Face impression analyzing method, aesthetic counseling method, and face image generating method

US9330298B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9330298-B2
Application numberUS-201214131374-A
CountryUS
Kind codeB2
Filing dateJul 6, 2012
Priority dateJul 7, 2011
Publication dateMay 3, 2016
Grant dateMay 3, 2016

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

The face impression analyzing device ( 100 ) includes a facial form acquiring unit ( 10 ), a face component analyzing unit ( 50 ), a face impression determining unit ( 60 ), and a storage unit ( 70 ). The facial form acquiring unit ( 10 ) acquires facial form information representing a form of a face surface of a subject. The storage unit ( 70 ) stores one or more feature values obtained by applying multivariate analysis to target population face information representing three-dimensional forms of facial surfaces of a target population formed by a plurality of persons, and tendency information indicating an impression tendency of a facial shape associated with each of the one or more feature values. The face component analyzing unit ( 50 ) calculates an amount of revelation of each of the one or more feature values of the face of the subject on the basis of the facial form information of the subject, and the feature value extracted from the target population face information. The face impression determining unit ( 60 ) refers to the storage unit ( 70 ), and acquires the impression tendency of the face of the subject or the degree of the impression tendency on the basis of the feature value of the face of the subject and the amount of revelation of the feature value.

First claim

Opening claim text (preview).

The invention claimed is: 1. A face impression analyzing method, comprising: providing, memory, one or more base vectors obtained by applying multivariate analysis to target population face information representing three-dimensional forms of facial surfaces of a target population formed by a plurality of persons; based on facial form information representing a form of a face surface of a subject, and the one or more base vectors provided from the memory and obtained by applying multivariate analysis to target population face information representing three-dimensional forms of facial surfaces of the target population formed by the plurality of persons, calculating, using processing circuitry, a weighting factor of each of the one or more base vectors in the face of the subject; and obtaining, using the processing circuitry, a degree of an impression tendency of a facial shape of the subject based on the weighting factor, wherein a correlation coefficient between the base vector and the impression tendency is greater than a critical value of a 5% significance level with the number of samples in the target population. 2. The face impression analyzing method according to claim 1 , wherein the target population face information is represented by a homologous model in which the number of data points and topology are consistent among the faces. 3. The face impression analyzing method according to claim 2 , further comprising: calculating the base vector of the subject by applying multivariate analysis to the target population face information containing the facial form information, wherein the facial form information of the subject is represented by the homologous model. 4. The face impression analyzing method according to claim 1 , further comprising: classifying the target population into a plurality of groups; and obtaining a group to which the subject belongs according to the weighting factor of the subject. 5. The face impression analyzing method according to claim 4 , further comprising: classifying the target population into the plurality of groups according to a degree of match of tendencies of a plurality of weighting factors related to plural base vectors having a correlation with the impression tendency above a threshold. 6. The face impression analyzing method according to claim 1 , wherein said obtaining the degree of the impression tendency is performed based on the weighting factor of at least one base vector, the at least one base vector corresponding to a second-dimension or higher, having a high correlation with the impression tendency, and extracted from the one or more base vectors obtained through the multivariate analysis. 7. The face impression analyzing method according to claim 6 , wherein the degree of the impression tendency is two or more impression tendencies selected from above or below an apparent age or actual age of the subject, a degree of being an adult face or baby face, a degree of an impression of having a small face, a degree of having a round face or long face, and a degree of an impression of having a large eye, and the one or more base vectors associated with each of these two or more impression tendencies include base vectors corresponding to dimensions different from each other. 8. The face impression analyzing method according to claim 7 , wherein the one or more base vectors associated with each of the two or more impression tendencies are formed only by base vectors corresponding to dimensions different from each other. 9. The face impression analyzing method according to claim 1 , wherein the degree of the impression tendency is above or below an apparent age or actual age of the subject. 10. The face impression analyzing method according to claim 1 , wherein the degree of the impression tendency is one or more selected from above or below an apparent age or actual age of the subject, a degree to which the subject has an adult face or baby face, a degree of an impression of having a small face, a degree of having a round face or long face, and a degree of an impression of having a large eye. 11. The face impression analyzing method according to claim 1 , further comprising: acquiring a three-dimensional coordinate value of a surface of the head and the face of the subject as the facial form information using a contact-type three-dimensional digitizer. 12. The face impression analyzing method according to claim 11 , wherein said acquiring the three-dimensional coordinate value includes: acquiring a three-dimensional coordinate value related to a plurality of feature points on the surface of the head using the contact-type three-dimensional digitizer, and acquiring a three-dimensional coordinate value related to another point on the surface of the head using a non-contact three-dimensional measurement device. 13. The face impression analyzing method according to claim 1 , further comprising: capturing a plurality of two-dimensional images on the head and the face of the subject from different angles; and calculating a three-dimensional coordinate value on the surface of the head as the facial form information based on the two-dimensional images. 14. The face impression analyzing method according to claim 1 , further comprising: applying multivariate analysis to the target population face information that does not contain the facial form information of the subject to obtain a plurality of base vectors continuing from a first-dimension to a predetermined dimension; and calculating the weighting factor by reproducing the facial form information of the subject through calculation including multiplication and addition applied to the base vectors and the weighting factor for each of the base vectors. 15. The face impression analyzing method according to claim 1 , further comprising: receiving selection of the impression tendency from the subject. 16. An aesthetic counseling method using the face impression analyzing method according to claim 1 , comprising: outputting aesthetic information associated in advance with the base vector having the calculated weighting factor more than or equal to a predetermined value. 17. The aesthetic counseling method according to claim 16 , wherein the aesthetic information is information indicating a group of the impression tendency that the subject belongs to, said group being selected according to a percentage of contribution of the base vector. 18. The aesthetic counseling method according to claim 17 , wherein a degree of the impression tendency is a degree at which the subject has an adult face or baby face, a degree of an impression of having a small face, a degree of having a round face or long face, or a degree of an impression of having a large eye, and aesthetic information associated in advance with the group to which the subject belongs and another group to which the subject does not belong is outputted. 19. The aesthetic counseling method according to claim 16 , wherein the aesthetic information is information indicating an aesthetic treatment method comprising any method of a cosmetic surgery method, an aesthetic massage method, a hair makeup method, and a cosmetic makeup method, or a hair cosmetic, or a cosmetic for makeup. 20. An aesthetic counseling method using the face impression analyzing method according to claim 1 , comprising: classifying the target population into a plurality of groups according to a degree of match of tendencies of a plurality of weighting factors related to plural base vectors

Assignees

Inventors

Classifications

  • G06Q50/10Primary

    Services · CPC title

  • Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods · CPC title

  • Feature extraction; Face representation · CPC title

  • based on approximation criteria, e.g. principal component analysis · CPC title

  • Stereo images · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9330298B2 cover?
The face impression analyzing device ( 100 ) includes a facial form acquiring unit ( 10 ), a face component analyzing unit ( 50 ), a face impression determining unit ( 60 ), and a storage unit ( 70 ). The facial form acquiring unit ( 10 ) acquires facial form information representing a form of a face surface of a subject. The storage unit ( 70 ) stores one or more feature values obtained by app…
Who is the assignee on this patent?
Imai Takeo, Kao Corp
What technology area does this patent fall under?
Primary CPC classification G06Q50/10. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue May 03 2016 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).