← Back to Patent Explorer
US7515739B2 Expired / Lapsed US ⏱️ 0.0 years remaining

Face detection

Assignee: Sony United Kingdom Ltd
•
Filing: 2003-11-28
•
Granted: 2009-04-07
•
Expires: 2023-11-28
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract A face detection apparatus associated methodology is provided to generate an output indicating a likelihood of a region of an image containing a face. The apparatus includes a comparing device for comparing the region with face data that indicates a presence of the face and for detecting respective likelihood values indicating the likelihood of the region containing the face in a group of respective different face size. A control device is provided for modifying at least one of the group and the likelihood values based on a face size or a range of face sizes appropriate to at least one classification of the image. The control device is responsive to metadata associated with the image that define the at least one classification of the image. The image is a part of a video sequence, and at least one classification includes a video program type.

Inventors

  • 👤 Robert Mark Stefan Porter
  • 👤 Ratna Rambaruth

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-11-09 12:37
CPC Classifications
G; G06; G06V; G06V40/00; G06V40/10; G06V40/16; G06V40/161

Claims Analysis

Total Claims: 16
Claim 1
Independent Claim 135 words
A face detection apparatus generating an output indicating a likelihood of a region of an image containing a face, the apparatus comprising: means for comparing the region with face data that indicates a presence of the face and for detecting respective likelihood values indicating the likelihood of the region containing the face in a group of respective different face sizes; and means for modifying at least one of the group and the likelihood values based on a face size or a range of face sizes appropriate to at least one classification of the image, the means for modifying being responsive to metadata associated with the image defining the at least one classification of the image, the image being a part of a video sequence and the at least one classification includes a video program type.
Claim 2
Dependent Claim 135 words
A face detection apparatus generating an output indicating a likelihood of a region of an image containing a face, the apparatus comprising: means for comparing the region with face data that indicates a presence of the face and for detecting respective likelihood values indicating the likelihood of the region containing the face in a group of respective different face sizes; and means for modifying at least one of the group and the likelihood values based on a face size or a range of face sizes appropriate to at least one classification of the image, the means for modifying being responsive to metadata associated with the image defining the at least one classification of the image, the image being a part of a video sequence and the at least one classification includes a video program type.
Claim 3
Dependent Claim 37 words
The apparatus according to claim 1 , wherein the means for comparing weighs the likelihood values to enhance the likelihood of the face in a face size appropriate to the at least one classification of the image.
Claim 4
Dependent Claim 48 words
The apparatus according to claim 1 , wherein the means for modifying selects a subset of the group for detecting the likelihood values, and the subset is dependent upon the face size or the range of face sizes appropriate to the at least one classification of the image.
Claim 5
Dependent Claim 25 words
The apparatus according to claim 1 , further comprising: means for detecting whether a greatest one of the likelihood values exceeds a threshold likelihood value.
Claim 6
Dependent Claim 60 words
The apparatus according to claim 1 , wherein the means for comparing derives attributes from respective blocks of the region, compares the derived attributes with attributes that indicate the presence of the face, and derives a probability of the presence of the face by a similarity between the derived attributes and the attributes that indicate the presence of the face.
Claim 7
Dependent Claim 28 words
The apparatus according to claim 5 , wherein the attributes that indicate the presence of the face comprise projections of image areas onto one or more image eigenblocks.
Claim 8
Dependent Claim 12 words
A video conferencing apparatus, comprising the apparatus according to claim 1 .
Claim 9
Dependent Claim 11 words
A surveillance apparatus comprising the apparatus according to claim 1 .
Claim 10
Dependent Claim 41 words
A display apparatus, comprising: a display screen; a video camera; and the apparatus according to claim 1 , wherein the video camera and the apparatus are arranged with respect to the display screen to detect faces looking at the display screen.
Claim 11
Independent Claim 131 words
A method of face detection for generating an output indicating a likelihood of a region of an image containing a face, the method comprising: comparing, with a processor the region with face data that indicates a presence of the face to detect likelihood values indicating the likelihood of the region containing the face in a group of respective different face sizes; and modifying at least one of the group and the likelihood values based on a face size or a range of face sizes appropriate to at least one classification of the image, in response to metadata associated with the image that defines the at least one classification of the image, wherein the image is part of a video sequence and the at least one classification includes a video program type.
Claim 12
Independent Claim 131 words
A method of face detection for generating an output indicating a likelihood of a region of an image containing a face, the method comprising: comparing, with a processor the region with face data that indicates a presence of the face to detect likelihood values indicating the likelihood of the region containing the face in a group of respective different face sizes; and modifying at least one of the group and the likelihood values based on a face size or a range of face sizes appropriate to at least one classification of the image, in response to metadata associated with the image that defines the at least one classification of the image, wherein the image is part of a video sequence and the at least one classification includes a video program type.
Claim 13
Dependent Claim 127 words
A computer-readable medium, including computer executable instructions, wherein the instructions when executed by a processor, cause the processor to perform a method comprising: comparing a region with face data that indicates a presence of a face to detect likelihood values indicating a likelihood of the region containing the face in a group of respective different face sizes; and modifying at least one of the group and the likelihood values based on a face size or a range of face sizes appropriate to at least one classification of an image, in response to metadata associated with the image that defines the at least one classification of the image, wherein the image is part of a video sequence and the at least one classification includes a video program type.
Claim 14
Dependent Claim 127 words
A computer-readable medium, including computer executable instructions, wherein the instructions when executed by a processor, cause the processor to perform a method comprising: comparing a region with face data that indicates a presence of a face to detect likelihood values indicating a likelihood of the region containing the face in a group of respective different face sizes; and modifying at least one of the group and the likelihood values based on a face size or a range of face sizes appropriate to at least one classification of an image, in response to metadata associated with the image that defines the at least one classification of the image, wherein the image is part of a video sequence and the at least one classification includes a video program type.
Claim 15
Dependent Claim 136 words
A face detection apparatus generating an output indicating a likelihood of a region of an image containing a face, the apparatus comprising: a comparator configured to compare the region with face data that indicates a presence of the face and to detect respective likelihood values indicating the likelihood of the region containing the face in a group of respective different face sizes; and a controller configured to modify at least one of the group and the likelihood values based on a face size or a range of face sizes appropriate to at least one classification of image, the controller is responsive to metadata associated with the image that define the at least one classification of the image, the image being part of a video sequence and the at least one classification includes a video program type.
Claim 16
Dependent Claim 136 words
A face detection apparatus generating an output indicating a likelihood of a region of an image containing a face, the apparatus comprising: a comparator configured to compare the region with face data that indicates a presence of the face and to detect respective likelihood values indicating the likelihood of the region containing the face in a group of respective different face sizes; and a controller configured to modify at least one of the group and the likelihood values based on a face size or a range of face sizes appropriate to at least one classification of image, the controller is responsive to metadata associated with the image that define the at least one classification of the image, the image being part of a video sequence and the at least one classification includes a video program type.

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 2012-04-06 2012-10-06 2013-04-07 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 2016-04-06 2016-10-06 2017-04-07 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2020-04-06 2020-10-06 2021-04-07 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag