Hierarchical image feature-based visualization

• US 20030093437A1
• Filed: 07/16/2001
• Published: 05/15/2003
• Est. Priority Date: 07/16/2001
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Gargi, Ullas, Tretter, Daniel R.
• Granted Patent: US 7,425,963 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/90328 using search space presentation or visualization, e.g. category or range presentation and selection
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99937 Sorting
• CPC Class Codes: Y10S 707/99938 Concurrency, e.g. lock management in shared database
• CPC Class Codes: Y10S 707/99939 Privileged access
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A method of visualizing and retrieving data files includes displaying a plurality of images representing data files on a display device using a first distance metric between each data file. A portion of the images is redisplayed on the display device using a refined distance metric. Optionally, the method repeats the redisplaying step until a desired data file is identifiable. Then, the desired data file is retrieved.

Claims

1. A method of visualizing and retrieving a data file from a set of data files comprising:

displaying a plurality of images representing corresponding data files on a display device using a first distance metric between each data file;

redisplaying a portion of the images on the display device using a refined distance metric; and

performing at least one of retrieving, marking, and selecting at least one desired data file.

2. The method of claim 1, further comprising:

repeating the redisplaying step until a desired data file is identifiable.

3. The method of claim 1, wherein the first distance metric is calculated by a method comprising:

computing a feature vector for each data file; and

calculating the first distance metric between each data file using a first subset of data contained in the feature vector.

4. The method of claim 3, wherein the refined distance metric is calculated by a method comprising:

calculating a second distance metric between each data file using a second subset of data contained in the feature vector which is greater than the first subset.

5. The method of claim 4, wherein the step of computing the feature vector comprises:

computing the feature vector for each data file before starting the method;

storing the feature vector for each data file; and

accessing the feature vector for each data file.

6. The method of claim 4, wherein each feature vector has a length of at least eight.

7. The method of claim 4, wherein the feature vector includes at least one of a color feature and a texture feature.

8. The method of claim 4, wherein the feature vector includes at least one of a color histogram, color moment, color coherence histogram, Multiresolution Simultaneous Autoregressive (MRSAR) Model, coarseness, and directionality.

9. The method of claim 1, wherein the first distance metrics are mapped into an N-dimensional space using FastMap for displaying and wherein the refined distance metrics are mapped into an N-dimensional space using FastMap for redisplaying.

10. The method of claim 9, wherein N is two or three.

11. The method of claim 1, wherein the data files are image files.

12. The method of claim 1, wherein the data files are video files.

13. The method of claim 1, further comprising:

establishing a fixed scale that spans a maximum distance between the plurality of data files; and

indicating a relative position on the fixed scale for the redisplay of the portion of the images, thereby providing the user with a reference frame.

14. The method of claim 1, wherein the fixed scale is at least one of a linear scale, a logarithmic scale, and a hyperbolic scale.

15. The method of claim 1, further comprising:

providing a display depth indication that represents an amount of overlapping of images on the display; and

scrolling to view images that were previously not viewable due to overlapping of the images.

16. The method of claim 1, wherein the portion of the images redisplayed is graphically selected by the user.

17. A method of interactively retrieving a data file from a set of data files in real time comprising:

displaying a plurality of images, each image corresponding to a data file, on a display device using a first distance metric between each data file;

interactively selecting, by a user, a portion of the images;

redisplaying the portion of the images in real time on the display device using a refined distance metric; and

retrieving a desired data file.

18. The method of claim 17, wherein the first distance metric is calculated by a method comprising:

computing a feature vector for each data file; and

calculating the first distance metric between each data file using a first subset of data contained in the feature vector.

19. The method of claim 18, wherein the refined distance metric is calculated by a method comprising:

calculating a second distance metric between each data file using a second subset of data contained in the feature vector which is greater than the first subset.

20. The method of claim 19, wherein the first distance metrics are mapped into a N-dimensional space using FastMap for displaying and second distance metrics are mapped into a N-dimensional space using FastMap for redisplaying.