Dynamic facial feature substitution for video conferencing
US-2015381939-A1 · Dec 31, 2015 · US
US2017068845A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2017068845-A1 |
| Application number | US-201615257225-A |
| Country | US |
| Kind code | A1 |
| Filing date | Sep 6, 2016 |
| Priority date | Sep 7, 2015 |
| Publication date | Mar 9, 2017 |
| Grant date | — |
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.
According to an embodiment, a people search system includes a receiver, a detector, a search unit, and a display. The search unit obtains features of a first face image and a second face image of a predetermined person and searches for the predetermined person based on a similarity between the features of the first and the second face images when an inhibiting factor is not detected, and generates a third face image that is a composite image of the second face image and the inhibiting factor, obtains features of the first and the third face images, and searches for the predetermined person based on a similarity between the features of the first and the third face images when the inhibiting factor is detected The display displays the search result of the predetermined person obtained by the search unit.
Opening claim text (preview).
1 . A people search system comprising: a receiver that receives image data captured by an image-capturing unit provided so as to be capable of capturing people passing through a first location; a detector that detects an inhibiting factor that inhibits a search for a predetermined person based on a face image from a first face image contained in the image data; a search unit that obtains a feature of the first face image and a feature of a second face image of the predetermined person and searches for the predetermined person based on a similarity between the feature of the first face image and the feature of the second face image when the inhibiting factor has not been detected, and generates a third face image that is a composite image of the second face image and the inhibiting factor, obtains the feature of the first face image and a feature of the third face image, and searches for the predetermined person based on a similarity between the feature of the first face image and the feature of the third face image when the inhibiting factor has been detected; and a display that displays a search result of the predetermined person obtained by the search unit. 2 . The people search system according to claim 1 , wherein the search unit generates the third face image by combining only the inhibiting factor detected from the first face image with the second face image. 3 . The people search system according to claim 1 , wherein when the similarity between the feature of the first face image and the feature of the third face image is equal to or higher than a certain threshold, the display displays the first face image, the second face image, and the third face image, and, when the similarity between the feature of the first face image and the feature of the third face image is lower than the certain threshold, the display displays the first face image and the third face image except the second face image. 4 . The people search system according to claim 1 , wherein the detector unit detects at least one of concealment, a human race, facial orientation, headwear, glasses, sunglasses, an accessory, a lighting condition, and image quality in the face image as the inhibiting factor. 5 . The people search system according to claim 1 , wherein when the inhibiting factor has not been detected, the search unit finds the predetermined person when the similarity between the feature of the first face image and the feature of the second face image exceeds a certain threshold, and, when the inhibiting factor has been detected, the search unit finds the predetermined person when the similarity between the feature of the first face image and the feature of the third face image exceeds the certain threshold. 6 . The people search system according to claim 1 , further comprising: a first storage that stores therein, as the second face image, the first face image and the third face image that have been used in searching for the predetermined person in association with identification information of the predetermined person, wherein when the inhibiting factor has not been detected, the search unit searches for the predetermined person based on the similarity between the feature of the first face image and the feature of the second face image stored in the first storage, and, when the inhibiting factor has been detected, the search unit generates the third face image that is a composite image of the second face image stored in the first storage and the inhibiting factor. 7 . The people search 1 system according to claim 1 , wherein when the inhibiting factor has not been detected, the search unit does not generate the third face image. 8 . The people search system according to claim 3 , wherein when the similarity between the feature of the first face image and a feature of the third face image is equal to or higher than the certain threshold, the display displays third face image whose similarities to the feature of the first image are lower than the certain threshold among the third face images, in descending order of similarity to the feature of the first face image. 9 . The people search system according to claim 1 , further comprising a second storage that stores therein a search result of the predetermined person obtained by the search unit. 10 . A people search method comprising: receiving image data captured by an image-capturing unit provided so as to be capable of capturing people passing through a first location; detecting an inhibiting factor that inhibits a search for a predetermined person based on a face image from a first face image contained in the image data; obtaining a feature of the first face image and a feature of a second face image of the predetermined person and searching for the predetermined person based on a similarity between the feature of the first face image and the feature of the second face image when the inhibiting factor has not been detected; generating a third face image that is a composite image of the second face image and the inhibiting factor, obtaining the feature of the first face image and a feature of the third face image, and searching for the predetermined person based on a similarity between the feature of the first face image and the feature of the third face image when the inhibiting factor has been detected; and displaying a search result of the predetermined person on a display. 11 . The people search method according to claim 10 , wherein the generating includes generating the third face image by combining only the inhibiting factor detected from the first face image with the second face image. 12 . The people search method according to claim 10 , wherein when the similarity between the feature of the first face image and the feature of the third face image is equal to or higher than a certain threshold, the displaying includes displaying the first face image, the second face image, and the third face image on the display, and when the similarity between the feature of the first face image and the feature of the third face image is lower than the certain threshold, the displaying includes displaying the first face image and the third face image except the second face image on the display. 13 . The people search method according to claim 10 , wherein the detecting includes detecting at least one of concealment, a human race, facial orientation, headwear, glasses, sunglasses, an accessory, a lighting condition, and image quality in the face image as the inhibiting factor. 14 . The people search method according to claim 10 , wherein when the inhibiting factor has not been detected, the predetermined person is found when the similarity between the feature of the first face image and the feature of the second face image exceed a certain threshold, and, when the inhibiting factor has been detected, the predetermined person is found when the similarity between the feature of the first face image and the feature of the third face image exceeds the certain threshold. 15 . The people search method according to claim 10 , further comprising: storing, as the second face image, the first face image and the third face image that have been used in searching for the predetermined person in association with identification information of the predetermined person in a first storage, wherein when the inhibiting factor has not been detected, the searching includes searching for the predetermined person based on the similarity between the feature of the first face image and the feature of the second face image stored in the first storage, and, when the inhibiting factor has been detected, th
Face · CPC title
Physics · mapped topic
Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast · CPC title
Physics · mapped topic
Physics · mapped topic
Related publications grouped by family.
Answers are generated from the same data shown on this page.