Search

CN-122025016-A - Skin focus quantitative evaluation and intelligent pricing interaction system based on image recognition

CN122025016ACN 122025016 ACN122025016 ACN 122025016ACN-122025016-A

Abstract

The invention relates to the technical field of intelligent interaction, in particular to a skin focus quantitative evaluation and intelligent pricing interaction system based on image recognition, which comprises an image acquisition module, a control module and a control module, wherein the image acquisition module is used for acquiring a first image containing skin marks of a user and synchronously converting the first image into a second image which is suitable for a mobile terminal of the user; the system comprises a first image, a second image, a grid dividing module, an identification module, an interaction module and a price calculating module, wherein the first image or the second image is used for carrying out grid division on the first image or the second image, each grid is used as an interaction contact, the identification module is used for identifying and displaying the spot information in each grid, the interaction module is used for responding to the user to select or cancel the interaction contact, the price calculating module is used for matching the interaction contact with a preset grid unit price database to obtain the unit price of each selected interaction contact, and the interactive quotation containing the spot information is obtained according to the unit price summary. Compared with the prior art, the system provided by the invention effectively improves the interactive experience of the user.

Inventors

  • LIU LIQIANG

Assignees

  • 广州市中崎商业机器股份有限公司

Dates

Publication Date
20260512
Application Date
20260203

Claims (10)

  1. 1. An image recognition-based skin lesion quantitative evaluation and intelligent pricing interaction system is characterized by comprising the following components: The image acquisition module is used for acquiring a first image containing skin marks of a user and synchronously converting the first image into a second image suitable for a mobile terminal of the user; The grid division module is used for carrying out grid division on the first image or the second image, wherein each grid is used as an interactive contact; the identification module is used for identifying and displaying the speckle information in each grid; an interaction module for responding to the selection or cancellation of the interaction contact by the user, and And the pricing module is used for matching the interactive contacts with a preset grid unit price database to obtain unit price of each selected interactive contact, and summarizing according to the unit price to obtain the interactive quotation containing the spot information.
  2. 2. The image recognition-based skin lesion quantitative assessment and intelligent pricing interaction system of claim 1, wherein synchronously converting the first image into a second image adapted to a user mobile terminal comprises: calculating the scaling of a mobile terminal screen of a user relative to an interactive device screen; And scaling the first image according to the scaling ratio to obtain the second image.
  3. 3. The image recognition-based skin lesion quantitative assessment and intelligent pricing interaction system of claim 1, wherein the interaction module is further configured to: And scaling the grid distributed in the second image in an equal proportion in response to the scaling of the second image by the user.
  4. 4. The image recognition-based skin lesion quantitative assessment and intelligent pricing interaction system according to claim 1, wherein the patch information comprises at least a patch color value, a patch density, and a text label.
  5. 5. The image recognition-based skin lesion quantitative assessment and intelligent pricing interaction system according to claim 4, wherein the recognition module is configured with a patch attribute definition model; wherein the speckle attribute definition model is for: Extracting texture entropy features and edge gradient features of the first image or the second image; and judging the speckle type of the user according to the texture entropy characteristics and the edge gradient characteristics so as to generate a character mark containing the speckle type.
  6. 6. The image recognition-based skin lesion quantitative assessment and intelligent pricing interaction system according to claim 4, wherein the recognition module is configured with a color recognition model; wherein the color recognition model is for: converting pixels within each grid into uniform color space pixels for each grid; calculating the brightness average value of all the pixels in the uniform color space and the brightness value of a single pixel in the uniform color space in the grid; Defining the uniform color space pixels having the intensity values lower than the intensity mean as deposited pixels and generating a set of pigments from the plurality of deposited pixels as a pigmented area; and taking the color component mean value of the pigmentation area as a patch color value of a corresponding grid.
  7. 7. The image recognition-based skin lesion quantitative assessment and intelligent pricing interaction system according to claim 6, wherein the recognition module is configured with a speckle concentration calculation model; wherein, the speckle concentration calculation model is used for: calculating the euclidean distance of the pigmented section relative to a normal skin background as a color difference value; calculating a coverage area of the pigmented section; and carrying out weighted fusion calculation on the color difference value and the coverage area to obtain the speckle concentration.
  8. 8. The image recognition-based skin lesion quantitative assessment and intelligent pricing interaction system according to claim 1, further comprising an image preprocessing module for preprocessing the first image or the second image to eliminate facial glints of a user.
  9. 9. The image recognition-based skin lesion quantitative assessment and intelligent pricing interaction system according to claim 8, wherein the image preprocessing module is configured with an illumination component separation algorithm; The illumination component separation algorithm is used for: separating pixels in the grid into a diffuse reflection component and a specular reflection component, wherein the diffuse reflection component is used for representing facial pigment information, and the specular reflection component is used for representing facial luster; Calculating pixel distribution density and average brightness value of the specular reflection component in a user face area T; performing weighted operation on the pixel distribution density and the average brightness value to obtain a sebaceous gland active coefficient; Performing pixel mapping on the specular reflection component by utilizing the sebaceous gland active coefficient to generate a high light inhibition mask; And carrying out weighted stripping on specular reflection components in the first image by adopting the high light inhibition mask.
  10. 10. A computer device comprising a processor and a memory, the memory storing computer program instructions that, when executed by the processor, implement the image recognition-based skin lesion quantitative assessment and intelligent pricing interaction system of any of claims 1-9.

Description

Skin focus quantitative evaluation and intelligent pricing interaction system based on image recognition Technical Field The invention relates to the technical field of intelligent interaction. More particularly, the invention relates to an image recognition-based skin focus quantitative evaluation and intelligent pricing interactive system. Background In the picosecond laser speckle removing scene, a customer needs to register and carry out speckle assessment on a specific doctor, and provides speckle removing range description, a speckle removing scheme and corresponding quotation according to personal experience of the doctor. For clients, there is a certain poor information understanding, and the relevant evaluation criteria have no transparency, for example, two users have freckles on cheek parts, and the freckle-removing quotations of the two users are different, so that doctors are very busy, often lack effective communication time, medical disputes are easily caused when similar situations occur, and the freckle-removing experience of the clients is very poor. In view of the above, publication number CN116823250a discloses a remote billing system and method for laser beauty treatment, which automatically performs feature evaluation and information summarization on the face of the user by adopting face recognition technology, generates delivery information based on the information summarization result and links the user bank account to pay automatically. Although the method releases the evaluation time of doctors to a certain extent, certain defects exist in the transparency of information and the interactive space of users, particularly in the fact that the method cannot respond to the actual freckle removing will of the users and analyzes the optimal or user-satisfied freckle removing scheme for the users, the possibility of forced service and deduction exists, and the interactive experience of the users is poor. Disclosure of Invention In order to solve the technical problem of low customer experience, the invention discloses a skin focus quantitative evaluation and intelligent pricing interactive system based on image recognition. In a first aspect, the invention discloses a skin focus quantitative evaluation and intelligent pricing interactive system based on image recognition, which comprises the following steps: the image acquisition module is used for acquiring a first image containing skin marks of a user and synchronously converting the first image into a second image suitable for a mobile terminal of the user; the grid division module is used for carrying out grid division on the first image or the second image, wherein each grid is used as an interactive contact; the identification module is used for identifying and displaying the speckle information in each grid; an interactive module for responding to the user selection or cancellation of the interactive contacts, and And the pricing module is used for matching the interactive contacts with a preset grid unit price database to obtain unit price of each selected interactive contact, and obtaining an interactive quotation containing spot information according to unit price summarization. Preferably, the step of synchronously converting the first image into a second image adapted to the mobile terminal of the user includes: calculating the scaling of a mobile terminal screen of a user relative to an interactive device screen; And scaling the first image according to the scaling ratio to obtain a second image. Preferably, the interaction module is further configured to: In response to a user scaling the second image, a grid equi-scaled distributed across the second image is scaled. Preferably, the patch information at least comprises a patch color value, a patch density and a character mark. Preferably, the identification module is configured with a patch attribute definition model; wherein the patch attribute definition model is for: Extracting texture entropy features and edge gradient features of the first image or the second image; and judging the speckle type of the user according to the texture entropy characteristics and the edge gradient characteristics so as to generate a character mark containing the speckle type. Preferably, the recognition module is configured with a color recognition model; wherein the color recognition model is for: converting pixels within each grid into uniform color space pixels for each grid; calculating the brightness average value of all the pixels in the uniform color space and the brightness value of a single pixel in the uniform color space in the grid; Defining uniform color space pixels having a luminance value below the luminance mean as deposited pixels and generating a set of pigments from the plurality of deposited pixels as a pigmented area; The mean value of the color components of the pigmented areas is taken as the patch color value of the corresponding grid. Preferably, the identification m