Face recognition device and method that update feature amounts at different frequencies based on estimated distance
US-9621779-B2 · Apr 11, 2017 · US
US10496874B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10496874-B2 |
| Application number | US-201615765951-A |
| Country | US |
| Kind code | B2 |
| Filing date | Sep 28, 2016 |
| Priority date | Oct 14, 2015 |
| Publication date | Dec 3, 2019 |
| Grant date | Dec 3, 2019 |
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.
In order to eliminate erroneous detection in a case where a plurality of facial regions are detected in a captured image, facial detection device ( 2 ) of the present disclosure is a facial detection device that detects a facial region of a person from captured images which are continuous in time series, including a processor ( 15 ) that performs facial detection processing of detecting the facial region from the captured images and error determination processing of calculating a moving direction of each facial region between the captured images that are sequential in time series, and determining whether or not the detection as a facial region is correct with respect to a plurality of facial regions in which a correlation degree in the moving directions of the facial regions is equal to or larger than a predetermined threshold value, in a case where a plurality of facial regions are detected.
Opening claim text (preview).
The invention claimed is: 1. A facial detection device that detects a facial region of a person from captured images which are continuous in time series, comprising: a processor that performs facial detection processing of detecting the facial region from the captured images, error determination processing of calculating moving directions of each facial region between the captured images that are sequential in time series, and determining whether or not detection as a facial region is correct with respect to a plurality of facial regions in which a correlation degree in the moving directions of the facial regions is equal to or larger than a predetermined threshold value, in a case where a plurality of facial regions are detected. 2. The facial detection device of claim 1 , wherein, by performing the error determination processing, a facial region having the largest evaluation value of facial likeness of the facial region is determined as correct detection and the other facial regions are determined as erroneous detection, in the plurality of facial regions in which the correlation degree of the moving directions of the facial regions is equal to or larger than the predetermined threshold value. 3. The facial detection device of claim 1 , wherein, by performing the error determination processing, a facial region, in which a coordinate value at a center of gravity of the facial region in a height direction of the person is an extreme value, is determined as correct detection and the other facial regions are determined as erroneous detection, in the plurality of facial regions in which the correlation degree of the moving directions of the facial regions is equal to or larger than the predetermined threshold value. 4. The facial detection device of claim 1 , wherein, by performing the error determination processing, a facial region in which an evaluation value of facial likeness of the facial region is equal to or larger than a predetermined threshold value is determined as correct detection and the other facial regions are determined as erroneous detection, in the plurality of facial regions in which the correlation degree of the moving directions of the facial regions is equal to or larger than the predetermined threshold value. 5. A facial detection system comprising: the facial detection device according to claim 1 ; and an imaging device that continuously captures a facial region of a person in time series. 6. A facial detection method for detecting a facial region of a person from captured images that are continuous in time series, comprising: a facial detection processing step of detecting the facial region from the captured images, and error determination processing step of calculating moving directions of each facial region between the captured images that are sequential in time series and determining whether or not detection as a facial region is correct with respect to a plurality of facial regions in which a correlation degree in the captured moving directions of the facial regions is equal to or larger than a predetermined threshold value, in a case where a plurality of facial regions are detected.
Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries · CPC title
Feature extraction; Face representation · CPC title
using comparisons between temporally consecutive images · CPC title
Matching criteria, e.g. proximity measures · CPC title
Face · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.