1 / 61

Introduction to Computer Vision Location 70-3455

Introduction to Computer Vision Location 70-3455. Lecture 1 Dr. Roger S. Gaborski. Where to Find Me. Office: 70 – 3647 Office Hours: Tuesday, 2:00-3:00pm (except December 8 th ) Thursday, 11:00-noon My lab 70-3400 Email: rsg@cs.rit.edu. Co-Instructor. Yuheng ‘Helen’ Wang.

soren
Download Presentation

Introduction to Computer Vision Location 70-3455

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. Introduction to Computer Vision Location 70-3455 Lecture 1 Dr. Roger S. Gaborski

  2. Where to Find Me • Office: 70 – 3647 • Office Hours: • Tuesday, 2:00-3:00pm (except December 8th) • Thursday, 11:00-noon • My lab 70-3400 • Email: rsg@cs.rit.edu RS Gaborski

  3. Co-Instructor • Yuheng ‘Helen’ Wang RS Gaborski

  4. Teaching Assistant • Santosh Kandregula • E-Mail: <sxk9011@rit.edu> RS Gaborski

  5. Course Outline • Textbook – Digital Image Processing using MATLAB • SECOND EDITION 2009 Gatesmark Publishing • Online MATLAB tutorial-Register at Mathworks: • http://www.mathworks.com/academia/student_center/tutorials/launchpad.html • Topics • Homework • Quizzes and Exams • Projects (4005-757 only) • Grading • Webpage: www.cs.rit.edu/~rsg (includes course calendar on CV page) • Lecture slides will not always be posted on webpage RS Gaborski

  6. Homework • Questions concerning Homework • Do not wait until the night before its due to start working on the HW • Ask questions in class concerning HW • First, ask the TA during his office hours • If TA cannot answer your questions, see me during my office hours • Do not send me email concerning the HW after noon the night before it is due. I will not be able to respond to your email. RS Gaborski

  7. Grading • Homework 30%(457) 20%(757) • Quizzes/Exams 70% 70% • Project* --- 10% • No Project for 4003-457 • *Project: 757 Individual only, weekly presentation updates RS Gaborski

  8. Course Grade • 90%-100% A* • 80%-89% B • 70%-79% C • 60%-69% D • <60% F * Note: For example, 89.4 is a ‘B’, 89.5 is rounded to 90 which is an ‘A’ RS Gaborski

  9. Project • Choose from a list of projects provided on course Project Page • Ten minute verbal proposal presentation (see course calendar) • Verbal updates (see course calendar) • *Project grade includes verbal proposal, verbal update report and final report RS Gaborski

  10. Computer Vision • Low-level Processes • Primitive operations • Reduce noise • Enhance contrast • Sharpen image • Mid-level Processes • Input are images, output are attributes extracted from image (edges, contours and identity of objects • Segmentation (partition image into objects or regions) • Description of objects/regions RS Gaborski

  11. Computer Vision • High-level Processes • Understanding content of images RS Gaborski

  12. SUMMARY:Goals of Computer Vision • Image Enhancement • Reduce noise in an image thereby revealing features in the image, extract features • Image Processing Operations • Segment the image into objects • Label individual objects • Image Understanding • Understand the ‘content’ of an image or sequence of images (video) • Extract meaning of the image RS Gaborski

  13. Computer Vision – Interpretation of Images • Digital photographs • Medical radiographic images • Functional magnetic resonance imaging (fMRI) • Medical ultrasound • Industrial radiographic images • Digital video images • Satellite images • Astronomy RS Gaborski

  14. Digital Image RS Gaborski

  15. Digital Image RS Gaborski

  16. Digital Image RS Gaborski

  17. Medical Related Images Information obtained from images: Bone structure Soft Tissue Brain Activity

  18. Medical Radiographic Image www.4umi.com/image/x-ray.jpg RS Gaborski

  19. Medical Ultrasound http://keystone.stanford.edu/~huster/photos/i/ultrasound.640.jpg RS Gaborski

  20. Functional MRI A 20-year old female drinker A 20-year old female nondrinker Response to the spatial working memory task. Brain activation is shown in bright colors. RS Gaborski www.alcoholism2.com/

  21. Industrial Applications Non Destructive Testing Inspection / Security

  22. Industrial Radiographic Image www.vidisco.com/ CabinetXrayMic80A_01.htm RS Gaborski

  23. Industrial Radiographic Image Pseudo- color www.vidisco.com/ CabinetXrayMic80A_01.htm RS Gaborski

  24. RS Gaborski

  25. Satellite Images andAstronomy

  26. Satellite Images RS Gaborski www.noaa.gov

  27. Astronomy Images www.sdsc.edu/ sciencegroup/astronomy/ RS Gaborski

  28. Astronomy Images astro.martianbachelor.com/ RS Gaborski

  29. Image Database Problem • Assume you have taken pictures with your digital camera the last three years • You now have 4000 pictures stored on your computer’s hard drive • How do you sort them? RS Gaborski

  30. Sample Images C:\Documents and Settings\rsg\My Documents\My Pictures\Picture RS Gaborski

  31. iPhoto 09 "Places" Geotagging • http://www.youtube.com/watch?v=GVW8700LrvE RS Gaborski

  32. How do you find a particular face • How do you find a particular object in an image? • Faces • Cars • Buildings • etc RS Gaborski

  33. Image Models • Task: “Look for an object in an image” • Assume the task is to find rectangle and washer objects RS Gaborski

  34. Image models, continued RS Gaborski

  35. Image Models • Task: “Look for an object in an image” • Assume the task is to find rectangle and washer objects • Find outlines of objects in the image • Create a model of the object • Rectangle: Four straight lines, Opposite lines equal in length, 90 degree angles, lines connected • Washer: Two concentric circles RS Gaborski

  36. Image models, edges RS Gaborski

  37. Image models, continued One object partially overlaps another RS Gaborski

  38. Objects are 3 Dimensional Rotating Disk Frame 1 Frame 2 Frame 3 RS Gaborski

  39. License Plate Model • Rectangular (depending on viewpoint) • Aspect ratio 2:1 • Textures (characters on license plate) RS Gaborski

  40. RS Gaborski

  41. Face Model http://www.faceresearch.org/ RS Gaborski

  42. Face Model http://www.faceresearch.org/ RS Gaborski

  43. Face Model Features: eyes, nose, mouth, shape of face (oval) Spatial orientation of features Issues to investigate: how do we detect features? Normalize for different faces? Scale? Orientation? Cluttered background? RS Gaborski

  44. iPhoto 09 "Faces" Face Recognition, http://www.youtube.com/watch?v=NzCV_L87J2I • Digital Face Recognition, http://www.youtube.com/watch?v=obyPvoSTo-o&feature=related RS Gaborski

  45. Deformable Objects in Video RS Gaborski

  46. Finding Cars in ImagesTraining RS Gaborski

  47. Testing RS Gaborski

  48. What’s Missing? • perceptual organization • similarity between semantic concepts “The semantic gap” RS Gaborski

  49. Examples of “semantic” similarity From: http://web.cecs.pdx.edu/~mm/ RS Gaborski

  50. From: http://web.cecs.pdx.edu/~mm/ RS Gaborski

More Related