Your SlideShare is downloading. ×
An interpretation system for ducth cadastral system
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×
Saving this for later? Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime – even offline.
Text the download link to your phone
Standard text messaging rates apply

An interpretation system for ducth cadastral system

364
views

Published on


0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
364
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
1
Comments
0
Likes
0
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide

Transcript

  • 1. Recognition system for building flop lines
    Poojith Jain-0666444
  • 2. Introduction
    Aim
    Extraction of informationfrom building flop lines
    Storing extractedinformation
    Representinginformation in CityGML
  • 3. BasicConcepts
    Graph
     Graph is an ordered pair G: = (V,E) comprising a set V of  vertices together with a set E of edges.
    Graph is used to show connectivity of vertices.
    Computer Representation of images
    Pixels
    Pixel valuebasedon the color
    Arrayrepresentation
  • 4. The Process
    Thresholding and NoiseRemoval
    Labels Identification And image cleaning
    Graphconstruction
    Flop line image of Building
    CityGMLRepresentation
  • 5. Building Flop Line
    Grayscale image
    High Resolution
    Indication
    • Thicklinesownershipboundary
    • 6. Numbersownesrhiprights
    • 7. Labels usage type
  • Assumptions made
    Always thicklinesindicatesownershipboundary
    Numbersalwaysenclosed in a polygon
    Single number in a polygonrepresentsownership
    Numbers does notovelapwithlines and symbols
  • 8. The Process
    Thresholding and NoiseRemoval
    Labels Identification And image cleaning
    Graphconstruction
    Flop line image of Building
    CityGMLRepresentation
  • 9. Thresholding and NoiseRemoval
    Thresholding
    Noise
    Gaps
    Missing pixels
    Continuity is important for contour detection
    Solution
    ClosingOperation
  • 10. ClosingOperation
    CLOSING
  • 11. The Process
    Thresholding and NoiseRemoval
    Labels Identification And image cleaning
    Graphconstruction
    Flop line image of Building
    CityGMLRepresentation
    NumberIdentification
    Removing Labels and
    Thin Lines
  • 12. OwnershipIdentification
    Identify the location of the labels
    Connected component labeling
    Size criteria
    Extract the labels
    Recognize the labels
    {3,x,y}
    OCR
    {4,x,y}
    OCR
  • 13. The Process
    Thresholding and NoiseRemoval
    Labels Identification And image cleaning
    Graphconstruction
    Flop line image of Building
    CityGMLRepresentation
    NumberIdentification
    Removing Labels and
    Thin Lines
  • 14. Removing Labels and Thin Lines
    Labels indicatepropertyusage and type
    Thin Lines indicate sub regioninformation
    Thicklinesindicateboundary
    Remove labels and thinlines.
    Connected component labeling
    Opening operation
  • 15. The Process
    Thresholding and NoiseRemoval
    Labels Identification And image cleaning
    Graphconstruction
    Flop line image of Building
    CityGMLRepresentation
    Skeletonization
    Corner Dection
    IdentifyingOwnershipboundary
  • 16. Skeletonization
    WhySkeletonization?
    Reducesforegroundregions in an image to a skeleton
    Bythinningoperation
    Skeletonshouldbe
    One pixel width
    Preserves connectivity
    Preserves Topology
    Centered
  • 17. The Process
    Thresholding and NoiseRemoval
    Labels Identification And image cleaning
    Graphconstruction
    Flop line image of Building
    CityGMLRepresentation
    Skeletonization
    Corner Detection
    Graphconstruction
    Face and Floor
    identification
  • 18. Corner Detection
    Corenrs are intersection of twoor more edges
    Corners forms the node of the graph
    Harris corner Detection
    Invariant to
    Scaling
    Image noise
    Rotation
    Illuminationvariance
    Corner Detection
  • 19. Graph Construction
    Identify the nodes
    Identify the edges
    Optimization
  • 20. Graph Construction
    Identify the nodes
    Identify the edges
    Optimization
  • 21. The Process
    Thresholding and NoiseRemoval
    Labels Identification And image cleaning
    Graphconstruction
    Flop line image of Building
    CityGMLRepresentation
    Skeletonization
    Corner Detection
    Graph Construction
    Face and Floor
    Identification
  • 22. Face Recognition
    Eachenclosed face becomesownershipboundary
    Associateownership
    Store the information
    {3,x,y}
    3
    {4,x,y}
    4
  • 23. Floor Identification
    IdentifyingFloors
    Storing Information
    2
    3
    4
    4
    4
    1
    2
    3
    4

×