Interactive image selection method

• US 8,731,308 B2
• Filed: 08/12/2009
• Issued: 05/20/2014
• Est. Priority Date: 10/03/2008
• Status: Expired due to Fees

• Current Assignee: Monument Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Intellectual Ventures Fund 83 LLC (Intellectual Ventures LLC)
• Inventors: Kiddle, Graham Robert, Fry, Peter Thomas, Piper, John Denis, Muammar, Hani, Payne, Alan
• Primary Examiner(s): CHAWAN, SHEELA C
• Application Number:
  US13/122,153
• Publication Number:
  US 20120114257A1
• Time in Patent Office: 1,742 Days
• Field of Search: 382/224, 382/312, 382/100, 382/137, 382/138, 382/276, 382/284, 428/914, 428/913, 358/471, 358/400, 358/500, 358/518, 348/739, 348/744, 348/759, 348/760, 348/761, 348/218.1, 348/207.99, 339/130, 339/297, 339/310, 339/314, 339/166, 339/159
• US Class Current: 382/224
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/587 using geographical or spatial information, e.g. location

Abstract

Image selection method amongst a plurality of digital images (102) classified in a plurality of images categories (104a, 104b 104c), the method comprising the following steps: —allocating to each image at least one strength value (112, 112i, 112j, 112k), —allowing an user to select (120) images amongst the plurality of digital images, —collecting (122) user data, —updating (130) the strength value of all images classified in a same category than an image selected by the user as a function of the collected user data, and —upon selection of an image by the user, automatically selecting (142) at least one additional image classified in at least one same category than an image selected by the user, and for which the strength value exceeds a threshold value —making the selected images available (146) for subsequent use.

Claims

1. A method comprising:

allocating, by a processing system, a strength value to each image in a plurality of digital images, wherein the plurality of digital images are classified into a plurality of categories;

collecting, by the processing system, user data of a user in response to a selection of at least one image from the plurality of digital images;

updating, by the processing system, the strength value of all images classified in a same category as the at least one selected image as a function of the collected user data and as a function of a visual quality of an image; and

automatically selecting, by the processing system, at least one additional image classified in at least one same category as the at least one selected image, the selection of the additional image being based on the strength value of the at least one additional image.

2. The method of claim 1, further comprising selecting additional images for which the strength value exceeds a threshold value.

3. The method of claim 1 wherein collecting user data comprises at least one of:

measuring a display duration for each image viewed by the user;

collecting data on the user'"'"'s name, date of birth, age, location;

counting the number of clicks performed on a computer keyboard/mouse, whilst an image selected by the user is displayed;

capturing image of the user'"'"'s face;

collecting data on prior images viewed by the same user; and

measuring emotive response of the user to at least one image.

4. The method of claim 1, wherein the strength value of the at least one additional image is updated by:

an update value proportional to the display duration of the at least one additional image;

an update value proportional to a correlation of semantic content of the at least one additional image and a captured image of the user'"'"'s face;

a preset update value when the user'"'"'s name, date of birth or location is found in metadata of the at least one selected image;

an update value proportional to a number of clicks performed whilst the at least one additional image is displayed;

an update value proportional to an emotive response of the user to the at least one additional image; and

an update value proportional to the strength value of previously viewed images.

5. The method of claim 1, wherein the plurality of digital images are classified into classes corresponding to features extracted from image data.

6. The method of claim 5, wherein each image in the plurality of digital images are classified in at least one amongst the following categories:

a category corresponding to semantic content of the image;

a category corresponding to a time- or date-frame in which the image has been captured;

a category corresponding to a key word stored as a metadata along with the image data;

a category of images selected by the user in a same session on a selection/viewing device;

a category of images selected by location of the image capture or user location; and

a category of images selected by significance to the user.

7. The method of claim 1, further comprising:

collecting images;

determining features of the images based on image data and/or image metadata computation;

searching for similarities between determined features for sets of images, and/or searching similarities between computed features and preset features of image categories;

sorting images having similar features in common categories.

8. The method of claim 7, further comprising the automatic creation of new categories of images each time a similarity is found from among a preset number of images.

9. The method of claim 1, further comprising updating a plurality of strength values based on input from a plurality of users, wherein each of the plurality of strength values correspond to data about the corresponding user.

10. The method of claim 1, further comprising a random selection of additional images, and/or a selection of additional images for which the strength value is below a threshold value and/or a selection of additional images not classified in a same category as images selected by the user.

11. The method of claim 1, further comprising updating the strength value of the at least one additional image by an update value proportional to an emotive response of the user to the at least one additional image.

12. The method of claim 1, further comprising reducing the strength value of an image as the function of the visual quality of the image, wherein the function of visual quality determines that the visual quality of the image is poor.

13. The method of claim 12, wherein the function of the visual quality of the image is based on at least one of:

contrast of the image, sharpness of the image, color analysis, spatial frequency analysis, texture analysis, and histograms analysis.

14. The method of claim 1, further comprising weighting the strength value of a first image assigned to a category with respect to a second image assigned to the category.

15. The method of claim 1, further comprising displaying the at least one additional image, wherein those of the at least one additional image corresponding to different categories are displayed in different areas of a display screen.

16. A method comprising:

allocating, by a processing system, a strength value to each image in a plurality of digital images, wherein the plurality of digital images are classified into a plurality of categories;

collecting, by the processing system, user data in response to a selection of at least one image from the plurality of digital images;

updating, by the processing system, the strength value of all images classified in a same category as the at least one selected image as a function of the collected user data and as a function of a visual quality of an image;

automatically selecting, by the processing system, at least one additional image classified in at least one same category as the at least one selected image, the selection of the additional image being based on the strength value of the at least one additional image; and

displaying the at least one additional image, wherein each additional image is displayed with a relative size which is a function of the strength value of the additional image.

17. A non-transitory computer-readable medium having computer-readable instructions stored thereon, the computer-readable instructions comprising:

instructions to allocate a strength value to each image in a plurality of digital images, wherein the plurality of digital images are classified into a plurality of categories;

instructions to collect user data in response to a selection of at least one image from the plurality of digital images;

instructions to update the strength value of all images classified in a same category as the at least one selected image as a function of the collected user data and as a function of a visual quality of an image; and

instructions to, automatically select at least one additional image classified in at least one same category as the at least one selected image, the selection of the additional image being based on the strength value of the at least one additional image.

18. A system comprising:

a memory configured to store a plurality of digital images;

a processing system configured to;

allocate a strength value to each image in the plurality of digital images, wherein the plurality of digital images are classified into a plurality of categories;

collect user data in response to a selection of at least one image from the plurality of digital images;

update the strength value of all images classified in a same category as the at least one selected image as a function of the collected user data and as a function of a visual quality of an image; and

automatically select at least one additional image classified in at least one same category as the at least one selected image, the selection of the additional image being based on the strength value of the at least one additional image.

19. The system of claim 18, wherein the processor is further configured to:

determine features of images based on image data;

search for similarities between determined features for sets of images; and

sort images having similar features in common categories.

20. The system of claim 18, wherein the processor is further configured to automatically create new categories of images each time a similarity is found amongst a preset number of images.