Measurement system and method for training a machine learning model therefor
AssigneeHunbiome Co., Ltd.
InventorsYongju AN, Kung AHN, Boreum PARK
Life of this patent
Estimating the term…
Abstract
The present invention relates to a skin condition measurement system, wherein the measurement system includes: a sub-device including a color sensor for receiving an optical signal; and a main device including a reception hole for forming a path for the optical signal incident to the color sensor and a slot to which a film for collecting oil of a user's skin is inserted, wherein the slot extends to the reception hole.
Claims21
A method for training a machine learning model for identifying skin types, the method comprising:
- collecting skin-related data for a group of users;
- determining a data set of skin features based on the collected skin-related data;
- and
- performing clustering on the data set of skin features to generate a set of clusters corresponding to a set of skin types.
A measurement system comprising:
- a sub-device including a color sensor configured to receive an optical signal;
- and
- a main device including a receiving hole configured to form a path of the optical signal incident on the color sensor, and a slot in which a film having user skin oil collected thereon is inserted,
- wherein the slot extends to the receiving hole.
20-29. (canceled)
A method for implementing a measurement system comprising:
- an elasticity sensor that measures a force by which the skin pushes a protrusion or a displacement of the protrusion contacting the skin;
- a moisture sensor comprising a comb-shaped electrode contacting the skin and a conductive pad absorbing skin moisture, and measuring an electrical resistance to determine moisture content in the skin;
- a sub-device including the elasticity sensor and the moisture sensor;
- and
- a main device electrically connected to the sub-device, configured to acquire data related to skin elasticity and skin moisture and display information about the user's skin condition, the method comprising:
- acquiring skin elasticity data and moisture data of a user from the sub-device;
- determining user values for a set of skin metrics from the skin-related data;
- identifying a skin type that most closely represents the user's skin by comparing the user values with skin metric values corresponding to each of a set of skin types;
- and
- providing information about the identified skin type of the user.
Dependencies are inferred from the claim text.