System and method for storing hierarchical data related to an image

• US 10,049,123 B2
• Filed: 05/15/2017
• Issued: 08/14/2018
• Est. Priority Date: 03/16/2010
• Status: Active Grant

• Current Assignee: Cubic Digital Intelligence, Inc. (Cubic Corporation)
• Original Assignee: Pixia Corp. (Cubic Corporation)
• Inventors: Thakkar, Rahul C.
• Primary Examiner(s): Patel, Jayesh A
• Application Number:
  US15/595,483
• Publication Number:
  US 20170249305A1
• Time in Patent Office: 456 Days
• Field of Search: None
• CPC Class Codes: G06F 16/2246 Trees, e.g. B+trees
• CPC Class Codes: G06F 16/282 Hierarchical databases, e.g. IMS, LDAP data stores or Lotus Notes
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/20112 Image segmentation details
• CPC Class Codes: G06T 7/00 Image analysis
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: H04N 19/182 the unit being a pixel
• CPC Class Codes: H04N 19/184 the unit being bits, e.g. of the compressed video stream
• CPC Class Codes: H04N 19/186 the unit being a colour or a chrominance component
• CPC Class Codes: H04N 19/40 using video transcoding, i.e. partial or full decoding of a coded input stream followed by re-encoding of the decoded output stream

Abstract

A system and method of storing data related to an image is disclosed. The method may include: storing computed statistical data for pixels of an image; unevenly dividing the image into polygonal image sections where each polygonal image section includes substantially homogenous features; dividing the image into quads such that each quad has boundaries that contain at least a portion of one of the polygonal image sections; storing the original image; storing at least one reduced resolution dataset (RRD or R-set) of the image; and storing data related to a form of a hierarchical tree-based structure that represents the image or the at least one R-set. Each hierarchical tree structure may have a root node that corresponds to the image, branches that correspond to the plurality of quads, and leaf nodes that correspond to polygonal image sections.

Claims

1. A method for storing data related to an image, the image being associated with statistical data, the method being implemented by a computer system that includes one or more processors configured to execute computer program instructions, the method comprising:

unevenly dividing the image into a plurality of polygonal image sections based on a detection of substantially homogenous features delimiting each of the polygonal image sections, each polygonal image section having the substantially homogenous features and comprising a plurality of pixels, each pixel having one or more bands and a bit depth per band that is too high for displaying on a display screen, the statistical data comprising statistical data computed for each band of each pixel within each polygonal image section, the image being further divided into a plurality of quads such that each quad has boundaries that contains at least a portion of one of the plurality of polygonal image sections;

organizing the image, the plurality of quads, and the plurality of polygonal image sections in a form of a hierarchical tree structure such that a root node corresponding to the image has a plurality of branches corresponding to the plurality of quads and a branch node of the tree structure corresponding to a quad of the plurality of quads has two or more leaf nodes, each leaf node corresponding to a polygonal image section of the plurality of polygonal image sections; and

storing the statistical data and the form of the hierarchical tree structure.

2. The method according to claim 1, wherein the uneven division into the plurality of polygonal image sections comprises at least two polygonal image sections of the plurality of polygonal image sections that have different polygonal shapes or area sizes or that have a different number of sides.

3. The method according to claim 1, further comprising:

storing a plurality of reduced resolution datasets (R-Sets), each of the R-Sets being a progressively smaller version of the image,

wherein data describing each of the polygonal image sections is stored with the statistical data for pixels within the each section.

4. The method according to claim 1, further comprising:

determining in which quad of the plurality of quads and, for each quad, in which of the plurality of polygonal image sections each pixel is located by traversing the hierarchical tree structure from the root node corresponding to the image to the leaf nodes corresponding to the polygonal image sections,

wherein the hierarchical tree is traversed sequentially.

5. The method according to claim 1, further comprising:

determining in which quad of the plurality of quads and, for each quad, in which of the plurality of polygonal image sections each pixel is located by traversing the hierarchical tree structure from the root node corresponding to the image to the leaf nodes corresponding to the polygonal image sections,

wherein the hierarchical tree is traversed using parallel processing.

6. The method according to claim 1, wherein the statistical data of each band of each pixel within each polygonal image section of the image comprises a histogram, and

wherein if a pixel is within multiple, overlapping polygonal image sections then the histogram of the polygonal image section computed most recently is used in computing the statistical data.

7. The method according to claim 1, further comprising:

storing coordinates of each of the plurality of polygonal image sections and coordinates of at least one polygonal image section that intersects with a quad in a reduced resolution dataset (R-Set), the R-Set being reduced with respect to the image.

8. The method according to claim 1, further comprising:

converting each pixel having the bit depth per band that is too high for displaying on the display screen in an area of interest of the image into a corresponding pixel that has a lower bit depth per band that is displayable on the display screen using the statistical data of each polygonal image section in which the respective pixel is located to obtain an image that corresponds to the area of interest and that has pixels with the lower bit depth per band.

9. The method according to claim 1, wherein the statistical data for pixels within each polygonal image section is used to generate a plurality of look up tables, each look up table in the plurality of look up tables being associated with the corresponding polygonal image section of the plurality of polygonal image sections.

10. The method according to claim 1, wherein the statistical data for pixels within each polygonal section are computed using one or more of minimum/maximum values, standard deviation, mean, median, mode, skew, and kurtosis for each band of each pixel in the image.

21. The method according to claim 1, wherein the substantially homogenous features of a first one of the polygonal image sections are different from the substantially homogenous features of a second one of the polygonal image sections.

11. A computer system for storing data related to an image, the image being associated with statistical data, the computer system comprising one or more processors configured to:

unevenly divide the image into a plurality of polygonal image sections based on a detection of substantially homogenous features delimiting each of the polygonal image sections, each polygonal image section having the substantially homogenous features and comprising a plurality of pixels, each pixel having one or more bands and a bit depth per band that is too high for displaying on a display screen, the statistical data comprising statistical data computed for each band of each pixel within each polygonal image section, the image being further divided into a plurality of quads such that each quad has boundaries that contains at least a portion of one of the plurality of polygonal image sections;

organize the image, the plurality of quads, and the plurality of polygonal image sections in a form of a hierarchical tree structure such that a root node corresponding to the image has a plurality of branches corresponding to the plurality of quads and a branch node of the tree structure corresponding to a quad of the plurality of quads has two or more leaf nodes, each leaf node corresponding to a polygonal image section of the plurality of polygonal image sections; and

store the statistical data and the form of the hierarchical tree structure.

12. The computer system according to claim 11, wherein the uneven division into the plurality of polygonal image sections comprises at least two polygonal image sections of the plurality of polygonal image sections that have different polygonal shapes or area sizes or that have a different number of sides.

13. The computer system according to claim 11, wherein the one or more processors are further configured to store a plurality of reduced resolution datasets (R-Sets), each of the R-Sets being a progressively smaller version of the image, and

wherein data describing each of the polygonal image sections is stored with the statistical data for pixels within the each section.

14. The computer system according to claim 11, wherein the one or more processors are further configured to:

determine in which quad of the plurality of quads and, for each quad, in which of the plurality of polygonal image sections each pixel is located by traversing the hierarchical tree structure from the root node corresponding to the image to the leaf nodes corresponding to the polygonal image sections,

wherein the hierarchical tree is traversed sequentially.

15. The computer system according to claim 11, wherein the one or more processors are further configured to:

determine in which quad of the plurality of quads and, for each quad, in which of the plurality of polygonal image sections each pixel is located by traversing the hierarchical tree structure from the root node corresponding to the image to the leaf nodes corresponding to the polygonal image sections,

wherein the hierarchical tree is traversed using parallel processing.

16. The computer system according to claim 11, wherein the statistical data of each band of each pixel within each polygonal image section of the image comprises a histogram,

wherein if a pixel is within multiple, overlapping polygonal image sections then the histogram of the polygonal image section computed most recently is used in computing the statistical data.

17. The computer system according to claim 11, wherein the one or more processors are further configured to:

store coordinates of each of the plurality of polygonal image sections and coordinates of at least one polygonal image section that intersects with a quad in a reduced resolution dataset (R-Set), the R-Set being reduced with respect to the image.

18. The computer system according to claim 11, wherein the one or more processors are further configured to convert each pixel having the bit depth per band that is too high for displaying on the display screen in an area of interest of the image into a corresponding pixel that has a lower bit depth per band that is displayable on the display screen using the statistical data of each polygonal image section in which the respective pixel is located to obtain an image that corresponds to the area of interest and that has pixels with the lower bit depth per band.

19. The computer system according to claim 11, wherein the statistical data for pixels within each polygonal image section is used to generate a plurality of look up tables, each look up table in the plurality of look up tables being associated with the corresponding polygonal image section of the plurality of polygonal image sections.

20. The computer system according to claim 11, wherein the statistical data for pixels within each polygonal section are computed using one or more of minimum/maximum values, standard deviation, mean, median, mode, skew, and kurtosis for each band of each pixel in the image.