Dynamic facial feature substitution for video conferencing
US-2015381939-A1 · Dec 31, 2015 · US
US9245173B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9245173-B2 |
| Application number | US-201313772519-A |
| Country | US |
| Kind code | B2 |
| Filing date | Feb 21, 2013 |
| Priority date | Feb 29, 2012 |
| Publication date | Jan 26, 2016 |
| Grant date | Jan 26, 2016 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An apparatus for identifying a fake face is provided. A first eye image acquirer acquires a first eye image by taking a picture of a subject while radiating a first ray having a first wavelength. A second eye image acquirer acquires a second eye image by taking a picture of the subject while radiating a second ray having a second wavelength that is shorter than the first wavelength. A controller extracts a first area and a second area having brighter lightness than the first area from each of the first and second eye images, calculates a lightness of the first area and a lightness of the second area in the first eye image, and a lightness of the first area and a lightness of the second area in the second eye image, and determines whether the subject uses a fake face based on the calculated lightness.
Opening claim text (preview).
What is claimed is: 1. An apparatus for identifying a fake face, the apparatus comprising: a first eye image acquirer configured to acquire a first eye image by taking a picture of a subject while radiating a first ray having a first wavelength; a second eye image acquirer configured to acquire a second eye image by taking a picture of the subject while radiating a second ray having a second wavelength that is shorter than the first wavelength; and a controller configured to calculate a first lightness of a first area and a second lightness of a second area having brighter lightness than the first area in the first eye image, and a third lightness of the first area and a fourth lightness of the second area having brighter lightness than the first area in the second eye image, and to determine that the subject uses a fake face when amplitude of a high frequency component for a first spatial frequency which is converted from a difference between the first lightness and the second lightness is equal to or greater than amplitude of a high frequency component for a second spatial frequency which is converted from a difference between the third lightness and the fourth lightness, and to determine the subject uses a real face when the amplitude of the high frequency component for the first spatial frequency is less than the amplitude of the high frequency component for the second spatial frequency. 2. The apparatus of claim 1 , wherein the first ray includes an infrared ray, and the second ray includes a visible ray. 3. The apparatus of claim 1 , wherein the first area includes an iris area, and the second area includes a sclera area. 4. The apparatus of claim 1 , wherein the fake face includes any one of an artificial eye, an eye image on a photo, an eye image on a printed page, an eye of a mannequin, or an eye image played by a video. 5. A method of identifying a fake face by a fake face identification apparatus, the method comprising: acquiring a first eye image by taking a picture of a subject while radiating a first ray having a first wavelength; acquiring a second eye image by taking a picture of the subject while radiating a second ray having a second wavelength that is shorter than the first wavelength; extracting a first area and a second area having brighter lightness than the first area from each of the first eye image and the second eye image; calculating a first lightness of the first area and a second lightness of the second area in the first eye image, and a third lightness of the first area and a fourth lightness of the second area in the second eye image; converting a difference between the first lightness and the second lightness to a first spatial frequency and a difference between the third lightness and the fourth lightness to a second spatial frequency; determining the subject uses the fake face when amplitude of a high frequency component for the first spatial frequency is equal to or higher than amplitude of a high frequency component for the second spatial frequency; and determining the subject uses a real face when the amplitude of the high frequency component for the first spatial frequency is less than the amplitude of the high frequency component for the second spatial frequency. 6. The method of claim 5 , wherein the first ray includes an infrared ray, and the second ray includes a visible ray. 7. The method of claim 5 , wherein the first area includes an iris area, and the second area includes a sclera area. 8. The method of claim 5 , wherein the fake face includes any one of an artificial eye, an eye image on a photo, an eye image on a printed page, an eye of a mannequin, or an eye image played by a video. 9. The method of claim 5 , further comprising storing the first lightness, the second lightness, the third lightness, the fourth lightness, and a determining result of the controller.
Physics · mapped topic
Physics · mapped topic
Physics · mapped topic
Spoof detection, e.g. liveness detection · CPC title
Extraction of image or video features · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.