capstone
play

Capstone Gather Valuable Information on Headstones as an Automated - PowerPoint PPT Presentation

Capstone Gather Valuable Information on Headstones as an Automated Process Cameron Christiansen William A. Barrett Brigham Young University Overview Capstone Introduction Information available Geneological information Headstone


  1. Capstone Gather Valuable Information on Headstones as an Automated Process Cameron Christiansen William A. Barrett Brigham Young University

  2. Overview Capstone

  3. Introduction  Information available  Geneological information  Headstone location  Need for automated process  Number of headstones  Challenge of manual data gathering Capstone

  4. Related Research  Noisy OCR  Commercial apps  Google Goggles  Business Card Readers Capstone

  5. Methods  Photo capture  Segmentation  Image Filtering  OCR Capstone

  6. Photo Capture  iPhone 4  Basic needs  libexif to extract geotagging Capstone

  7. Segmentation  Watershed tobogganing  Determining areas of interest  Graph cut on TRAPs Capstone

  8. Image Filtering  Rotatation  Blurring Capstone

  9. OCR  Importance of Image Filtering  Common fonts  Tesseract OCR @~ DAN JONES AUG. 4, 1810 JAN. 3. 1862 . Capstone

  10. Application Capstone

  11. Future Work  Automated segmentation  Noise removal  Shadows and glares  Stone texture, artwork  Text rectification  OCR engine  Integration into mobile app Capstone

  12. Conclusion  Automate information extraction  Geotagging  Segmentation  Image Filtering  OCR  Index the information found Capstone

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend