas, obtaining ROI image groups corresponding to each preset vulva and genital state recognition dimension; and an image analysis module 540, which inputs the ROI image groups into the image analysis model corresponding to the preset vulva and genital state recognition dimensions to obtain the information recognition results for the corresponding preset vulva and genital state recognition dimensions and displays the information recognition results.

[0096] The technical solution of this embodiment involves acquiring original images of the vulva and anterior vagina, identifying the clarity of these images, and selecting those images whose clarity meets preset image clarity conditions as images to be processed. These images are then input into a pre-trained image recognition model to obtain regions of interest (ROI) images of the vulva and anterior vagina corresponding to the images. Based on a preset mapping relationship between vulvar and anterior vaginal state recognition dimensions and the vulvar and anterior vaginal regions, the ROI images are grouped to obtain ROI image groups corresponding to each preset vulvar and anterior vaginal state recognition dimension. These ROI image groups are then input into an image analysis model corresponding to the preset vulvar and anterior vaginal state recognition dimension to obtain the corresponding information recognition results for that dimension, and these results are then displayed. This embodiment of the invention solves the problems of low efficiency and significant subjective influence in manual vulvar and anterior vaginal state assessment, improving the efficiency of assessment, obtaining more objective information recognition results, and providing greater convenience for relevant personnel during vulvar and anterior vaginal assessment.

[0097] In one alternative implementation, the image acquisition module 510 is specifically used for: In response to the first trigger operation of any internal or external vulva control in the image acquisition interface, the system enters the state of image acquisition of the target internal or external vulva corresponding to the internal or external vulva control. In response to the second trigger operation of the vulva control, the original vulva image corresponding to the target vulva is obtained, and the corresponding vulva identification is added to the original vulva image; The image acquisition interface displays controls for the internal and external vulva areas, respectively.

[0098] In one alternative implementation, the image acquisition module 510 may also be specifically used for: After entering the state of image acquisition of the target internal and external vulva corresponding to the internal and external vulva control, a preset prompt message for image acquisition of the target internal and external vulva is displayed.

[0099] In an optional embodiment, the internal and external vaginal image processing apparatus further includes an information recognition result editing module, used for: On the information recognition results display page, in response to any modification operation to the information recognition results of any preset internal and external genital state recognition dimension, the information recognition results corresponding to the modification operation are updated.

[0100] In one alternative implementation, the image acquisition module 510 may also be specifically used for: Original internal and external vulvar images whose clarity does not meet the preset image clarity conditions are marked as unclear internal and external vulvar images; a prompt message for re-acquiring the image associated with the unclear internal and external vulvar images is displayed.

[0101] In an optional embodiment, the internal and external vaginal image processing apparatus further includes an information recognition result editing module, used for: On the information recognition result display page, in response to the evaluation information input operation, the internal and external genital status evaluation input information is obtained and displayed; Among them, the input information for the evaluation of the internal and external vulva status is the evaluation information corresponding to the preset internal and external vulva status recognition dimension, which is not determined based on the image of the internal and external vulva to be processed.

[0102] In one alternative implementation, the image recognition module 520 may also be specifically used for: Image enhancement processing is performed on the images of the inner and outer vulva to be processed to obtain the target images of the inner and outer vulva; The target internal and external vulva images are input into a pre-trained image recognition model; The image recognition model includes a fast feature encoding module based on a convolutional architecture and a fully connected decision module.

[0103] In one alternative implementation, the image recognition module 520 may also be specifically used for: The images of the vulva to be processed are input into a pre-trained semantic segmentation model for private parts to obtain the effective and invalid pixel regions in the images to be processed. The invalid pixel regions in the images of the vulva to be processed are then removed to obtain new images of the vulva to be processed. Based on the standard coordinate system of the internal and external vulva, the new internal and external vulva images to be processed are adaptively corrected to obtain the corrected internal and external vulva images to be processed. Light compensation is performed on the corrected internal and external vulvar images to obtain the target internal and external vulvar images.

[0104] In one alternative implementation, the image recognition module 520 may also be specifically used for: Based on the pixel attribute features of secretions, identify secretions in images of the target vulva and vagina; The secretions are removed from the target vulva image, and the target vulva image is repaired based on the pixel information around the secretions to obtain a new target vulva image.

[0105] In one alternative implementation, the image acquisition module 510 may also be specifically used for: In response to the configuration operation of image acquisition parameters, at least one parameter of the image acquisition device for acquiring raw internal and external images is configured, including focal length, brightness, saturation, and hue.

[0106] In one alternative implementation, the image acquisition module 510 may also be specifically used for: In response to the triggering operation of the image acquisition process recording function, the image acquisition device acquires and saves the image information of the internal and external vulva images to be processed until all internal and external vulva images to be processed are acquired.

[0107] In one alternative embodiment, the internal and external vaginal image processing apparatus further includes an image editing module for: On the display interface of any internal or external vulva image to be processed, in response to any image editing operation, the corresponding image editing result is obtained; The image editing operations include at least one of the following: image rotation, marking, deletion, and image order adjustment.

[0108] The internal and external vulva image processing apparatus provided in the embodiments of the present invention can execute the internal and external vulva image processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0109] In specific application scenarios, such as in clinical gynecological examinations, when colposcopy is used to acquire colposcopy images, the internal and external vulvar image processing device provided in this embodiment of the invention can be used as the corresponding colposcopy image processing device to process the colposcopy images. These colposcopy images typically involve images of the cervix, vagina, and other areas.

[0110] In private medical aesthetics / private plastic surgery applications, when examining the vulva and genitals, the corresponding vulva and genital images can be obtained using vulva and genital examination equipment, and then processed using the vulva and genital image processing device provided in this embodiment of the invention.

[0111] Figure 8 This is a schematic diagram of the structure of an internal and external vulva image processing system provided in an embodiment of the present invention.

[0112] like Figure 8 As shown, the internal and external vaginal image processing system includes: An image acquisition device, at least one image display device, and an image processing device; The image acquisition device is used to acquire raw images of the internal and external genitalia and synchronize these images to the image processing device. The image acquisition device can be a colposcope used in clinical settings, or it can be an image acquisition device for the internal and external genitalia used in other private medical aesthetic / plastic surgery scenarios.

[0113] An image processing device is used to acquire raw images of the internal and external vulva and display them through an image display device; it is also used to implement the internal and external vulva image processing method provided in any embodiment of the present invention, performing image processing on the internal and external vulva images to be processed in the raw internal and external vulva images. The raw internal and external vulva images can be images acquired by an image acquisition device, and the internal and external vulva images to be processed can be raw internal and external vulva images that have undergone image clarity screening, or raw internal and external vulva images that do not meet the image clarity requirements but have met the clarity requirements after image enhancement processing. The raw internal and external vulva images acquired by the image processing device can be images acquired in real time or pre-acquired images stored in an image storage path.

[0114] The image display device can be a monitor of an image processing device or other display devices. When multiple image display devices are set up, multi-screen synchronous display can be performed so that multiple people can watch at the same time.

[0115] The internal and external vulvar image processing system is suitable for scenarios such as visual gynecological examinations, private medical aesthetic assessments, pelvic floor assessments, and physical examination centers.

[0116] In a specific example, the architecture of the internal and external vulvar image processing system can be referenced. Figure 9 The system architecture diagram shown is shown. Figure 9 The system architecture includes servers, computer hosts, printers, and image acquisition devices.

[0117] The server can be a third-party system, allowing users to obtain information related to vaginal condition analysis and the analysis object. The image acquisition device can be a camera device used to examine the internal and external genitalia.

[0118] The computer host is equipped with a vaginal image processing device and is connected to the image acquisition device. It displays real-time video from the image acquisition device and has functions such as taking pictures, image processing, recording video, creating new clients and client lists, evaluation, artificial intelligence-based analysis, report generation, and system settings. It can realize the vulvar image processing method provided in any embodiment of the present invention.

[0119] After the computer host obtains the analysis object information from the server, the user holds a handheld image acquisition device to examine the analysis object, while simultaneously adjusting the examination position by viewing the video feed from the computer host. After the examination, an evaluation is performed. The system can call upon AI-based image recognition and analysis models to recognize the image, automatically analyze the recognition results, and generate content including AI analysis explanations to assist the user. A report is then generated and printed. Users can be gynecologists, nurses, and / or other operators.

[0120] Understandably, the report can be a final assessment conclusion based on the explicit features preset by the system. Specifically, it can include the following assessment content: an overall assessment from different dimensions such as health, aesthetics, fullness, lubrication, sensitivity, vaginal mucosa, and pelvic floor muscle strength; separately assessing the vulva (pubic hair, mons pubis, labia majora, labia minora, clitoris, perineum) and the vulva (secretions, cervical condition, lubrication, fullness, tightness, and feeling of coverage); and the condition, color, elasticity, thickness, and folds of the vaginal mucosa. Therefore, the vulvar image processing system can provide a set of scientific assessment dimensions and standardized assessment criteria.

[0121] Figure 10 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Figure 10 A block diagram of an exemplary computer device 12 suitable for implementing embodiments of the present invention is shown. Figure 10 The computer device 12 shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities, such as intelligent controllers and servers, mobile phones, and other terminal devices.

[0122] like Figure 10 As shown, the computer device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0123] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0124] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0125] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 10 Not shown; usually referred to as a "hard drive"). Although Figure 10 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0126] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0127] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although... Figure 10As not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, R AID systems, tape drives, and data backup storage systems.

[0128] Processing unit 16 executes various functional applications and data processing by running programs stored in system memory 28, such as implementing the internal and external vaginal image processing method provided in this embodiment, which includes: Obtain the original internal and external vulva images, identify the clarity of the original internal and external vulva images, and use the original internal and external vulva images whose clarity meets the preset image clarity conditions as the internal and external vulva images to be processed. The images of the vulva and genitalia to be processed are input into a pre-trained image recognition model to obtain the region of interest images of the vulva and genitalia corresponding to the images of the vulva and genitalia to be processed. Based on the mapping relationship between the preset internal and external vulvar state recognition dimensions and the internal and external vulvar parts, the region of interest images are grouped to obtain the region of interest image group corresponding to each preset internal and external vulvar state recognition dimension; The image group of the region of interest is input into the image analysis model corresponding to the preset internal and external vulvar state recognition dimension to obtain the information recognition result of the preset internal and external vulvar state recognition dimension, and the information recognition result is displayed.

[0129] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the internal and external vaginal image processing method provided in any embodiment of this invention. The method includes: Obtain the original internal and external vulva images, identify the clarity of the original internal and external vulva images, and use the original internal and external vulva images whose clarity meets the preset image clarity conditions as the internal and external vulva images to be processed. The images of the vulva and genitalia to be processed are input into a pre-trained image recognition model to obtain the region of interest images of the vulva and genitalia corresponding to the images of the vulva and genitalia to be processed. Based on the mapping relationship between the preset internal and external vulvar state recognition dimensions and the internal and external vulvar parts, the region of interest images are grouped to obtain the region of interest image group corresponding to each preset internal and external vulvar state recognition dimension; The image group of the region of interest is input into the image analysis model corresponding to the preset internal and external vulvar state recognition dimension to obtain the information recognition result of the preset internal and external vulvar state recognition dimension, and the information recognition result is displayed.

[0130] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0131] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0132] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0133] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, Python, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0134] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the internal and external vulvar image processing method provided in any embodiment of this application.

[0135] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, Python, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0136] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0137] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for processing images of the vulva and anus, characterized in that, include: Obtain original internal and external vulvar images, identify the clarity of the original internal and external vulvar images, and use the original internal and external vulvar images whose clarity meets the preset image clarity conditions as the internal and external vulvar images to be processed. The images of the vulva to be processed are input into a pre-trained image recognition model to obtain the region of interest images of the vulva corresponding to the images of the vulva to be processed. Based on the mapping relationship between the preset internal and external vulvar state recognition dimensions and the internal and external vulvar parts, the region of interest images are grouped to obtain a region of interest image group corresponding to each preset internal and external vulvar state recognition dimension; The image group of the region of interest is input into the image analysis model corresponding to the preset internal and external vulvar state recognition dimension to obtain the information recognition result of the preset internal and external vulvar state recognition dimension, and the information recognition result is displayed.

2. The method according to claim 1, characterized in that, The process of obtaining the original internal and external vulvar images includes: In response to the first trigger operation of any internal or external vulva control in the image acquisition interactive interface, the system enters a state of image acquisition of the target internal or external vulva corresponding to the internal or external vulva control. In response to the second trigger operation of the vulva control, the original vulva image corresponding to the target vulva is obtained, and the corresponding vulva identifier is added to the original vulva image. The image acquisition interface displays controls for the internal and external vulva areas, respectively.

3. The method according to claim 2, characterized in that, The method further includes: After entering the state of image acquisition of the target internal and external vulva corresponding to the internal and external vulva control, a preset prompt message for image acquisition of the target internal and external vulva is displayed.

4. The method according to claim 1, characterized in that, The method further includes: On the information recognition result display page, in response to a modification operation on the information recognition result of any of the preset internal and external genital states recognition dimensions, the information recognition result corresponding to the modification operation is updated.

5. The method according to claim 1, characterized in that, Also includes: Original internal and external vulvar images whose clarity does not meet the preset image clarity conditions are marked as unclear internal and external vulvar images; The system displays a prompt message indicating that the image associated with the unclear internal and external vulvar images has been retrieved.

6. The method according to claim 1, characterized in that, The method further includes: On the information recognition result display page, in response to the evaluation information input operation, the internal and external genital status evaluation input information is acquired and displayed; The input information for evaluating the state of the vulva and genitalia is not the evaluation information corresponding to the preset vulva and genitalia state recognition dimension determined based on the vulva and genitalia image to be processed.

7. The method according to claim 1, characterized in that, The step of inputting the images of the internal and external genitalia to be processed into a pre-trained image recognition model includes: The images of the inner and outer vulva to be processed are subjected to image enhancement processing to obtain the target inner and outer vulva images; The target internal and external vulva images are input into a pre-trained image recognition model; The image recognition model includes a U-shaped network module.

8. The method according to claim 7, characterized in that, The image enhancement process is performed on the internal and external vulva images to be processed to obtain target internal and external vulva images, including: The images of the vulva to be processed are input into a pre-trained semantic segmentation model for private parts to obtain the effective and invalid pixel regions in the images to be processed. The invalid pixel regions in the images of the vulva to be processed are then removed to obtain new images of the vulva to be processed. Based on the standard coordinate system of the internal and external vulva, the new internal and external vulva images to be processed are adaptively corrected to obtain the corrected internal and external vulva images to be processed. Light compensation is performed on the corrected internal and external vulvar images to obtain the target internal and external vulvar images.

9. The method according to claim 8, characterized in that, Also includes: Based on the pixel attribute features of the secretions, the secretions in the target internal and external vulva images are identified; The secretions are removed from the target vulva image, and the target vulva image is repaired based on the pixel information around the secretions to obtain a new target vulva image.

10. The method according to claim 2, characterized in that, The process of obtaining the original internal and external vulvar images also includes: In response to the triggering operation of the image acquisition process recording function, the image information acquired by the image acquisition device for acquiring the original internal and external vulvar images is obtained and saved until all the original internal and external vulvar images are acquired.

11. An internal and external vaginal image processing device, characterized in that, include: The image acquisition module is used to acquire original internal and external vulvar images, identify the clarity of the original internal and external vulvar images, and use the original internal and external vulvar images whose clarity meets the preset image clarity conditions as internal and external vulvar images to be processed. The image recognition module is used to input the images of the vulva to be processed into a pre-trained image recognition model to obtain the region of interest image of the vulva corresponding to the images of the vulva to be processed. The image grouping module is used to group the region of interest images according to the preset mapping relationship between the internal and external vulva state recognition dimensions and the internal and external vulva parts, so as to obtain a region of interest image group corresponding to each preset internal and external vulva state recognition dimension. The image analysis module is used to input the image group of the region of interest into the image analysis model corresponding to the preset internal and external vulvar state recognition dimension, obtain the information recognition result of the preset internal and external vulvar state recognition dimension, and display the information recognition result.

12. A system for processing images of internal and external genitalia, characterized in that, include: An image acquisition device, at least one image display device, and an image processing device; The image acquisition device is used to acquire original internal and external vulvar images and synchronize the original internal and external vulvar images to the image processing device. The image processing device is used to acquire the original internal and external vulvar images and to display the original internal and external vulvar images through the image display device; it is also used to implement the internal and external vulvar image processing method as described in any one of claims 1-10, and to perform image processing on the internal and external vulvar images to be processed in the original internal and external vulvar images.

13. A computer device, characterized in that, The computer device includes: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the internal and external vulvar image processing method as described in any one of claims 1-10.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the internal and external vulvar image processing method as described in any one of claims 1-10.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the internal and external vulvar image processing method as described in any one of claims 1-10.

Images