IMAGING WORKFLOW USING FACIAL AND NON-FACIAL FEATURES

• US 20150049910A1
• Filed: 08/12/2014
• Published: 02/19/2015
• Est. Priority Date: 08/19/2013
• Status: Active Grant

• Current Assignee: Kodak Alaris Inc (KPP (no. 2) Trustees Ltd.)
• Original Assignee: Kodak Alaris Inc (KPP (no. 2) Trustees Ltd.)
• Inventors: Ptucha, Raymond William, Loui, Alexander C., Wood, Mark D., Rhoda, David K., Manico, Joseph Anthony, Kloosterman, David
• Granted Patent: US 9,552,374 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships

Abstract

A method for determining an impact score for a digital image includes providing the digital image wherein the digital image includes faces; using a processor to determine an image feature for the faces; using the processor to compute an object impact score for the faces, wherein the object impact score is based at least upon one of the determined image features; weighting the object impact score for the faces based on one of the determined image features for a face; using the processor to compute an impact score for the digital image by combining the weighted object impact scores for the faces in the image; and storing the computed impact score in a processor accessible memory.

Claims

1. A method for determining an impact score for a digital image, comprising:

providing the digital image wherein the digital image includes one or more faces;

using a processor to determine at least one image feature for each of the one or more faces;

using the processor to compute an object impact score for each of the one or more faces, wherein the object impact score is based at least upon one of the determined image features;

weighting the object impact score for each of the one or more faces based on at least one of the determined image features for the face;

using the processor to compute an impact score for the digital image by combining the weighted object impact scores for the one or more faces in the image; and

storing the computed impact score in a processor accessible memory.

2. The method of claim 1, further including:

using the processor to determine a size and a location for each of the one or more faces; and

weighting the object impact score for each of the one or more faces based on the location and the size of the face in the image.

3. The method of claim 1, wherein the image features include size, location, brightness, contrast, eye blink, facial expression, sharpness, noise, and colorfulness.

4. A method for adjusting an impact score for an appearance of a person in a digital image based on a profile for the person, comprising:

providing the digital image including the person;

providing a parameter profile for the person, the parameter profile including weighting scores for a plurality of features for the person;

using a processor to determine at least one image feature for the person;

using the processor to compute an object impact score for the person based at least upon one of the determined image features;

weighting the object impact score for the person using the parameter profile; and

storing the object impact score in a processor accessible memory.

5. The method of claim 4, further including using the processor to adjust the parameter profile for the person based on the determined image features for the person in the digital image.

6. The method of claim 4, wherein the image features include size, location, brightness, contrast, eye blink, facial expression, sharpness, noise, and colorfulness.

7. The method of claim 4, wherein the parameter profile includes weighting scores for individual features.

8. The method of claim 4, wherein the parameter profile includes weighting scores for demographic features.

9. A method for determining quality parameters of a media asset comprising:

using an object detector to detect and provide a plurality of objects from the media asset;

using an object feature detector to detect and provide a plurality of object features from the plurality of objects;

using an asset feature detector to provide a plurality of asset features from the media asset and the plurality object features;

using a capture information extractor to provide a plurality of capture features from the media asset;

using a social information extractor to provide a plurality of social features from the media asset; and

using a quality computer to provide a plurality of quality parameters from the plurality of object features, the plurality of asset features, the plurality of capture features, and the plurality of social features.

10. The method of claim 9 wherein the object detector is configured to detect human faces.

11. The method of claim 10 wherein the plurality of object features comprises a plurality of facial features.

12. The method of claim 10 wherein the plurality of object features comprises size and location of the face;

the pitch, roll, and yaw of the face;

the contrast, brightness, color balance, and noise of the face;

the gender, race, hair style and neatness of appearance, and identity of the face;

the facial expression, eye blink, eye gaze, red eye, mouth open, teeth detection, tongue detection, glasses detection, hat detection, or occlusion detection of the face.

13. The method of claim 10 wherein the plurality of object features comprises clothing, including the color of the clothing, the style of the clothing, or the condition of the clothing.

14. The method of claim 10 wherein the plurality of object features comprises environmental features.

15. The method of claim 9 wherein the object detector is configured to detect human bodies or torsos, animals, bacterium, viruses, internal organs, cars, or assembly line parts.

16. The method of claim 9 wherein the asset detector is configured to detect brightness, colorfulness, hues, color distribution, sharpness, noise, and contrast.

17. The method of claim 9 wherein the capture information extractor is configured to extract date and time that the media asset was captured, focal length, subject distance, magnification, presence of a flash, presence of a self-timer, GPS coordinates, and image resolution.

18. The method of claim 9 wherein the social information extractor is configured to extract number of likes of the media asset, comments, tags, viewings, downloads, links to other photo collections, upload date, whether or not the media asset was used as a profile picture, similarity to other media assets in other photo collections, or statistics on owners of the comments.

19. The method of claim 9 wherein the quality computer sums up equally valued or weighted inputs to provide the plurality of quality parameters.

20. The method of claim 16 wherein the brightness, contrast, colorfulness, sharpness, or noise is determined independently for each of the plurality of objects.