Image quality estimation using a reference image portion
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06K-009/00
G06K-009/46
G06K-009/40
G06K-009/54
G06F-007/00
G06K-009/62
G06T-007/00
출원번호
US-0277329
(2014-05-14)
등록번호
US-10026010
(2018-07-17)
발명자
/ 주소
Reibman, Amy Ruth
Liu, Zhu
Begeja, Lee
Renger, Bernard S.
Gibbon, David Crawford
Shahraray, Behzad
Gopalan, Raghuraman
Zavesky, Eric
출원인 / 주소
AT&T INTELLECTUAL PROPERTY I, L.P.
대리인 / 주소
Toler Law Group, PC
인용정보
피인용 횟수 :
0인용 특허 :
23
초록▼
A particular method includes receiving a set of images, where each image of the set of images is related to a common scene. The method also includes determining a first subset of pixels of a first image of the set, where the first subset of pixels corresponds to a second subset of pixels of a second
A particular method includes receiving a set of images, where each image of the set of images is related to a common scene. The method also includes determining a first subset of pixels of a first image of the set, where the first subset of pixels corresponds to a second subset of pixels of a second image of the set. The method further includes generating a first image quality estimate of the first image based on a comparison of the first subset of pixels and the second subset of pixels.
대표청구항▼
1. A method comprising: receiving, by a device comprising a processor, a first image of a scene;receiving, at the device, a second image of at least a portion of the scene;determining, by the device, a first subset of pixels of the first image, the first subset of pixels representing a particular fe
1. A method comprising: receiving, by a device comprising a processor, a first image of a scene;receiving, at the device, a second image of at least a portion of the scene;determining, by the device, a first subset of pixels of the first image, the first subset of pixels representing a particular feature of the scene, wherein the determining the first subset of pixels includes identifying a first plurality of features from the first image;determining, by the device, a second subset of pixels of the second image, the second subset of pixels representing the particular feature of the scene, wherein the determining the second subset of pixels includes:identifying a second plurality of features from the second image, wherein the second plurality of features includes the particular feature;comparing the first plurality of features to the second plurality of features to identify a subset of common features, wherein the subset of common features includes the particular feature; anddetermining a particular subset of pixels that correspond to the particular feature in the second image based on the subset of common features, wherein the particular subset of pixels is the second subset of pixels; andgenerating, by the device, a first image quality estimate of the first image based on a comparison of a first degree of variation within the first subset of pixels and a second degree of variation within the second subset of pixels. 2. The method of claim 1, wherein the second subset of pixels are determined independent of a grid location of the first subset of pixels. 3. The method of claim 1, wherein the first degree of variation corresponds to first variation of color intensity of the first subset of pixels, and wherein the second degree of variation corresponds to a second variation of color intensity of the second subset of pixels. 4. The method of claim 1, wherein the first degree of variation corresponds to coloration of the first subset of pixels, and wherein the second degree of variation corresponds to coloration of the second subset of pixels. 5. The method of claim 1, further comprising: receiving a third image of at least a portion of the scene;generating a third quality image estimate of the third image based on a comparison of a third degree of variation within a third subset of pixels of the third image and the second degree of variation within the second subset of pixels, wherein the third subset of pixels corresponds to the particular feature; andperforming a comparison of the first image quality estimate to the third quality image estimate. 6. The method of claim 5, further comprising designating the first image or the third image as a preferred image based on the comparison of the first image quality estimate to the third quality image estimate. 7. The method of claim 5, further comprising determining that the first image quality estimate and the third image quality estimate satisfy an image quality threshold. 8. The method of claim 1, wherein the device comprises a camera, and wherein the first image is captured by the camera. 9. The method of claim 1, wherein the first image depicts the particular feature from a first angle, and wherein the second image depicts the particular feature from a second angle distinct from the first angle. 10. The method of claim 1, wherein the first degree of variation corresponds to spatial frequency of the first subset of pixels, and wherein the second degree of variation corresponds to spatial frequency of the second subset of pixels. 11. The method of claim 1, wherein the first image has a different resolution than the second image. 12. The method of claim 1, wherein the first image and the second image are captured by different devices. 13. The method of claim 1, wherein the first image has a different color space than the second image. 14. The method of claim 1, further comprising: comparing the first image quality estimate to a threshold; andgenerating an indication that the first image has an acceptable image quality based on the first image quality estimate satisfying the threshold. 15. An apparatus comprising: a processor; anda memory storing instructions executable by the processor to perform operations comprising: receiving a first image of a scene;receiving a second image of at least a portion of the scene;determining a first subset of pixels of the first image, the first subset of pixels representing a particular feature of the scene, wherein the determining the first subset of pixels includes identifying a first plurality of features from the first image;determining a second subset of pixels of the second image, the second subset of pixels representing the particular feature of the scene, wherein the determining the second subset of pixels includes:identifying a second plurality of features from the second image, wherein the second plurality of features includes the particular feature;comparing the first plurality of features to the second plurality of features to identify a subset of common features, wherein the subset of common features includes the particular feature; anddetermining a particular subset of pixels that correspond to the particular feature in the second image based on the subset of common features, wherein the particular subset of pixels is the second subset of pixels; andgenerating a first image quality estimate of the first image based on a comparison of a first degree of variation within the first subset of pixels and a second degree of variation within the second subset of pixels. 16. The apparatus of claim 15, wherein the operations further comprise: receiving a third image of at least a portion of the scene; andgenerating a third quality image estimate of the third image based on a second comparison of a third subset of pixels of the third image and the second subset of pixels, wherein the third subset of pixels corresponds to the particular feature. 17. The apparatus of claim 16, wherein the operations further comprise: performing a third comparison of the first image quality estimate to the third quality image estimate; anddesignating the first image or the third image as a preferred image based on the third comparison. 18. A computer-readable storage device storing instructions that, when executed by a computer, cause the computer to perform operations comprising: receiving a first image of a scene;receiving a second image of at least a portion of the scene;determining a first subset of pixels of the first image, the first subset of pixels representing a particular feature of the scene, wherein the determining the first subset of pixels includes identifying a first plurality of features from the first image;determining a second subset of pixels of the second image, the second subset of pixels representing the particular feature of the scene, wherein the determining the second subset of pixels includes: identifying a second plurality of features from the second image, wherein the second plurality of features includes the particular feature;comparing the first plurality of features to the second plurality of features to identify a subset of common features, wherein the subset of common features includes the particular feature; anddetermining a particular subset of pixels that correspond to the particular feature in the second image based on the subset of common features, wherein the particular subset of pixels is the second subset of pixels; andgenerating a first image quality estimate of the first image based on a comparison of a first degree of variation within the first subset of pixels and a second degree of variation within the second subset of pixels. 19. The computer-readable storage device of claim 18, wherein the first degree of variation corresponds to contrast associated with the first subset of pixels, and wherein the second degree of variation corresponds to contrast associated with the second subset of pixels. 20. The computer-readable storage device of claim 18, wherein the operations further comprise: receiving a third image of at least a portion of the scene;generating a third quality image estimate of the third image based on a second comparison of a third subset of pixels of the third image and the second subset of pixels;performing a third comparison of the first image quality estimate to the third quality image estimate; anddesignating the first image or the third image as a preferred image based on the third comparison.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (23)
Karasikov, Nir; Sela, Jona; Dubin, Uri; Goshen, Gal, Advanced digital pathology and provisions for remote diagnostics.
Covell, Michele M.; Ahmad, Subutai; Shiffer, Katerina L., Automatic selection of a visual image or images from a collection of visual images, based on an evaluation of the quality of the visual images.
Jabri,Kadri N.; Stevens,Grant M.; Battle,Vianney P.; Yao,Jianqing; Uppaluri,Renuka; Hobert,Kevin J., System and method for efficiently customizing an imaging system.
Hull,Jonathan J.; Baxter,Michael; Gage,Pamela; Graham,Jamey; Lee,Dar Shyang; Hart,Peter E., Techniques for capturing information during multimedia presentations.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.