Method for determining a perfume according to the physiognomic features of a person's face

By employing a neural network to analyze facial features and match them with perfume databases, the method objectively selects perfumes that align with a user's physiognomic characteristics, enhancing the accuracy and speed of perfume selection, addressing the subjectivity and inaccuracy of existing methods.

WO2025014393A1PCT designated stage expired Publication Date: 2025-01-16OGANYAN ARMEN ARKADIEVICH
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/RU2024/000250
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-07-10
Filing Date
2024-07-29
Publication Date
2025-01-16

AI Technical Summary

Technical Problem

Current methods for selecting a suitable perfume are subjective and inaccurate, relying on consultant experience and verbal information, which can lead to low accuracy due to incomplete data on perfume characteristics and user preferences.

Method used

A method using a neural network to analyze physiognomic characteristics of a person's face, comparing facial features with a database to objectively select perfumes with matching aromatic, fragrant, and essential substances, arranged in specific notes, thereby automating the perfume selection process.

Benefits of technology

This approach increases the accuracy and speed of selecting perfumes that complement a user's image by leveraging objective facial analysis and extensive databases, reducing subjective errors and improving the matching process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure RU2024000250_16012025_PF_FP_ABST
    Figure RU2024000250_16012025_PF_FP_ABST
Patent Text Reader

Abstract

The invention relates to a method for selecting a perfume for a person. The method consists in feeding a database with information about perfumes, the aromatic substances of which they are comprised, and the correlation between people's facial features and said aromatic substances. Using a neural network, the individual physiognomic features of the face of a person for whom a perfume is to be selected are determined from an uploaded image. The determined individual features are compared with the facial features of people in the database, and people with similar individual features are found. The aromatic substances that correlate with the individual physiognomic features of the face of the person on the uploaded image are selected from the database and a perfume is selected that contains the aromatic substances in question. The invention makes it possible to more accurately determine a suitable perfume for a specific person according to their external facial features.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Fashion-related customized perfume recommendation system using ai

    KR102495868B1

  • Big data-based user-customized perfume recommendation system and the method therefor

    KR102534852B1

  • A DEVICE FOR SELECTING PRODUCTS THAT CORRESPOND TO THE USER'S SIZE

    RU148909U1

  • Clothes registration device and clothes recommendation device, as well as online system containing thereof

    RU2768558C1

  • Personalized beauty system

    US20200098444A1