1 / 28

CSE 455 Computer Vision Autumn 2014

CSE 455 Computer Vision Autumn 2014. Professor Linda Shapiro shapiro@cs.washington.edu TA: Ezgi Mercan ezgi@cs.washington.edu TA: Bilge Soran bilge@cs.washington.edu. Introduction. What IS computer vision? Where do images come from?. The analysis of digital images by a computer.

Download Presentation

CSE 455 Computer Vision Autumn 2014

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. CSE 455Computer VisionAutumn 2014 Professor Linda Shapiro shapiro@cs.washington.edu TA: Ezgi Mercan ezgi@cs.washington.edu TA: Bilge Soran bilge@cs.washington.edu

  2. Introduction • What IS computer vision? • Where do images come from? The analysis of digital images by a computer You tell me!

  3. Applications: Medical Imaging CT image of a patient’s abdomen liver kidney kidney

  4. Visible Man Slice Through Lung

  5. 3D Reconstruction of the Blood Vessel Tree

  6. Robotics • 2D Gray-tone or Color Images • 3D Range Images “Mars” rover What am I?

  7. Robot Soccer

  8. Google Driverless Car

  9. Image Databases: Images from my Ground-Truth collection: http://www.cs.washington.edu/research/imagedatabase/groundtruth • Retrieve images containing trees

  10. Some Features for Image Retrieval

  11. Documents:

  12. Science Calineuria (Cal) Doroneuria (Dor) Yor (Yor) Previous Classification Results: UW and Oregon State University

  13. Soil Mesofauna XenillusA TraychetesA ZyqoribafulaA AchipteriaA BdellozoniumI CatoposurusA EniochthoniusA BelbaA BelbaI PtenothrixV PtiliidA HypochthoniusLA EpilohmanniaT EpilohmanniaD EpilohmanniaA EntomobrgaTM EpidamaeusA QuadroppiaA HypogastruraA MetrioppiaA LiacarusRA IsotomaVI NothrusF IsotomaA onychiurusA PlatynothrusF TomocerusA OppiellaA SiroVI PhthiracarusA PlatynothrusI PeltenuialaA

  14. Surveillance: Event Recognition in Aerial Videos Original Video Frame Color Regions Structure Regions

  15. 2D Face Detection

  16. Face Recognition Glasgow University

  17. 2D Object Recognition from “Parts” Oxford University

  18. Graphics: Special Effects Andy Serkis, Gollum, Lord of the Rings

  19. 3D Reconstruction and Graphics Viewer

  20. 3D Craniofacial Shape Analysis from Meshes of Children’s Heads

  21. Digital Breast Biopsy ImageShowing Regions of Interest

  22. Digital Image Terminology: 0 0 0 0 1 0 0 0 0 1 1 1 0 0 0 1 95 96 94 93 92 0 0 92 93 93 92 92 0 0 93 93 94 92 93 0 1 92 93 93 93 93 0 0 94 95 95 96 95 pixel (with value 94) its 3x3 neighborhood region of medium intensity resolution (7x7) • binary image • gray-scale (or gray-tone) image • color image • multi-spectral image • range image • labeled image

  23. The Three Stages of Computer Vision • low-level • mid-level • high-level image image image features features analysis

  24. Low-Level sharpening blurring

  25. Low-Level Canny original image edge image Mid-Level ORT data structure circular arcs and line segments edge image

  26. Mid-level K-means clustering (followed by connected component analysis) regions of homogeneous color original color image data structure

  27. Low- to High-Level low-level edge image mid-level consistent line clusters high-level BuildingRecognition

More Related