Method and system for detection and characterization of open space in digital images

• US 5,901,245 A
• Filed: 01/23/1997
• Issued: 05/04/1999
• Est. Priority Date: 01/23/1997
• Status: Expired due to Term

• Current Assignee: Apple Inc.
• Original Assignee: Eastman Kodak Company
• Inventors: Senn, Robert A., Warnick, James, Mehrotra, Rajiv
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): MEHTA, BHAVESH M
• Application Number:
  US08/786,932
• Time in Patent Office: 831 Days
• Field of Search: 382/203, 382/206, 382/162, 382/165, 382/172, 382/173, 382/190, 382/199, 382/254, 382/270, 382/271-275, 345/429-431, 348/584, 348/586, 348/589, 358/466
• US Class Current: 382/190
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 10/507 Summing image-intensity values; Histogram projection analysis
• 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 for detecting open space in a digital image, the method comprises the steps of creating an activity map for permitting determination of the activity of the digital image; determining which pixels in the activity map are below a threshold; and identifying open space as contiguous pixels of the activity map having values below the predetermined threshold.

Claims

1. A method for automatically detecting an open space region in a digital image, comprising the steps of:

(a) creating a corresponding activity map from the digital image for permitting determination of the activity of the digital image;

(b) analyzing the activity map to determine an activity threshold value;

(c) determining which pixels in the activity map are below the activity threshold value; and

(d) analyzing the threshold activity map for identifying contiguous pixel regions of the activity map having values below the activity threshold corresponding to open space regions in the digital image.

2. The method as in claim 1, wherein the step of analyzing the activity map to determine an activity threshold value includes analyzing the activity map to determine an image dependent threshold.

3. The method as in claim 2, wherein the step of creating the activity map is created by using either edge detection, local entropy measurement, local texture analysis, local color/luminance difrence analysis.

4. The method as in claim 2, wherein the step of creating the activity map includes determining an activity value at a pixel which activity value is computed as a maximum absolute difference between a value of a predetermined pixel and its neighboring pixel values in the digital image.

5. The method of claim 2, wherein the image dependent threshold is determined by an analysis of a histogram of the activity map histogram.

6. A method for automatically characterizing an open space region in a digital image, comprising the steps of

(a) creating a corresponding activity map from the digital image for permitting determination of the activity of the digital image:

(b) analyzing the activity map to determine an activity threshold value;

(c) determining which pixels in the activity map are below the activity threshold value;

(d) analyzing the threshold activity map for identifying contiguous pixel regions of the activity map having values below the activity threshold corresponding to open space regions in the digital image;

(e) extracting image metadata associated with the open space region.

7. The method as in claim 6, wherein step (e) includes identifying individually or any combination of either a shape of the open space, location of the open space in the digital image, color of the open space, or texture of the open space as the metadata.

8. The method as in claim 7, wherein determining the threshold includes analyzing the activity map to determine an image dependent threshold.

9. A system for automatically detecting an open space region in a digital image, the system comprising:

(a) means for creating a corresponding activity map from the digital image for permitting determination of the activity of the digital image;

(b) means for analyzing the activity map to determine an activity threshold value;

(c) means for determining which pixels in the activity map are below the activity threshold value; and

(d) means for analyzing the threshold activity map for identifying contiguous regions of the activity map having values below the activity threshold corresponding to open space regions in the digital image.

10. The system as in claim 9, wherein said means for determining the pixels below the threshold includes analyzing the activity map to determine an image dependent threshold.

11. The system as in claim 10, wherein said means for creating the activity map uses either edge detection, local entropy measurement, local texture analysis, local color/luminance difference analysis.

12. The system as in claim 10, wherein said means for creating the activity map includes determining an activity value at a pixel which activity value is computed as a maximum absolute difference between a value of a predetermined pixel and its neighboring pixel values in the digital image.

13. The system of claim 10, wherein means for determining the image dependent threshold is determined by analyzing a histogram of the activity map.

14. A computer program product for automatically detecting an open space region in a digital image, comprising:

a computer readable storage medium having a computer program stored thereon for performing the steps of;

(a) creating a corresponding activity map from the digital image for permitting determination of the activity of the digital image;

(b) analyzing the activity map to determine an activity threshold value;

(c) determining which pixels in the activity map are below the activity threshold value; and

(d) analyzing the threshold activity map for identifying contiguous regions of the activity map having values below the activity threshold corresponding to open space regions in the digital image.

15. The computer program product as in claim 14, wherein the step of analyzing the activity map to determine an activity threshold value includes analyzing the activity map to determine an image dependent threshold.

16. The computer program product as in claim 15, wherein the step of creating the activity map is created by using either edge detection, local entropy measurement, local texture analysis, local color/luminance difference analysis.

17. The computer program product as in claim 15, wherein the step of creating the activity map includes determining an activity value at a pixel which activity value is computed as a maximum absolute difference between a value of a predetermined pixel and its neighboring pixel values in the digital image.

18. The computer program product as in claim 15, wherein the image dependent threshold is determined by analyzing a histogram of the activity map.

19. A system for automatically characterizing an open space region in a digital image, the system comprising:

(a) creating a corresponding activity map from the digital image for permitting determination of the activity of the digital image;

(b) analyzing the activity map to determine an activity threshold value;

(c) determining which pixels in the activity map are below the activity threshold value;

(d) analyzing the threshold activity map for identifying contiguous pixel regions of the activity map having values below the activity threshold corresponding to open space regions in the digital image; and

(e) means for extracting metadata associated with the open space region.

20. The system as in claim 19, wherein extracting metadata means includes means for identifying individually or any combination of a shape of the open space, a location of the open space in the digital image, a color of the open space, or a texture of the open space as the metadata.

21. The system as in claim 20, wherein means for determining the threshold includes means for analyzing the activity map to determine an image dependent threshold.

22. A computer program product for automatically characterizing an open space region in a digital image, comprising:

a computer readable storage medium having a computer program stored thereon for performing the steps of;

(a) creating a corresponding activity map from the digital image for permitting determination of the activity of the digital image;

(b) analyzing the activity map to determine an activity threshold value;

(c) determining which pixels in the activity map are below the activity threshold value;

(d) analyzing the threshold activity map for identifying contiguous pixel regions of the activity map having values below the activity threshold corresponding to open space regions in the digital image; and

(e) extracting metadata associated with the open space region.

23. The computer program product as in claim 22, wherein step (e) includes identifying individually or any combination of a shape of the open space, a location of the open space in the digital image, a color of the open space, or a texture of the open space as the metadata.

24. The computer program product as in claim 23, wherein means for determining the threshold includes means for analyzing the activity map to determine an image dependent threshold.

25. A digital capture device comprising:

(a) means for creating a corresponding activity map from the digital image for permitting determination of the activity of the digital image;

(b) means for analyzing the activity map to determine an activity threshold value;

(c) means for determining which pixels in the activity map are below the activity threshold value; and

(d) means for analyzing the threshold activity map for identifying contiguous pixel regions of the activity map having values below the activity threshold corresponding to open space regions in the digital image.

26. The digital capture device as in claim 25, wherein said analyzing the activity map to determine the threshold value means includes means for analyzing the activity map to determine an image dependent threshold.

27. The digital capture device as in claim 26 further comprising means for creating said activity map means by using either edge detection, local entropy measurement, local texture analysis, local. color/luminance difference analysis.

28. The digital capture device as in claim 26, wherein said activity map means includes means for determining an activity pixel value which activity value is computed as a maximum absolute difference between a value of a predetermined pixel and its neighboring pixel values in the digital image.

29. The digital capture device of claim 26, wherein the image dependent threshold is determined by analyzing a histogram of the activity map.