최소 단어 이상 선택하여야 합니다.
최대 10 단어까지만 선택 가능합니다.
다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
NTIS 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
DataON 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
Edison 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
Kafe 바로가기국가/구분 | United States(US) Patent 등록 |
---|---|
국제특허분류(IPC7판) |
|
출원번호 | US-0038147 (2008-02-27) |
등록번호 | US-8509561 (2013-08-13) |
발명자 / 주소 |
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 | 피인용 횟수 : 1 인용 특허 : 216 |
A technique for determining a characteristic of a face or certain other object within a scene captured in a digital image including acquiring an image and applying a linear texture model that is constructed based on a training data set and that includes a class of objects including a first subset of
A technique for determining a characteristic of a face or certain other object within a scene captured in a digital image including acquiring an image and applying a linear texture model that is constructed based on a training data set and that includes a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations. A fit of the model to the face or certain other object is obtained including adjusting one or more individual values of one or more of the model components of the linear texture model. Based on the obtained fit of the model to the face or certain other object in the scene, a characteristic of the face or certain other object is determined.
1. A method of determining a characteristic of a face or certain other object within a scene captured in a digital image, comprising: (a) acquiring a digital image including a face or certain other object within a scene;(b) applying a linear texture model that is constructed based on a training data
1. A method of determining a characteristic of a face or certain other object within a scene captured in a digital image, comprising: (a) acquiring a digital image including a face or certain other object within a scene;(b) applying a linear texture model that is constructed based on a training data set and that comprises a combination of orthogonal directional and directionally-independent subspaces respectively constructed from a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations;(c) determining an initial location of the face or certain other object in the scene;(d) obtaining a fit of said model to said face or certain other object including adjusting one or more individual values of one or more of the model components of said linear texture model;(e) based on the obtained fit of the model to said face or certain other object in the scene, determining at least one characteristic of the face or certain other object; and(f) electronically storing, transmitting, applying a face or other object recognition program to, editing, or displaying the corrected face image or certain other object including the determined characteristic, or combinations thereof. 2. The method of claim 1, wherein the model components comprise eigenvectors, and the individual values comprises eigenvalues of the eigenvectors. 3. The method of claim 1, wherein the at least one determined characteristic comprises a feature that is independent of directional lighting. 4. The method of claim 1, further comprising generating a reconstructed image without a periodic noise component, including obtaining a second fit of the face or certain other object to a second linear texture model that is based on a training data set and that comprises a class of objects including a set of model components which are without a periodic noise component. 5. The method of claim 4, further comprising: (i) extracting the periodic noise component including determining a difference between the face or certain other object and the reconstructed image, and(ii) determining a frequency of the noise component; and(iii) removing the periodic noise component of the determined frequency. 6. The method of claim 1, further comprising determining an exposure value for the face or certain other object, including obtaining a fit to the face or certain other object to a second linear texture model that is based on a training data set and that comprises a class of objects including a set of model components that exhibit a dependency on exposure value variations. 7. The method of claim 6, further comprising including reducing an effect of a background region or density contrast caused by shadow or both. 8. The method of claim 1, further comprising controlling a flash to accurately reflect a lighting condition, including obtaining a flash control condition by referring to a reference table and controlling a flash light emission according to the flash control condition. 9. The method of claim 8, further comprising reducing an effect of contrasting density caused by shadow or black compression or white compression or combinations thereof. 10. The method of claim 1, further comprising adjusting or determining a sharpness value, or both, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit a dependency on sharpness variations,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, adjusting a sharpness of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 11. The method of claim 1, further comprising removing a blemish from a face or certain other object, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that do not include such a blemish;(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, removing the blemish from the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 12. The method of claim 11, wherein the blemish comprises an acne blemish or other skin blemish. 13. The method of claim 11, wherein the blemish comprises a photographic artefact. 14. The method of claim 1, further comprising adjusting or determining a graininess value, or both, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit a dependency on graininess variations,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, adjusting a graininess of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 15. The method of claim 1, further comprising converting, adjusting or determining a resolution value, or combinations thereof, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit approximately a same resolution as said face or certain other object,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, converting a resolution of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 16. A method of adjusting a characteristic of a face or certain other object within a scene captured in a digital image, comprising: (a) acquiring a digital image including a face or certain other object within a scene;(b) applying a linear texture model that is constructed based on a training data set and comprises a combination of orthogonal directional and directionally-independent subspaces respectively constructed from a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations;(c) determining an initial location of the face or certain other object in the scene;(d) obtaining a fit of said model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said linear texture model; and(e) based on the obtained fit of the model to said face or certain other object in the scene, adjusting at least one characteristic of the face or certain other object including changing one or more values of one or more model components of the linear texture model to generate an adjusted object model;(f) superimposing the adjusted object model onto said digital image; and(g) electronically storing, transmitting, applying a face recognition program to, editing, or displaying the corrected face image, or combinations thereof. 17. The method of claim 16, wherein the model components comprise eigenvectors, and the individual values comprises eigenvalues of the eigenvectors. 18. The method of claim 16, wherein the at least one determined characteristic comprises a feature that is independent of directional lighting. 19. The method of claim 16, further comprising generating a reconstructed image without a periodic noise component, including obtaining a second fit of the face or certain other object to a second linear texture model that is based on a training data set and that comprises a class of objects including a set of model components which are without a periodic noise component. 20. The method of claim 19, further comprising: (i) extracting the periodic noise component including determining a difference between the face or certain other object and the reconstructed image, and(ii) determining a frequency of the noise component; and(iii) removing the periodic noise component of the determined frequency. 21. The method of claim 16, further comprising determining an exposure value for the face or certain other object, including obtaining a fit to the face or certain other object to a second linear texture model that is based on a training data set and that comprises a class of objects including a set of model components that exhibit a dependency on exposure value variations. 22. The method of claim 21, further comprising including reducing an effect of a background region or density contrast caused by shadow or both. 23. The method of claim 16, further comprising controlling a flash to accurately reflect a lighting condition, including obtaining a flash control condition by referring to a reference table and controlling a flash light emission according to the flash control condition. 24. The method of claim 23, further comprising reducing an effect of contrasting density caused by shadow or black compression or white compression or combinations thereof. 25. The method of claim 16, further comprising adjusting or determining a sharpness value, or both, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit a dependency on sharpness variations,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, adjusting a sharpness of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 26. The method of claim 16, further comprising removing a blemish from a face or certain other object, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that do not include such a blemish;(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, removing the blemish from the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 27. The method of claim 26, wherein the blemish comprises an acne blemish or other skin blemish. 28. The method of claim 26, wherein the blemish comprises a photographic artefact. 29. The method of claim 16, further comprising adjusting or determining a graininess value, or both, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit a dependency on graininess variations,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, adjusting a graininess of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 30. The method of claim 16, further comprising converting, adjusting or determining a resolution value, or combinations thereof, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit approximately a same resolution as said face or certain other object,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, converting a resolution of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 31. The method of claim 16, wherein the adjusting comprises changing one or more values of one or more model components of said first subset of model components to a set of mean values, and thereby adjusting directional lighting effects on the scene within the digital image. 32. The method of claim 31, wherein the adjusting of directional lighting effects comprises increasing one or more directional lighting effects. 33. The method of claim 31, wherein the adjusting of directional lighting effect comprises decreasing one or more directional lighting effects. 34. The method of claim 16, wherein the face or certain other object comprises a face, and the adjusting comprises filtering directional light effects to generate a directional light filtered face image, and the method further comprises applying a face recognition program to the filtered face image. 35. A digital image acquisition device including an optoelectonic system for acquiring a digital image, and a digital memory having stored therein processor-readable code for programming the processor to perform a method of determining a characteristic of a face or certain other object within a scene captured in a digital image, wherein the method comprises: (a) acquiring a digital image including a face or certain other object within a scene;(b) applying a linear texture model that is constructed based on a training data set and that comprises a combination of orthogonal directional and directionally-independent subspaces respectively constructed from a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations;(c) determining an initial location of the face or certain other object in the scene;(d) obtaining a fit of said model to said face or certain other object including adjusting one or more individual values of one or more of the model components of said linear texture model;(e) based on the obtained fit of the model to said face or certain other object in the scene, determining at least one characteristic of the face or certain other object; and(f) electronically storing, transmitting, applying a face or other object recognition program to, editing, or displaying the corrected face image or certain other object including the determined characteristic, or combinations thereof. 36. The device of claim 35, wherein the model components comprise eigenvectors, and the individual values comprises eigenvalues of the eigenvectors. 37. The device of claim 35, wherein the at least one determined characteristic comprises a feature that is independent of directional lighting. 38. The device of claim 35, wherein the method further comprises generating a reconstructed image without a periodic noise component, including obtaining a second fit of the face or certain other object to a second linear texture model that is based on a training data set and that comprises a class of objects including a set of model components which are without a periodic noise component. 39. The device of claim 38, wherein the method further comprises: (i) extracting the periodic noise component including determining a difference between the face or certain other object and the reconstructed image, and(ii) determining a frequency of the noise component; and(iii) removing the periodic noise component of the determined frequency. 40. The device of claim 35, wherein the method further comprises determining an exposure value for the face or certain other object, including obtaining a fit to the face or certain other object to a second linear texture model that is based on a training data set and that comprises a class of objects including a set of model components that exhibit a dependency on exposure value variations. 41. The device of claim 40, wherein the method further comprises including reducing an effect of a background region or density contrast caused by shadow or both. 42. The device of claim 35, wherein the method further comprises controlling a flash to accurately reflect a lighting condition, including obtaining a flash control condition by referring to a reference table and controlling a flash light emission according to the flash control condition. 43. The device of claim 42, wherein the method further comprises reducing an effect of contrasting density caused by shadow or black compression or white compression or combinations thereof. 44. The device of claim 35, wherein the method further comprises adjusting or determining a sharpness value, or both, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit a dependency on sharpness variations,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, adjusting a sharpness of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 45. The device of claim 35, wherein the method further comprises removing a blemish from a face or certain other object, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that do not include such a blemish;(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, removing the blemish from the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 46. The device of claim 45, wherein the blemish comprises an acne blemish or other skin blemish. 47. The device of claim 45, wherein the blemish comprises a photographic artefact. 48. The device of claim 35, wherein the method further comprises adjusting or determining a graininess value, or both, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit a dependency on graininess variations,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, adjusting a graininess of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 49. The device of claim 35, wherein the method further comprises converting, adjusting or determining a resolution value, or combinations thereof, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit approximately a same resolution as said face or certain other object,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, converting a resolution of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 50. A digital image acquisition device including an optoelectonic system for acquiring a digital image, and a digital memory having stored therein processor-readable code for programming the processor to perform a method of adjusting a characteristic of a face or certain other object within a scene captured in a digital image, wherein the method comprises: (a) acquiring a digital image including a face or certain other object within a scene;(b) applying a linear texture model that is constructed based on a training data set and comprises a combination of orthogonal directional and directionally-independent subspaces respectively constructed from a class of objects including a first subset of model components that exhibit a dependency on directional lighting variations and a second subset of model components which are independent of directional lighting variations;(c) determining an initial location of the face or certain other object in the scene;(d) obtaining a fit of said model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said linear texture model; and(e) based on the obtained fit of the model to said face or certain other object in the scene, adjusting at least one characteristic of the face or certain other object including changing one or more values of one or more model components of the linear texture model to generate an adjusted object model;(f) superimposing the adjusted object model onto said digital image; and(g) electronically storing, transmitting, applying a face recognition program to, editing, or displaying the corrected face image, or combinations thereof. 51. The device of claim 50, wherein the model components comprise eigenvectors, and the individual values comprises eigenvalues of the eigenvectors. 52. The device of claim 50, wherein the at least one determined characteristic comprises a feature that is independent of directional lighting. 53. The device of claim 50, wherein the method further comprises generating a reconstructed image without a periodic noise component, including obtaining a second fit of the face or certain other object to a second linear texture model that is based on a training data set and that comprises a class of objects including a set of model components which are without a periodic noise component. 54. The device of claim 53, wherein the method further comprises: (i) extracting the periodic noise component including determining a difference between the face or certain other object and the reconstructed image, and(ii) determining a frequency of the noise component; and(iii) removing the periodic noise component of the determined frequency. 55. The device of claim 50, wherein the method further comprises determining an exposure value for the face or certain other object, including obtaining a fit to the face or certain other object to a second linear texture model that is based on a training data set and that comprises a class of objects including a set of model components that exhibit a dependency on exposure value variations. 56. The device of claim 55, wherein the method further comprises including reducing an effect of a background region or density contrast caused by shadow or both. 57. The device of claim 50, wherein the method further comprises controlling a flash to accurately reflect a lighting condition, including obtaining a flash control condition by referring to a reference table and controlling a flash light emission according to the flash control condition. 58. The device of claim 57, wherein the method further comprises reducing an effect of contrasting density caused by shadow or black compression or white compression or combinations thereof. 59. The device of claim 50, wherein the method further comprises adjusting or determining a sharpness value, or both, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit a dependency on sharpness variations,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, adjusting a sharpness of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 60. The device of claim 50, wherein the method further comprises removing a blemish from a face or certain other object, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that do not include such a blemish;(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, removing the blemish from the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 61. The device of claim 60, wherein the blemish comprises an acne blemish or other skin blemish. 62. The device of claim 60, wherein the blemish comprises a photographic artefact. 63. The device of claim 50, wherein the method further comprises adjusting or determining a graininess value, or both, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit a dependency on graininess variations,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, adjusting a graininess of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 64. The device of claim 50, wherein the method further comprises converting, adjusting or determining a resolution value, or combinations thereof, including: (i) applying a second linear texture model that is constructed based on a training data set and comprises a class of objects including a subset of model components that exhibit approximately a same resolution as said face or certain other object,(ii) obtaining a fit of said second model to said face or certain other object in the scene including adjusting one or more individual values of one or more model components of said second linear texture model; and(e) based on the obtained fit of the second model to said face or certain other object in the scene, converting a resolution of the face or certain other object including changing one or more values of one or more model components of the second linear texture model to generate a further adjusted object model. 65. The device of claim 50, wherein the adjusting comprises changing one or more values of one or more model components of said first subset of model components to a set of mean values, and thereby adjusting directional lighting effects on the scene within the digital image. 66. The device of claim 65, wherein the adjusting of directional lighting effects comprises increasing one or more directional lighting effects. 67. The device of claim 65, wherein the adjusting of directional lighting effect comprises decreasing one or more directional lighting effects. 68. The device of claim 50, wherein the face or certain other object comprises a face, and the adjusting comprises filtering directional light effects to generate a directional light filtered face image, and the method further comprises applying a face recognition program to the filtered face image.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.