Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Image Stitching: Exploring Practices,     Software and Performance                    DON WILLIAMS;     IMAGE SCIENCE ASSO...
Image Stitching The merging of separate, neighboring digital images of  portions of an object into a single, larger digita...
Categories High total ownership   Research institutes, restoration studios, galleries, museums,    collectors, auction h...
Typical Stitching Workflow                             using COTS resources Object identified, mechanically constrained a...
Typical Stitching Software Operation Align – ( seam carving, content aware resize)   Identify approximate relative locat...
COTS Software ? Choices are overwhelming Developed as creative tools (edit vs. calibrate ?) Usually yield visually plea...
Good News, Bad News
Synthetic Stitching Experiment
Before Stitching
After Stitching
Steps in Modern Stitching Operations
Low Energy Seam Carving Boundary Path               (PhotoShop)
Sources of Variability/Errors Lens performance Capture conditions    Overlap    Rotation, flatness    Illumination va...
Error Detection/Prevention/Correction    Detection - Visual cueing features      Alignment - at seam interfaces      Bl...
Tactical Approaches Take an incremental approach Observe and benefit from algorithm idiosyncrasies Archive component ti...
Alternative Solutions Large flatbed scanners   Cruse   Zuetschel   I2S Large Sheet Fed scanners    WideTek 36DS, etc...
Conclusions Most Automerge tools do a good first order job, but …… Visually appealing results ≠ Spatially accurate resul...
Gratitudes  Dave Mathews, Image Collective       Northwestern University Stanford University, Green Library   Jeff Chi...
Upcoming SlideShare
Loading in …5
×

Image Stitching: Exploring Practices, Software and Performance, D.Williams & P. D. Burns

559 views

Published on

Presentation by Don Williams at IS&T's Archiving 2013 Conference

Published in: Technology, Art & Photos
  • Be the first to comment

  • Be the first to like this

Image Stitching: Exploring Practices, Software and Performance, D.Williams & P. D. Burns

  1. 1. Image Stitching: Exploring Practices, Software and Performance DON WILLIAMS; IMAGE SCIENCE ASSOCIATES; WILLIAMSON, NY/US, PETER D. BURNS; BURNS DIGITAL IMAGING; FAIRPORT, NY/USIS&T’s Archiving 2013 Conference, Washington DC April 2013
  2. 2. Image Stitching The merging of separate, neighboring digital images of portions of an object into a single, larger digital object. Requires integration of both spatial and luminance image information. Identified under FADGI gap analysis Increased popularity Are the results as analytically accurate as they appear ?
  3. 3. Categories High total ownership  Research institutes, restoration studios, galleries, museums, collectors, auction houses  Step-and-repeat robotics: SatScan™ Art, ResolutionArt, Google Art  Well characterized imaging performance, and mechanical constraints  High value objects Affordable COTS hardware and software  Institutional libraries, small collections, service bureaus  COTS hardware and/or software  Less calibrated systems, demanding productivity, challenging and varied content.
  4. 4. Typical Stitching Workflow using COTS resources Object identified, mechanically constrained and scan parameters selected Multiple captures performed  Manual or mechanical translation  6 - 30 separate captures Images uploaded to servers or dedicated computer Into the software sausage factory  Results QC’d  Redo with new approaches or software parameters if unacceptable Manually edit in image editors Set limits on time/image Save and move on
  5. 5. Typical Stitching Software Operation Align – ( seam carving, content aware resize)  Identify approximate relative location of the component images  Identify corresponding features in overlap areas  Select stitching boundaries and margins  Correct for distortion, perspective, intensity differences. Merge  Combine image tiles and create boundaries
  6. 6. COTS Software ? Choices are overwhelming Developed as creative tools (edit vs. calibrate ?) Usually yield visually pleasing results but … Pshop Photomerge, Autopano, PTGui Ease of use –  Few excellent results vs. many good ones ?  How many choices do you need ?
  7. 7. Good News, Bad News
  8. 8. Synthetic Stitching Experiment
  9. 9. Before Stitching
  10. 10. After Stitching
  11. 11. Steps in Modern Stitching Operations
  12. 12. Low Energy Seam Carving Boundary Path (PhotoShop)
  13. 13. Sources of Variability/Errors Lens performance Capture conditions  Overlap  Rotation, flatness  Illumination variability Mechanics Software complexity Computational power and storage Object characteristics Algorithm idiosyncrasies Operator training
  14. 14. Error Detection/Prevention/Correction  Detection - Visual cueing features  Alignment - at seam interfaces  Blending – image equalization processing  Prevention & Correction  Good image practices and equipment  Use simple fill and digital cloning tools  Avoid complex operations
  15. 15. Tactical Approaches Take an incremental approach Observe and benefit from algorithm idiosyncrasies Archive component tiles for future processing Try it again ! Take care in original capture  Placement, hardware  Reasonable overlap Object Triage ?  Fragile vs. non fragile  Sizes ?
  16. 16. Alternative Solutions Large flatbed scanners  Cruse  Zuetschel  I2S Large Sheet Fed scanners  WideTek 36DS, etc.  Contex
  17. 17. Conclusions Most Automerge tools do a good first order job, but …… Visually appealing results ≠ Spatially accurate results. Good imaging practices and moderated image processing ( lens and lighting profiles) can reduce geometric distortions significantly. Most errors tend to be due align rather than merge operations. Keep post processing edits simple. Better full reference distortion metrics needed to assess stitching goodness.
  18. 18. Gratitudes  Dave Mathews, Image Collective  Northwestern University Stanford University, Green Library  Jeff Chien, Adobe Systems Inc. For more information contact: Don Williams or Peter Burns

×