Anzeige
Anzeige

### Weeks 1 Introductions_V1_1.ppt

1. Digital Image Processing Lecture 1 Introduction Fall 2019
2. Introduction to the course ► Class Time 8:10 – 8:50 & 8:55 – 9:35 Monday 1A102 Week 1-16 13:30 – 15:30 Wednesday Week 3- ►Instructor Wen Shi (shiwen@wzu.edu.cn)
3. Introduction to the course ► Grading  Attendance: 10%  Class participation: 10%  Lab practice : 30%  Final report: 50%  Total: 100%
4. ► Applications Face modeling Introduction to the course
5. ► Applications Face generator Object generator Introduction to the course
6. ► Applications Style transfer Introduction to the course
7. ► Applications Expression recognition Object recognition Introduction to the course
8. ► Applications Super-resolution Compression Introduction to the course
9. Introduction to the course ► Textbooks Digital Image Processing, by Rafael Gonzalez and Richard Woods
10. Introduction to the course ► Useful references but are not required Computer Vision: Algorithms and Applications, by Richard Szeliski Multiple View Geometry in Computer Vision, by Richard Hartley Computer Vision: A Modern Approach, by David Forsyth and Jean Ponce. Photography, by Barbara London and John Upton
11. ►Lectures  Signals and systems. Discrete sequences and systems, their types and properties. Linear time-invariant systems, convolution.  Phasors. Eigen functions of linear time-invariant systems. Review of complex arithmetic. Some examples from electronics, optics and acoustics.  Fourier transform. Phasors as orthogonal base functions. Forms of the Fourier transform. Convolution theorem, Dirac’s delta function, impulse combs in the time and frequency domain.  Discrete sequences and spectra. Periodic sampling of continuous signals, periodic signals, aliasing, sampling and reconstruction of low-pass and band-pass signals, spectral inversion.  Discrete Fourier transform. Continuous versus discrete Fourier transform, symmetry, linearity, review of the FFT, real-valued FFT.
12. ►Lectures  Correlation coding. Random vectors, dependence versus correlation, covariance, decorrelation, matrix diagonalization, eigen decomposition, Karhunen-Loève transform, principal component analysis. Relation to orthogonal transform coding using fixed basis vectors, such as DCT.  Lossy versus lossless compression. What information is discarded by human senses and can be eliminated by encoders? Perceptual scales, masking, spatial resolution, colour coordinates, some demonstration experiments.  Quantization, image/video coding standards. A/mu-law coding, delta coding, JPEG, H.264, HEVC.
13. Introduction to the course ► Article Reading  Medical image analysis (MRI/PET/CT/X-ray tumor detection/classification)  Face, fingerprint, and other object recognition  Image and/or video compression  Image segmentation and/or denoising  Digital image/video watermarking/steganography and detection  Whatever you’re interested …
14. Journals & Conferences in Image Processing ► Journals: — IEEE T IMAGE PROCESSING — IEEE T MEDICAL IMAGING — INTL J COMP. VISION — IEEE T PATTERN ANALYSIS MACHINE INTELLIGENCE — PATTERN RECOGNITION — COMP. VISION AND IMAGE UNDERSTANDING — IMAGE AND VISION COMPUTING … … ► Conferences: — CVPR: Comp. Vision and Pattern Recognition — ICCV: Intl Conf on Computer Vision — ACM Multimedia — ICIP — SPIE — ECCV: European Conf on Computer Vision — CAIP: Intl Conf on Comp. Analysis of Images and Patterns … …
15. Introduction ► What is Digital Image Processing? Digital Image — a two-dimensional function x and y are spatial coordinates The amplitude of f is called intensity or gray level at the point (x, y) Digital Image Processing — process digital images by means of computer, it covers low-, mid-, and high-level processes low-level: inputs and outputs are images mid-level: outputs are attributes extracted from input images high-level: an ensemble of recognition of individual objects Pixel — the elements of a digital image ( , ) f x y
16. Introduction 123 33 234 45 67 90 12 134 34 56 89 54 67 98 111 56 67 90 65 34 …. The World Numerical representation of the brightness and colors of the world scene
17. Introduction ► Mainly study these topics Image acquisition – (low-level) digital representation of the world scenes Image processing – noise removal, smoothing, sharpening, contrast enhancement, alter the appearance of an image Image compression – efficiently represent image data for storage (save disk space) and communication (save network bandwidth) . Display – render the image data on reproduction media (monitors, printing papers)
18. Introduction ► More related subjects Artificial intelligence Pattern recognition Machine learning Robotics Visualization
19. Image Processing ► Image acquisition – (low-level) digital representation of the world scenes 123 33 234 45 67 90 12 134 34 56 89 54 67 98 111 56 67 90 65 34 …. Numbers represent the brightness and colors of the world objects, but we have no knowledge what object, e.g., books, monitors, these numbers contain – hence low-level
20. Image Processing ► Image acquisition – (low-level) digital representation of the world scenes 123 33 234 45 67 90 12 134 34 56 89 54 67 98 111 56 67 90 65 34 …. What numbers? How many numbers? How large/small should the numbers be?
21. Image Processing ► Image processing – noise removal, smoothing, sharpening, contrast enhancement, alter the appearance of an image Noise removal
22. Image Processing ► Image processing – noise removal, smoothing, sharpening, contrast enhancement, alter the appearance of an image Sharpening
23. Image Processing ► Image processing – noise removal, smoothing, sharpening, contrast enhancement, alter the appearance of an image Blurring/smoothing
24. Image Processing ► Image processing – noise removal, smoothing, sharpening, contrast enhancement, alter the appearance of an image Contrast enhancement
25. Image Processing ► Image processing – noise removal, smoothing, sharpening, contrast enhancement, alter the appearance of an image Alter appearance
26. Image Processing ► Image compression – efficiently represent image data for storage (save disk space) and communication (save network bandwidth) 245,760 bytes 69,632 bytes 5,951 bytes
27. Image Processing ► Display – render the image data on reproduction media (monitors, printing papers) 123 33 234 45 67 90 12 134 34 56 89 54 67 98 111 56 67 90 65 34 ….
28. Image Processing ► Display – render the image data on reproduction media (monitors, printing papers) 123 33 234 45 67 90 12 134 34 56 89 54 67 98 111 56 67 90 65 34 ….
29. Sources for Images ► Electromagnetic (EM) energy spectrum ► Acoustic ► Ultrasonic ► Electronic ► Synthetic images produced by computer
30. Electromagnetic (EM) energy spectrum Major uses Gamma-ray imaging: nuclear medicine and astronomical observations X-rays: medical diagnostics, industry, and astronomy, etc. Ultraviolet: lithography, industrial inspection, microscopy, lasers, biological imaging, and astronomical observations Visible and infrared bands: light microscopy, astronomy, remote sensing, industry, and law enforcement Microwave band: radar Radio band: medicine (such as MRI) and astronomy
31. Examples: Gama-Ray Imaging
32. Examples: X-Ray Imaging
33. Examples: Ultraviolet Imaging
34. Examples: Light Microscopy Imaging
35. Examples: Visual and Infrared Imaging
36. Examples: Visual and Infrared Imaging
37. Examples: Infrared Satellite Imaging
38. Examples: Automated Visual Inspection
39. Examples: Automated Visual Inspection The area in which the imaging system detected the plate Results of automated reading of the plate content by the system