![Image Representation
Discrete representation of images
• we’ll carve up image into a rectangular grid of pixels P[x,y]
• each pixel p will store an intensity value in [0 1]
• 0 → black; 1 → white; in-between → gray
• Image size mxn → (mn) pixels](https://image.slidesharecdn.com/paulo1-240918114928-f6bb7172/85/Digital-Image-Processing-for-Bachelor-and-Masters-25-320.jpg)
Digital Image Processing for Bachelor and Masters
- 1. CSCE 763: Digital Image Processing Spring 2024 Dr. Yan Tong Department of Computer Science and Engineering University of South Carolina
- 2. Course Information Instructor: Dr. Yan Tong Email: tongy@cse.sc.edu Office: Storey Innovation Center 2273 Office Hours: By appointment
- 3. Dr. Tong’s Main Research Areas CV/ML Enabled Data Analysis Fundamental Research in CV/ML Multimodal Information Fusion
- 4. Now, tell me about yourself! • Name • Major • Research interest • Why do you take this course
- 5. Today’s Agenda • Welcome • Tentative Syllabus • Topics covered in the course
- 7. Tentative Syllabus • Prerequisites • Objectives • Textbook • Grade
- 8. Prerequisites of This Course This is a computer science course • It will involve a fair amount of math –calculus, linear algebra, geometry –probability –analog/digital signal processing –graph theory etc. • It will involve the modeling and design of a real system - one final course project –Programming skills with matlab, Python, or C++
- 9. The Objective of This Course This is a graduate-level topic course • Research oriented –Paper reading & presentation –Final project & presentation –Review on the state-of-the-art • Understanding → Innovation –your own innovative and original work/opinion/result • Basic knowledge → Research frontier –learn through reading recent papers
- 10. Textbook Required: Digital Image Processing, Rafael C. Gonzalez and Richard E. Woods, 4th Edition, Pearson We will cover many topics in this text book We will also include special topics on recent progresses on image processing
- 12. Requirement for Final Project Option 1: A complete research project • Introduction (problem formulation/definition) • literature review • the proposed method and analysis • experiment • conclusion • reference Option 2: A survey research • A well-defined problem or topic • a complete list of previous (typical) work on this problem (15+ papers under the topic) • clearly and briefly describe the topic • analyze each method/group and compare them • give the conclusion and list of references
- 13. Requirement for Final Project Requirements • Select a topic and write a one-page proposal (due Feb 21 ) • Progress report (discuss with the instructor) • Research work and report writing • Oral presentation • Final project report
- 14. Requirement for Final Project Teamwork is acceptable for a research project (Option 1) • <=2 people • Get the permission from the instructor first • Under a single topic, each member must have their own specific tasks • One combined report with each member clearly stating their own contributions • One combined presentation
- 15. Requirement for Final Project Written report • Report format: the same as an IEEE conference paper • Executable code must be submitted with clear comments except for a survey study Academic integrity (avoiding plagiarism) • don’t copy other person’s work • describe using your own words • complete citation and acknowledgement whenever you use any other work (either published or online)
- 16. Requirement for Final Project Evaluation • written report (be clear, complete, correct, etc.) • code (be clear, complete, correct, well documented, etc.) • oral presentation • discussion with the instructor • quality: publication-level project – extra credits
- 17. Requirement for Final Project Notes: • You are encouraged to incorporate your own research expertise in, but the project topic must be related to the content of this course • Discuss with the instructor on topic selection, progress, writing, and presentation • Use the library and online resource
- 18. Paper Reading and Presentation • A paper picked by yourself and approved by the instructor • Suggested paper source: To be provided • Thorough understanding of the paper • Prepare PPT slides • Clearly explain the main contributions in the selected paper • Critical comments and discussions • About 10 mins oral presentation for each student
- 19. Major Topics Covered in Class Image acquisition and digital image representation Image enhancement Image restoration Color image processing Image compression Image segmentation Morphological image processing Special topics on recent progresses on digital image processing
- 20. Human Perception VS Machine Vision http://www.kollewin.com/blog/electromagnetic-spectrum/ • Limited vs entire EM spectrum
- 21. Image Processing → Image Analysis Image acquisition Image enhancement Image compression Image segmentation Object recognition Scene understanding Semantics Low level Mid level High level Image processing Image analysis (Computer vision, Pattern recognition, etc.)
- 22. Image Acquisition and Representation
- 23. Examples 1. Brain MRI 1 and 3. http://en.wikipedia.org 4. http://emap-int.com 2. http://radiology.rsna.org 5. http://www.imaging1.com 2. Cardiac CT 3. Fetus Ultrasound 4. Satellite image 5. IR image
- 24. Image Acquisition Camera + Scanner → Digital Camera: Get images into computer lens shutter aperture film
- 25. Image Representation Discrete representation of images • we’ll carve up image into a rectangular grid of pixels P[x,y] • each pixel p will store an intensity value in [0 1] • 0 → black; 1 → white; in-between → gray • Image size mxn → (mn) pixels
- 26. Color Image RGB channels Red (1,0,0) Green (0,1,0) Blue (0,0,1) + 0.6 0.0 0.8 0 1 Colors along Red axis
- 27. Video: Frame by Frame 30 frames/second
- 30. Image Compression → Video compression
- 31. Image Processing → Image Analysis Image acquisition Image enhancement Image compression Image segmentation Object recognition Scene understanding Semantics Low level Mid level High level Image processing Image analysis (Computer vision, Pattern recognition, etc.)
- 32. Image Segmentation Microsoft multiclass segmentation data set
- 33. Image Completion Interactively select objects. Remove them and automatically fill with similar background (from the same image) I. Drori, D. Cohen-Or, H. Yeshurun, SIGGRPAH’03
- 34. More Examples
- 36. Object Detection / Recognition
- 38. Biometrics
- 39. Super-Resolution
- 40. Applications of Digital Image Processing Digital camera Photoshop Human computer interaction Medical imaging for diagnosis and treatment Surveillance Automatic driving … Fast-growing market!
- 41. Basic Concepts in Digital Image Processing
- 42. Now, Introducing some basic concepts in digital image processing • Human vision system • Basics of image acquisition Reading: Chapter 2.
- 43. Elements of Human Visual Perception Human visual perception plays a key role in selecting a technique Lens and Cornea: focusing on the objects Two receptors in the retina: • Cones and rods • Cones located in fovea and are highly sensitive to color • Rods give a general overall picture of view, are insensitive to color and are sensitive to low level of illumination http://www.mydr.com.au/eye-health/eye-anatomy Visual axis
- 44. Distribution of Rods and Cones in the Retina
- 45. Brightness Adaptation: Subjective Brightness Scotopic: • Vision under low illumination • rod cells are dominant Photopic: • Vision under good illumination • cone cells are dominant The total range of distinct intensity levels the eye can discriminate simultaneously is rather small Brightness adaptation level Lambert
- 46. Brightness Discrimination Weber Ratio/Fraction Short-duration flash Small ratio: good brightness discrimination Large ratio: poor brightness discrimination I Ic : c I I + An opaque glass Additional light source
- 47. Brightness Discrimination at Different Intensity Levels rod cone
- 48. Perceived Intensity is Not a Simple Function of the Actual Intensity (1)
- 49. Perceived Intensity is Not a Simple Function of the Actual Intensity – Simultaneous Contrast
- 50. Optical Illusions: Complexity of Human Vision
- 52. Features Groups of Features Objects Scenes How do we perceive separate features, objects, scenes, etc. in the environment? ▪ Perception of a scene involves multiple levels of perceptual analysis.
- 53. What Do We Do With All Of This Visual Information?? “Bottom up processing” • Data-driven • Sensation reaches brain, and then brain makes sense of it “Top down processing” • Cognitive functions informs our sensation • E.g., walking to refrigerator in middle of night Features Groups of Features Objects Scenes Bottom-up Top-down