DETECTING EXPOSURE QUALITY IN IMAGES

• US 20140153827A1
• Filed: 11/30/2012
• Published: 06/05/2014
• Est. Priority Date: 11/30/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Krishnaswamy, Aravind
• Granted Patent: US 8,873,850 B2
• Time in Patent Office: Days
• US Class Current: 382/170
• CPC Class Codes: G06T 2207/20012 Locally adaptive
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• CPC Class Codes: G06T 5/40 using histogram techniques
• CPC Class Codes: G06T 5/90 Dynamic range modification of images or parts thereof
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation

Abstract

Systems, methods and computer readable media for exposure quality detection are described. In some implementations, a method can include computing an overall image exposure score for an image. The method can also include determining one or more face regions in the image. The method can further include computing a face region exposure score for each face region. The method can also include combining the overall image exposure score and each face region exposure score to generate an exposure quality score for the image.

Claims

1. A method comprising:

computing an overall image exposure score for an image, the overall exposure score being based on a clipped pixel score and a tonal distribution score;

determining one or more face regions in the image;

computing a face region exposure score for each face region, the face region exposure score including a clipped pixel score and a face region tonal distribution score;

adjusting the overall image exposure score and each face region exposure score according to a penalty value;

combining the overall image exposure score and each face region exposure score to generate an exposure quality score for the image; and

applying one or more of an overall exposure correction and an independent correction for each face region.

2. A method comprising:

computing an overall image exposure score for an image;

determining one or more face regions in the image;

computing a face region exposure score for each face region; and

combining the overall image exposure score and each face region exposure score to generate an exposure quality score for the image.

3. The method of claim 2, wherein the overall image exposure score includes a clipped pixel score and a tonal distribution score based on a histogram of the image.

4. The method of claim 2, wherein each face region exposure score includes a clipped pixel score and a face region tonal distribution score based on a histogram of the image.

5. The method of claim 4, wherein the face region tonal distribution score includes a determination of a distance of each of a median histogram value and a mean histogram value from a predetermined histogram section.

6. The method of claim 2, wherein the clipped pixel score is computed for each color channel of a plurality of color channels.

7. The method of claim 6, further comprising adjusting the overall image exposure score according to a penalty value when a zone value for each color channel exceeds a predetermined threshold and adjusting each face region exposure score according to the penalty value when a zone value for each color channel exceeds a predetermined threshold.

8. The method of claim 2, further comprising applying one or more of an overall exposure correction and an independent correction for each face region.

9. The method of claim 2, further comprising automatically curating the image based on the exposure quality score for the image.

10. A system comprising one or more computers configured to perform operations including:

computing an overall image exposure score for an image;

determining one or more face regions in the image;

computing a face region exposure score for each face region; and

combining the overall image exposure score and each face region exposure score to generate an exposure quality score for the image.

11. The system of claim 10, wherein the overall image exposure score includes a clipped pixel score and a tonal distribution score based on a histogram of the image.

12. The system of claim 10, wherein each face region exposure score includes a clipped pixel score and a face region tonal distribution score based on a histogram of the image.

13. The system of claim 12, wherein the face region tonal distribution score includes a determination of a distance of each of a median histogram value and a mean histogram value from a predetermined histogram section.

14. The system of claim 10, wherein the clipped pixel score is computed for each color channel of a plurality of color channels.

15. The system of claim 14, further comprising adjusting the overall image exposure score according to a penalty value when a zone value for each color channel exceeds a predetermined threshold and adjusting each face region exposure score according to the penalty value when a zone value for each color channel exceeds a predetermined threshold.

16. The system of claim 10, further comprising applying one or more of an overall exposure correction and an independent correction for each face region.

17. The system of claim 10, further comprising automatically curating the image based on the exposure quality score for the image.