Take the 2-minute tour ×
Ask Patents is a question and answer site for people interested in improving and participating in the patent system. It's 100% free, no registration required.

AN OVERBROAD PATENT ON classifying digital images into semantic categories - This application from IV seeks to patent the idea of...Generating time-based event boundaries detected in a plurality of images, computing inter-event durations, grouping events into clusters based on the inter-event durations, and validating that each event belongs to an associated cluster based on event level content based features using a rule-based system.! 10 minutes of your time can help narrow US patent applications before they become patents. Follow @askpatents on twitter to help.

QUESTION - Have you seen anything that was published before 11/19/2008 that discusses:

  • Classification of digital images into event based semantic categories

If so, please submit evidence of prior art as an answer to this question. We welcome multiple answers from the same individual.

EXTRA CREDIT - Semantic categories may include events, people, places etc.

TITLE: Semantic classification of digital images based on events

Summary: [Translated from Legalese into English] Generating time-based event boundaries detected in a plurality of images, computing inter-event durations, grouping events into clusters based on the inter-event durations, and validating that each event belongs to an associated cluster based on event level content based features using a rule-based system.

  • Publication Number: US 20140046914 A1
  • Application Number: US 14/054,954
  • Assignee: IV
  • Prior Art Date: Seeking prior Art predating 11/19/2008
  • Open for Challenge at USPTO: Open through 8/12/2014
  • Link to Google Prior Art Search - "Find Prior Art"

Claim 1 requires each and every step below:

A method comprising:

  1. generating, using a processor, time-based event boundaries detected in a plurality of images;

  2. computing inter-event durations;

  3. grouping events into clusters based on the inter-event durations; and

  4. validating, using a rule-based system, that each event belongs to an associated cluster based on event level content based features.

In English this means:

A method comprising:

  1. Generating time-based event boundaries detected in a plurality of images;

  2. Computing inter-event durations;

  3. Grouping events into clusters based on the inter-event durations; and

  4. Validating whether each event belongs to an associated cluster based on event level content based features using a rule-based system.

Good prior art would be evidence of a system that did each and every one of these steps prior to 11/19/2008

You're probably aware of ten pieces of art that meet this criteria already... separately, the applicant is claiming A location is determined for each image in an event and grouping events into clusters based upon the locations


"Semantic classification of digital images" from the Applicant


What is good prior art? Please see our FAQ.

Want to help? Please vote or comment on submissions below. We welcome you to post your own request for prior art on other questionable US Patent Applications.


share|improve this question
1  
What makes you think this is overbroad. I haven't heard anything like this before? –  McKay Mar 31 at 12:41

2 Answers 2

This patent from 2005 also seems to contain prior art and references to prior art. Ex:

"[5] So far, there have been quite a bit of research suggesting differing methods of clustering photo data. Basically, those methods include clustering photos according to the photographed time, and methods of clustering photos based on contents-based feature information. As further developments, research on methods of clustering photos based on events of the photos, and methods of clustering photos based on the actual people in the photos, have been carried out."

share|improve this answer

Here's an example of potential prior art for this patent application: US20070136275

If you are aware of other potential prior art references, please post it here.

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.