JP2001167273A5 - - Google Patents
Download PDFInfo
- Publication number
- JP2001167273A5 JP2001167273A5 JP1999349498A JP34949899A JP2001167273A5 JP 2001167273 A5 JP2001167273 A5 JP 2001167273A5 JP 1999349498 A JP1999349498 A JP 1999349498A JP 34949899 A JP34949899 A JP 34949899A JP 2001167273 A5 JP2001167273 A5 JP 2001167273A5
- Authority
- JP
- Japan
- Prior art keywords
- image
- color
- face detection
- detection method
- pixels
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 claims 44
- 210000003491 Skin Anatomy 0.000 claims 26
- 230000001815 facial Effects 0.000 claims 12
- 230000000875 corresponding Effects 0.000 claims 5
- 238000005286 illumination Methods 0.000 claims 5
- 238000004590 computer program Methods 0.000 claims 4
- 238000005070 sampling Methods 0.000 claims 4
Claims (49)
前記画像を各々がほぼ同色を有する複数の領域に分割する分割工程と、
前記分割工程で生成された前記領域の各々の色を試験して、主に肌色を有する領域を判定する判定工程と、
前記判定工程で主に肌色を持つと決定された画素に基づいて、顔面特徴解析を実行する解析工程と
を備えることを特徴とする顔面検出方法。A face detection method for detecting a face in a color digital image,
A dividing step of dividing the image into a plurality of regions each having substantially the same color;
A determination step of testing each color of the region generated in the dividing step and determining a region mainly having skin color;
A facial detection method comprising: an analysis step of performing facial feature analysis based on pixels determined to have skin color mainly in the determination step.
ことを特徴とする請求項１に記載の顔面検出方法。The face detection method according to claim 1, wherein the determination step uses a color distribution model .
ことを特徴とする請求項１に記載の顔面検出方法。The face detection method according to claim 1, further comprising: using a chromatic color extracted from an RGB value in the determination step.
ことを特徴とする請求項１に記載の顔面検出方法。The face detection method according to claim 1, wherein the image is obtained from a camera.
ことを特徴とする請求項４に記載の顔面検出方法。The face detection method according to claim 4, wherein the image is selected from an image group including an image captured using a flash and an image captured without using a flash.
ことを特徴とする請求項１に記載の顔面検出方法。The face detection method according to claim 1, wherein the facial feature analysis in the analysis step is independent of a face color.
前記画像を各々がほぼ同色を有する複数の領域に分割する分割手段と、
前記分割手段に接続され、該分割手段で生成された前記領域の各々の色を試験して、主に肌色を有する領域を判定する判定手段と、
前記判定手段に接続され、前記判定手段で主に肌色を持つと決定された画素に基づいて、顔面特徴解析を実行する解析手段と
を備えることを特徴とする顔面検出装置。A face detection device for detecting a face in a color digital image,
Dividing means for dividing the image into a plurality of regions each having substantially the same color;
A determination unit connected to the dividing unit and testing each color of the region generated by the dividing unit to determine a region mainly having skin color;
An apparatus for analyzing a face, comprising: analyzing means for performing facial feature analysis based on pixels determined to have skin color mainly by the determining means, connected to the determining means .
ことを特徴とする請求項７に記載の顔面検出装置。The face detection apparatus according to claim 7 , wherein the determination unit uses a color distribution model .
ことを特徴とする請求項７に記載の顔面検出装置。The face detection apparatus according to claim 7 , wherein the image is obtained from a camera.
ことを特徴とする請求項７に記載の顔面検出装置。The face detection device according to claim 7 , wherein the image is selected from an image group including an image captured using a flash and an image captured without using a flash.
前記画像を各々がほぼ同色を有する複数の領域に分割する分割工程と、
前記分割工程で生成された前記領域の各々の色を試験して、主に肌色を有する領域を判定する判定工程と、
前記判定工程で主に肌色を持つと決定された画素に基づいて、顔面特徴解析を実行する解析工程と
を実行するコンピュータ実行可能な命令シーケンスを備える
ことを特徴とするコンピュータ可読媒体。A computer readable medium storing a computer program product for detecting a face in a color digital image, the computer program comprising:
A dividing step of dividing the image into a plurality of regions each having substantially the same color;
A determination step of testing each color of the region generated in the dividing step and determining a region mainly having skin color;
A computer-readable medium comprising: a computer-executable instruction sequence for performing an analysis step for performing facial feature analysis based on pixels determined to have skin color mainly in the determination step.
ことを特徴とする請求項１１に記載のコンピュータ可読媒体。The computer-readable medium according to claim 11 , wherein the determination step uses a color distribution model.
ことを特徴とする請求項１１に記載のコンピュータ可読媒体。The computer-readable medium of claim 11 , wherein the image is obtained from a camera.
ことを特徴とする請求項１１に記載のコンピュータ可読媒体。The computer-readable medium of claim 11 , wherein the image is selected from a group of images including an image captured using a flash and an image captured without using a flash.
前記画像から得られる少なくとも１つの画像撮影条件を利用して前記画素の色の試験を行い、該画素から主に肌色を有する画素を判定する判定工程と、
前記判定工程で主に肌色を持つと決定された画素に基づいて、顔面特徴解析を実行する解析工程と
を備えることを特徴とする顔面検出方法。A face detection method for detecting a face in a color digital image formed from a plurality of pixels,
A determination step of performing a color test of the pixel using at least one image capturing condition obtained from the image, and determining a pixel mainly having skin color from the pixel;
A facial detection method comprising: an analysis step of performing facial feature analysis based on pixels determined to have skin color mainly in the determination step.
ことを特徴とする請求項１５に記載の顔面検出方法。The face detection method according to claim 15 , wherein the image capturing condition is acquired when the image is captured.
ことを特徴とする請求項１５に記載の顔面検出方法。The face detection method according to claim 15 , wherein the at least one image capturing condition includes an illumination condition at the time of capturing the image.
前記画像を各々複数の前記画素を有する領域に分割する分割工程とを備え、
前記試験は、主に肌色である領域の１つを判定するために、前記領域各々内の画素に対し実行される
ことを特徴とする請求項１５に記載の顔面検出方法。The determination step is performed before the test.
Dividing the image into regions each having a plurality of the pixels,
The test is primarily to determine one of the regions is skin color, face detection method according to claim 15, characterized in that it is performed on the pixels in said each region.
ことを特徴とする請求項１５に記載の顔面検出方法。The face detection method according to claim 15 , wherein the determination step uses a color distribution model.
ことを特徴する請求項２０に記載の顔面検出方法。The face detection method according to claim 20 , wherein the color distribution model is generated for a specific image capturing device.
ことを特徴とする請求項２０に記載の顔面検出方法。The face detection method according to claim 20 , wherein the color distribution model is generated for different image capturing conditions.
ことを特徴とする請求項２２に記載の顔面検出方法。The at least one image capturing condition includes an illumination condition at the time of capturing the image, and the color distribution model is generated for different illumination conditions at the time of capturing the previously sampled facial image data. The face detection method according to claim 22 , wherein
ことを特徴とする請求項２３に記載の顔面検出方法。The face detection method according to claim 23 , wherein the color distribution model is generated for an image group photographed using a flash and an image group photographed without using a flash.
ことを特徴とする請求項２３に記載の顔面検出方法。The face detection method according to claim 23 , wherein the color and color distribution model is generated for an image group photographed indoors and an image group photographed outdoors.
ことを特徴とする請求項２０に記載の顔面検出方法。The face detection method according to claim 20 , wherein each of the color distribution models is expressed as a frequency histogram of a color expression vector.
ことを特徴とする請求項２０に記載の顔面検出方法。The face detection method according to claim 20 , wherein each of the color distribution models is expressed as a probability distribution of a color expression vector.
ことを特徴とする請求項２０に記載の顔面検出方法。21. The face detection method according to claim 20 , wherein each of the color distribution models is expressed as a binary map of color expression vectors.
ことを特徴とする請求項２６乃至請求項２８のいずれか１項に記載の顔面検出方法。The face detection according to any one of claims 26 to 28 , wherein the color expression vector is extracted from a perceptual color space of the predetermined skin color pixel in the previously sampled face image data. Method.
ことを特徴とする請求項２６乃至請求項２８のいずれか１項に記載の顔面検出方法。The color representation vectors to any one of claims 26 to 28, characterized in that it comprises a chromatic value which is extracted from the RGB values of the predetermined skin color pixel in the face image data sampled on the destination The face detection method described.
ことを特徴とする請求項２８に記載の顔面検出方法。The face detection method according to claim 28 , wherein the binary map has a ratio of skin color pixels identified in the previously sampled image data.
ことを特徴とする請求項３１に記載の顔面検出方法。The face detection method according to claim 31 , wherein one of the pixels is classified as a skin color when the color expression vector corresponding to the pixel is generated in the binary map.
ことを特徴とする請求項２６に記載の顔面検出方法。27. The face detection method according to claim 26 , wherein each of the pixels is classified as a skin color when the frequency of the color expression vector corresponding to each of the pixels exceeds a predetermined threshold frequency.
ことを特徴とする請求項２７に記載の顔面検出方法。28. The face detection method according to claim 27 , wherein each of the pixels is classified as a skin color when the probability of the color expression vector corresponding to each of the pixels exceeds a predetermined probability threshold.
ことを特徴とする請求項３２に記載の顔面検出方法。The face detection method according to claim 32 , wherein the area is mainly determined to be a skin color when a predetermined ratio or more of the total number of the pixels in the area is classified as a skin color.
ことを特徴とする請求項１６に記載の顔面検出方法。The face detection method according to claim 16 , wherein the image capturing condition is expressed as metadata .
前記画像から得られる少なくとも１つの画像撮影条件を利用して前記画素の色の試験を行い、該画素から主に肌色を有する画素を判定する判定手段と、
前記判定手段で前記判定工程で主に肌色を持つと決定された画素に基づいて、顔面特徴解析を実行する解析手段と
を備えることを特徴とする顔面検出装置。A face detection device for detecting a face in a color digital image formed from a plurality of pixels,
A determination unit that performs a color test of the pixel using at least one image capturing condition obtained from the image, and determines a pixel mainly having skin color from the pixel;
Analyzing means for executing facial feature analysis based on pixels determined to have skin color mainly in the judging step by the judging means .
ことを特徴とする請求項３７に記載の顔面検出装置。The face detection apparatus according to claim 37 , wherein the image capturing condition is acquired when the image is captured.
有する
ことを特徴とする請求項３７に記載の顔面検出装置。The face detection device according to claim 37 , wherein the at least one image capturing condition includes an illumination condition at the time of capturing the image.
前記画像を各々複数の前記画素を有する領域に分割する分割手段とを備え、
前記試験は、主に肌色である領域の１つを判定するために、前記試験を、前記領域各々内の画素に対して実行される
ことを特徴とする請求項３７に記載の顔面検出装置。The determination means, before the test,
Dividing means for dividing the image into regions each having a plurality of the pixels,
The test is primarily to determine one of the regions is skin color, face detection device of claim 37, the test, characterized in that it is performed for the pixels in said each region.
前記画像から得られる少なくとも１つの画像撮影条件を利用して前記画素の色の試験を行い、該画素から主に肌色を有する画素を判定する判定手段と、
前記判定手段で前記判定工程で主に肌色を持つと決定された画素に基づいて、顔面特徴解析を実行する解析手段と
を備えることを特徴とするコンピュータ可読媒体。A computer readable medium storing a computer program product for detecting a face in a color digital image formed from a plurality of pixels, the computer program product comprising:
A determination unit that performs a color test of the pixel using at least one image capturing condition obtained from the image, and determines a pixel mainly having skin color from the pixel;
A computer-readable medium comprising: analysis means for performing facial feature analysis based on pixels determined to have skin color mainly in the determination step by the determination means .
ことを特徴とする請求項４２に記載のコンピュータ可読媒体。The computer-readable medium according to claim 42 , wherein the image capturing condition is acquired when the image is captured.
ことを特徴とする請求項４２に記載のコンピュータ可読媒体。The computer-readable medium according to claim 42 , wherein the at least one image capturing condition includes an illumination condition at the time of capturing the image.
ことを特徴とする請求項４３に記載のコンピュータ可読媒体。44. The computer-readable medium of claim 43 , wherein the image capturing condition is expressed as metadata .
ことを特徴とする請求項３８に記載の顔面検出装置。The face detection apparatus according to claim 38, wherein
主に肌色を有する画素を決定するために複数の画素の色を判定する判定工程と、A determination step of determining a color of a plurality of pixels in order to mainly determine pixels having skin color;
前記判定工程で主に肌色をもつと決定された画素に基づいて、顔面特徴解析を実行する解析工程とを備え、An analysis step for performing facial feature analysis based on the pixels determined to have skin color mainly in the determination step,
前記判定工程は、前記カラーデジタル画像に対応する少なくとも１つの画像撮影条件に依存する少なくとも１つのしきい値を使用し、前記画像撮影条件はメタデータとして表現されるThe determination step uses at least one threshold value depending on at least one image capturing condition corresponding to the color digital image, and the image capturing condition is expressed as metadata.
ことを特徴とする顔面検出方法。A face detection method characterized by the above.
主に肌色を有する画素を決定するために複数の画素の色を判定する判定手段と、Determination means for determining a color of a plurality of pixels in order to determine a pixel mainly having skin color;
前記判定手段で主に肌色をもつと決定された画素に基づいて、顔面特徴解析を実行する解析手段とを備え、Analysis means for performing facial feature analysis based on pixels determined to have skin color mainly by the determination means,
前記判定手段は、前記カラーデジタル画像に対応する少なくとも１つの画像撮影条件に依存する少なくとも１つのしきい値を使用し、前記画像撮影条件はメタデータとして表現されるThe determination unit uses at least one threshold value depending on at least one image capturing condition corresponding to the color digital image, and the image capturing condition is expressed as metadata.
ことを特徴とする顔面検出装置。A face detection apparatus characterized by that.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP34949899A JP3962517B2 (en) | 1999-12-08 | 1999-12-08 | Face detection method and apparatus, and computer-readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP34949899A JP3962517B2 (en) | 1999-12-08 | 1999-12-08 | Face detection method and apparatus, and computer-readable medium |
Publications (3)
| Publication Number | Publication Date |
|---|---|
| JP2001167273A JP2001167273A (en) | 2001-06-22 |
| JP2001167273A5 true JP2001167273A5 (en) | 2005-07-28 |
| JP3962517B2 JP3962517B2 (en) | 2007-08-22 |
Family
ID=18404162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP34949899A Expired - Fee Related JP3962517B2 (en) | 1999-12-08 | 1999-12-08 | Face detection method and apparatus, and computer-readable medium |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP3962517B2 (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2395781A (en) * | 2002-11-29 | 2004-06-02 | Sony Uk Ltd | Face detection |
| JP4645223B2 (en) * | 2005-02-18 | 2011-03-09 | 富士通株式会社 | Face tracking program and face tracking method |
| JP4782600B2 (en) * | 2006-03-30 | 2011-09-28 | 富士フイルム株式会社 | Face detection method and photographing apparatus using the same |
| JP4321645B2 (en) | 2006-12-08 | 2009-08-26 | ソニー株式会社 | Information processing apparatus, information processing method, recognition apparatus, information recognition method, and program |
| JP4375448B2 (en) | 2007-06-26 | 2009-12-02 | ソニー株式会社 | Image processing apparatus, imaging apparatus, image processing method, and program |
| JP5219706B2 (en) * | 2008-09-12 | 2013-06-26 | キヤノン株式会社 | Image processing apparatus, image processing method, and image processing program |
| KR101398968B1 (en) | 2014-03-04 | 2014-06-27 | 엘아이지넥스원 주식회사 | Method for testing efficiency of Infra-Red detector |
| CN114468973B (en) * | 2022-01-21 | 2023-08-11 | 广州视域光学科技股份有限公司 | Intelligent vision detection system |
-
1999
- 1999-12-08 JP JP34949899A patent/JP3962517B2/en not_active Expired - Fee Related
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2000003452A5 (en) | ||
| WO2017092431A1 (en) | Human hand detection method and device based on skin colour | |
| CN102915372B (en) | Image search method, Apparatus and system | |
| CN108174185B (en) | Photographing method, device and terminal | |
| WO2019033572A1 (en) | Method for detecting whether face is blocked, device and storage medium | |
| US20080175481A1 (en) | Color Segmentation | |
| JP2017520050A5 (en) | ||
| CN106845396B (en) | Illegal fishing behavior identification method based on automatic image identification | |
| KR20120035734A (en) | A method for detecting fire or smoke | |
| JP2010211498A (en) | Image processing program and image processing system | |
| JP2004310475A (en) | Image processor, cellular phone for performing image processing, and image processing program | |
| CN111723656B (en) | Smog detection method and device based on YOLO v3 and self-optimization | |
| CN111582045B (en) | Living body detection method and device and electronic equipment | |
| CN102088539A (en) | Method and system for evaluating pre-shot picture quality | |
| KR102503872B1 (en) | Information processing device, information processing method, and program | |
| US20110158511A1 (en) | Method and apparatus for filtering red and/or golden eye artifacts | |
| JP2001167273A5 (en) | ||
| CN111709305A (en) | Face age identification method based on local image block | |
| CN114066823A (en) | Method for detecting color block and related product thereof | |
| CN113221763A (en) | Flame identification method based on video image brightness | |
| KR20130111021A (en) | Device and method for processing image | |
| KR102444544B1 (en) | Method for image pre-processing and apparatus for the same | |
| CN111797694A (en) | License plate detection method and device | |
| JP2004030225A (en) | White smoke detection method and apparatus | |
| CN112883762A (en) | Living body detection method, device, system and storage medium |