1. Image Processing
Lecture 1
Introduction and Application
-Gaurav Gupta
-Shobhit Niranjan

2. Instructors
 Gaurav Gupta
Can catch at : B109/Hall-1
mail at: gauravg@iitk.ac.in
gtalk: gauravg.84@GMAIL
more information at: http://home.iitk.ac.in/~gauravg
 Shobhit Niranjan
Can catch at : B211/Hall-1
mail at: nshobhit@iitk.ac.in
gtalk: shobhitn@GMAIL
more information at: http://home.iitk.ac.in/~nshobhit

3. Course Structure
1. Introduction to Image Processing, Application and
Prospects (Today)
2. Introduction, Image formation, camera models and
perspective geometry
3. Fourier Transform theory , Convolution and
Correlation
4. Color, Image enhancement Techniques
5. Binary images: thresholding, moments, topology
Note: Some topics may not be in order to maintain coherency and running
time requirements. (Bare with us …trying to teach first time !!)

4. Today
 Image Formation
 Range Transformations
 Point Processing
 Reading for this week:
 Gonzalez & Woods, Ch. 3

5. Image Formation
f(x,y) = reflectance(x,y) * illumination(x,y)
Reflectance in [0,1], illumination in [0,inf]

6. Sampling and Quantization

7. Sampling and Quantization

8. What is an image?
 We can think of an image as a function, f, from R2
to R:
 f( x, y ) gives the intensity at position ( x, y )
 Realistically, we expect the image only to be defined over a
rectangle, with a finite range:
 f: [a,b]x[c,d]  [0,1]
 A color image is just three functions pasted together.
We can write this as a “vector-valued” function:
( , )
( , ) ( , )
( , )
r x y
f x y g x y
b x y
 
 =
 
  

9. Images as functions

10. What is a digital image?
 We usually operate on digital (discrete) images:
 Sample the 2D space on a regular grid
 Quantize each sample (round to nearest integer)
 If our samples are ∆ apart, we can write this as:
f[i ,j] = Quantize{ f(i ∆, j ∆) }
 The image can now be represented as a matrix of integer values

11. Image processing
 An image processing operation typically defines a
new image g in terms of an existing image f.
 We can transform either the range of f.
 Or the domain of f:
 What kinds of operations can each perform?

12. Negative

13. Log

14. Image Enhancement

15. Contrast Streching

16. Image Histograms

17. Histogram Equalization

18. Neighborhood Processing (filtering)
 Q: What happens if I reshuffle all pixels within
the image?
 A: It’s histogram won’t change. No point
processing will be affected…
 Need spatial information to capture this.

19. Programming Assignment #1
 Easy stuff to get you started with
Matlab
 Shobhit will hold your first tutorial
 Topics will be from next 2 lectures

20. Applications
&
Research Topics

21. Document Handling

22. Signature Verification

23. Biometrics

24. Fingerprint Verification / Identification

25. Fingerprint Identification Research at
UNR
Minutiae Matching
Delaunay Triangulation

26. Object Recognition

27. Object Recognition Research
reference view 1 reference view 2
novel view recognized

28. Indexing into Databases
 Shape content

29. Indexing into Databases (cont’d)
 Color, texture

30. Target Recognition
 Department of Defense (Army, Airforce,
Navy)

31. Interpretation of aerial photography is a problem domain in both
computer vision and registration.
Interpretation of Aerial Photography

32. Autonomous Vehicles
 Land, Underwater, Space

33. Traffic Monitoring

34. Face Detection

35. Face Recognition

36. Face Detection/Recognition Research at
UNR

37. Facial Expression Recognition

38. Face Tracking

39. Face Tracking (cont’d)

40. Hand Gesture Recognition
 Smart Human-Computer User Interfaces
 Sign Language Recognition

41. Human Activity Recognition

42. Medical Applications
 skin cancer breast cancer

43. Morphing

44. Inserting Artificial Objects into a Scene

45. Companies In this Field In India and came
to IITK*
 Sarnoff Corporation
 Kritikal Solutions
 National Instruments
 GE Laboratories
 Ittiam, Bangalore
 Interra Systems, Noida
 Yahoo India (Multimedia Searching)
 nVidia Graphics, Pune (have high requirements)
 ADE Bangalore, DRDO

46. Links for Self Study and a little Play
 http://undergraduate.csse.uwa.edu.au/units/233.4
 http://www.netnam.vn/unescocourse/computervis
 Book: Digital Image Processing, 2nd Edition
by Gonzalez and Woods, Prentice Hall

47. Good Luck !!!