Method for determining a skin colour of a face on basis of numerical values and corresponding system

System A system for determining a skin colour of a region of interest of a user, comprising:

• communication means (COM) that are suitable for communicating with a user computational device (APP) and that are configured to import, from an image library (LIB) of the user computational device (APP), at least one image (IMk) comprising a representation of the region of interest of the user, wherein the at least one image (IMk) includes metadata (MTDk, ts) timestamping the creation of the respective image and/or metadata (MTDk, geoloc) geolocating the creation of the respective image;
• processing means (PU) configured to perform processing (TS) of said at least one image (IMk) with a machine-learning model (AI_TS) suitable for providing, for each imported image (IMk), a single numerical value (ClrEstm_k) representative of the skin colour of the region of interest present in said at least one imported image (IMk), wherein the processing (TS) comprises pre-processing (P_TS) comprising a correction of the colour temperature (TempCorr) of each image (IMk) depending on the respective metadata (MTDk);
• the processing means (PU) furthermore being configured to perform evaluation (EVAL) of the skin colour of the region of interest on the basis of said one or more numerical values (ClrEstm_k) of each imported image,
• the system being further configured to recommend at least one cosmetic product based on said evaluation (EVAL) of the skin colour of the region of interest.

A non-transitory computer-readable medium comprising instructions that, when they are executed by a computer, cause the computer to perform method steps comprising:

• importing, from an image library of a user computational device, at least one image comprising a representation of the region of interest of the user;
• performing processing of said at least one image with a machine-learning model suitable for providing, for each imported image, a numerical value representative of the skin colour of the region of interest present in said at least one imported image;
• performing evaluation of the skin colour of the region of interest on the basis of said one or more numerical values of each imported image;
• and
• generating a recommendation of at least one cosmetic product based on said evaluation of the skin colour of the region of interest,
• wherein the at least one image includes metadata timestamping the creation of the respective image or metadata geolocating the creation of the respective image;
• wherein the processing comprises pre-processing comprising a correction of the colour temperature of each image depending on the respective metadata.

A method for determining a skin colour of a region of interest of a user, comprising:

• importing, from an image library (LIB) of a user computational device (APP), at least one image (IMk) comprising a representation of the region of interest of the user;
• performing processing (TS) of said at least one image (IMk) with a machine-learning model (AI_TS) suitable for providing, for each imported image (IMk), a numerical value (ClrEstm_k) representative of the skin colour of the region of interest present in said at least one imported image (IMk);
• performing evaluation (EVAL) of the skin colour of the region of interest on the basis of said one or more numerical values (ClrEstm_k) of each imported image, the method further comprising a recommendation of at least one cosmetic product based on said evaluation (EVAL) of the skin colour of the region of interest;
• wherein the at least one image (IMk) includes metadata (MTDk, ts) timestamping the creation of the respective image;
• wherein the evaluation (EVAL) of the skin colour is carried out on the basis of the numerical value of each image (ClrEstm_k) weighted (wght2) according to a current date and to respective timestamping metadata (ts).

A system for determining a skin colour of a region of interest of a user, comprising:

• communication means (COM) that are suitable for communicating with a user computational device (APP) and that are configured to import, from an image library (LIB) of the user computational device (APP), at least one image (IMk) comprising a representation of the region of interest of the user, at least one image (IMk) includes metadata (MTDk, ts) timestamping the creation of the respective image;
• processing means (PU) configured to perform processing (TS) of said at least one image (IMk) with a machine-learning model (AI_TS) suitable for providing, for each imported image (IMk), a single numerical value (ClrEstm_k) representative of the skin colour of the region of interest present in said at least one imported image (IMk), wherein the evaluation (EVAL) of the skin colour is carried out on the basis of the numerical value of each image (ClrEstm_k) weighted (wght2) according to a current date and to respective timestamping metadata (ts);
• the processing means (PU) furthermore being configured to perform evaluation (EVAL) of the skin colour of the region of interest on the basis of said one or more numerical values (ClrEstm_k) of each imported image;
• the system being further configured to recommend at least one cosmetic product based on said evaluation (EVAL) of the skin colour of the region of interest.