Patent US7020345B2 successfully refreshed from Google Patents.
US7020345B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
Methods and system for illuminant-compensation
Assignee: Industrial Technology Research Institute
•
Filing: 2001-04-26
•
Granted: 2006-03-28
•
Expires: 2021-04-26
Abstract
Abstract The present invention relates to methods and systems for an illuminant compensation. In particular, these methods and systems include a method for operations on an image, for example, an image of a human face. In the described methods and systems, it is determined for each pixel in the image whether it is part of the face region. A surface fitting is then determined based on only the pixels that are determined to be part of the face region. Also, described are methods and systems for image normalization wherein the standard deviation and average for the gray levels of the pixels are determined and then used to normalize the image so that the gray level for each of the pixels falls between a particular range.
Inventors
- 👤 Yao-Hong Tsai
- 👤 Yea-Shuan Huang
- 👤 Cheng-Chin Chiang
- 👤 Chun-Wei Hsieh
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 14:14
CPC Classifications
G; G06; G06T; G06T5/00; G06T5/90; G06V; G06V40/00; G06V40/10; G06V40/16; G06V40/168; G06T2207/00; G06T2207/30; G06T2207/30196; G06T2207/30201
Claims Analysis
Total Claims: 27
Claim 1
Independent Claim
103 words
A method for illuminant compensation of an image of a human face, wherein the image includes a plurality of color pixels, comprising: determining a face region based on skin color pixels, wherein the skin color pixels are determined based on intensity and chrominance color of the pixels; determining a surface fitting based on the face region for the image using a linear model, wherein the surface fitting is determined using only the skin color pixels of the face region; generating an illuminant corrected image using the surface fitting and the image; and normalizing the illuminant corrected image to generate an illuminant compensated image.
Claim 2
Independent Claim
103 words
A method for illuminant compensation of an image of a human face, wherein the image includes a plurality of color pixels, comprising: determining a face region based on skin color pixels, wherein the skin color pixels are determined based on intensity and chrominance color of the pixels; determining a surface fitting based on the face region for the image using a linear model, wherein the surface fitting is determined using only the skin color pixels of the face region; generating an illuminant corrected image using the surface fitting and the image; and normalizing the illuminant corrected image to generate an illuminant compensated image.
Claim 3
Dependent Claim
21 words
The method of claim 1 , wherein the illuminant corrected image is generated by subtracting the surface fitting from the image.
Claim 4
Dependent Claim
92 words
The method of claim 1 , wherein the image includes a plurality of pixels each having a gray level, and wherein the step of normalizing the image, comprises the substeps of: computing an average gray level for the plurality of pixels in the image; computing a standard deviation of the gray level for the plurality of pixels in the image; and transforming the gray level for each pixel of the plurality of pixels to a gray level within a predetermined range using the computed average gray level and the computed standard deviation.
Claim 5
Dependent Claim
60 words
The method of claim 3 , wherein in the step of computing the average gray level for the plurality of pixels, only the pixels of the face region are used in computing the average gray level; and wherein in the step of computing the standard deviation, only the pixels of the face region are used in computing the standard deviation.
Claim 6
Dependent Claim
16 words
The method of claim 1 , further comprising: inputting the image from electronic sources in real-time.
Claim 7
Dependent Claim
29 words
The method of claim 1 , further comprising: deciding that the human face in the illuminant compensated image matches one of a plurality of faces stored in a database.
Claim 8
Dependent Claim
28 words
The method of claim 6 , further comprising: outputting the illuminant compensated image and information associated with the matched one of plurality of faces stored in a database.
Claim 9
Dependent Claim
22 words
The method of claim 1 , wherein the linear model is further simplified by a discrete least-square approximation to avoid extensive computations.
Claim 10
Independent Claim
125 words
A system for illuminant compensation of an image of a human face, wherein the image includes a plurality of color pixels, comprising: a memory; and a processor; wherein the memory stores a program that is operative with the processor to perform the following steps: determining a face region based on skin color pixels, wherein the skin color pixels are determined based on intensity and chrominance color of the pixels; determining a surface fitting based on the face region for the image using a linear model, wherein the surface fitting is determined using only the skin color pixels of the face region; generating an illuminant corrected image using the surface fitting and the image; and normalizing the illuminant corrected image to generate an illuminant compensated image.
Claim 11
Independent Claim
125 words
A system for illuminant compensation of an image of a human face, wherein the image includes a plurality of color pixels, comprising: a memory; and a processor; wherein the memory stores a program that is operative with the processor to perform the following steps: determining a face region based on skin color pixels, wherein the skin color pixels are determined based on intensity and chrominance color of the pixels; determining a surface fitting based on the face region for the image using a linear model, wherein the surface fitting is determined using only the skin color pixels of the face region; generating an illuminant corrected image using the surface fitting and the image; and normalizing the illuminant corrected image to generate an illuminant compensated image.
Claim 12
Dependent Claim
30 words
The system of claim 9 , wherein in the step of generating the illuminant corrected image, the illuminant corrected image is generated by subtracting the surface fitting from the image.
Claim 13
Dependent Claim
92 words
The system of claim 9 , wherein the image includes a plurality of pixels each having a gray level, and wherein the step of normalizing the image, comprises the substeps of: computing an average gray level for the plurality of pixels in the image; computing a standard deviation of the gray level for the plurality of pixels in the image; and transforming the gray level for each pixel of the plurality of pixels to a gray level within a predetermined range using the computed average gray level and the computed standard deviation.
Claim 14
Dependent Claim
60 words
The system of claim 11 , wherein in the step of computing the average gray level for the plurality of pixels, only the pixels of the face region are used in computing the average gray level; and wherein in the step of computing the standard deviation, only the pixels of the face region are used in computing the standard deviation.
Claim 15
Dependent Claim
123 words
A computer readable medium storing a program for illuminant compensation of an image of a human face, wherein the image includes a plurality of color pixels and the program is operative with a processor to perform a method comprising the steps of determining a face region based on skin color pixels, wherein the skin color pixels are determined based on intensity and chrominance color of the pixels; determining a surface fitting based on the face region for the image using a linear model, wherein the surface fitting is determined using only the skin color pixels of the face region; generating an illuminant corrected image using the surface fitting and the image; and normalizing the illuminant corrected image to generate an illuminant compensated image.
Claim 16
Dependent Claim
123 words
A computer readable medium storing a program for illuminant compensation of an image of a human face, wherein the image includes a plurality of color pixels and the program is operative with a processor to perform a method comprising the steps of determining a face region based on skin color pixels, wherein the skin color pixels are determined based on intensity and chrominance color of the pixels; determining a surface fitting based on the face region for the image using a linear model, wherein the surface fitting is determined using only the skin color pixels of the face region; generating an illuminant corrected image using the surface fitting and the image; and normalizing the illuminant corrected image to generate an illuminant compensated image.
Claim 17
Dependent Claim
32 words
The computer readable medium of claim 13 , wherein in the step of generating the illuminant corrected image, the illuminant corrected image is generated by subtracting the surface fitting from the image.
Claim 18
Dependent Claim
94 words
The computer readable medium of claim 13 , wherein the image includes a plurality of pixels each having a gray level, and wherein the step of normalizing the image, comprises the substeps of: computing an average gray level for the plurality of pixels in the image; computing a standard deviation of the gray level for the plurality of pixels in the image; and transforming the gray level for each pixel of the plurality of pixels to a gray level within a predetermined range using the computed average gray level and the computed standard deviation.
Claim 19
Dependent Claim
62 words
The computer readable medium of claim 15 , wherein in the step of computing the average gray level for the plurality of pixels, only the pixels of the face region are used in computing the average gray level; and wherein in the step of computing the standard deviation, only the pixels of the face region are used in computing the standard deviation.
Claim 20
Independent Claim
111 words
A system for illuminant compensation of an image of a human face, wherein the image includes a plurality of color pixels, comprising: means for determining a face region based on skin color pixels, wherein the skin color pixels are determined based on intensity and chrominance color of the pixels; means for determining a surface fitting based on the face region for the image using a linear model, wherein the surface fitting is determined using only the skin color pixels of the face region; means for generating an illuminant corrected image using the surface fitting and the image; and means for normalizing the illuminant corrected image to generate an illuminant compensated image.
Claim 21
Independent Claim
111 words
A system for illuminant compensation of an image of a human face, wherein the image includes a plurality of color pixels, comprising: means for determining a face region based on skin color pixels, wherein the skin color pixels are determined based on intensity and chrominance color of the pixels; means for determining a surface fitting based on the face region for the image using a linear model, wherein the surface fitting is determined using only the skin color pixels of the face region; means for generating an illuminant corrected image using the surface fitting and the image; and means for normalizing the illuminant corrected image to generate an illuminant compensated image.
Claim 22
Independent Claim
126 words
A system for determining a surface fitting for an image that includes a plurality of pixels each having a color, and wherein the image includes a face region, comprising: a memory; and a processor; wherein the memory stores a program that is operative with a processor to perform a method comprising the steps of: determining for each pixel whether the pixel's color is within a predetermined set of colors; determining the pixel to be part of the face region if it is determined that the pixel's color is within the predetermined set of colors; and determining a surface fitting for the image using a linear model, wherein the surface fitting is determined using only the pixels that were determined to be part of the face region.
Claim 23
Independent Claim
126 words
A system for determining a surface fitting for an image that includes a plurality of pixels each having a color, and wherein the image includes a face region, comprising: a memory; and a processor; wherein the memory stores a program that is operative with a processor to perform a method comprising the steps of: determining for each pixel whether the pixel's color is within a predetermined set of colors; determining the pixel to be part of the face region if it is determined that the pixel's color is within the predetermined set of colors; and determining a surface fitting for the image using a linear model, wherein the surface fitting is determined using only the pixels that were determined to be part of the face region.
Claim 24
Dependent Claim
118 words
A computer readable medium storing a program that is operative with a processor to perform method for determining a surface fitting for an image that includes a plurality of pixels each having a color, and wherein the image includes a face region, comprising the steps of: determining for each pixel whether the pixel's color is within a predetermined set of colors; determining the pixel to be part of the face region if it is determined that the pixel's color is within the predetermined set of colors; and determining a surface fitting for the image using a linear model, wherein the surface fitting is determined using only the pixels that were determined to be part of the face region.
Claim 25
Dependent Claim
118 words
A computer readable medium storing a program that is operative with a processor to perform method for determining a surface fitting for an image that includes a plurality of pixels each having a color, and wherein the image includes a face region, comprising the steps of: determining for each pixel whether the pixel's color is within a predetermined set of colors; determining the pixel to be part of the face region if it is determined that the pixel's color is within the predetermined set of colors; and determining a surface fitting for the image using a linear model, wherein the surface fitting is determined using only the pixels that were determined to be part of the face region.
Claim 26
Independent Claim
107 words
A system for determining a surface fitting using a linear model for an image that includes a plurality of pixels each having a color, and wherein the image includes a face region, comprising: means for determining for each pixel whether the pixel's color is within a predetermined set of colors; means for determining the pixel to be part of the face region if it is determined that the pixel's color is within the predetermined set of colors; and means for determining a surface fitting for the image, wherein the surface fitting is determined using only the pixels that were determined to be part of the face region.
Claim 27
Independent Claim
107 words
A system for determining a surface fitting using a linear model for an image that includes a plurality of pixels each having a color, and wherein the image includes a face region, comprising: means for determining for each pixel whether the pixel's color is within a predetermined set of colors; means for determining the pixel to be part of the face region if it is determined that the pixel's color is within the predetermined set of colors; and means for determining a surface fitting for the image, wherein the surface fitting is determined using only the pixels that were determined to be part of the face region.
References Cited (Backward Citations)
US4975970A
Cited
US4824246A
Cited
US5089976A
Cited
US5642431A
Cited
US5991456A
Cited
US6148092A
Cited
US6445812B1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2009-03-27 | 2009-09-26 | 2010-03-28 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2013-03-27 | 2013-09-26 | 2014-03-28 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2017-03-27 | 2017-09-26 | 2018-03-28 | $7700.00 | Window Closed / Lapsed |