1. Fundamentals of Digital Image Processing
By:
Dr G R Sinha, IEEE Senior Member & Fellow IETE
Professor, Department of Electronics and Communication Engineering
CMR Technical Campus, Hyderabad
ISTE National Award, TCS Award, IEI Award, Expert Engineer Award, Young Engineer Award, Young Scientist Award Recipient

2. Outline of Presentation
Motivation
Digital Images and Computer Vision
Digital Image Processing
Resources
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017 2

3. Motivation/Preamble
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

4. My Invited Talk at NRSC Hyderabad on 7th Feb, 2017
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

5. Remote Sensing and Image Classification
Remote Sensing helps to acquire and interpret geospatial data to develop information about features, objects, and classes on Earth's land surface, oceans, and atmosphere.
It detects and measures electromagnetic energy emanating from distant objects made of various materials, so that we can identify and categorize these object by class or type, substance, and spatial distribution.
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

6. Remote Sensing and Image Classification (contd..)
Data Acquision and Survey of Remotely Sensed Images
Pre-processing of Images
Developing Image Enhancement Methods
Assessment of Enhancement Methods
Image Segmentation and Feature Extraction
Classification and Regional Description
Study of Lands, Forests, Crop Assessment and Impact of Environmental Changes
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

7. Application in Agriculture
Crop modeling for yield & production forecast / estimation
Crop growth monitoring
Soil status monitoring
Regular reports regarding total area under cultivation
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

8. Application in Forestry
Forest change detection; forest resource inventory
Planning for a-forestation strategies
Futuristic resource planning; Sustainability of environment
Wild life conservation & development for recreation purpose
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

9. Digital Image and Computer Vision
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

10. Digital Image One picture is worth more than ten thousand words
Digital Image: Two-dimensional function, f(x,y), where x and y are spatial (plane) coordinates, and the amplitude of f at any pair of coordinate (x,y) is called the intensity or gray level of the image at that point; x, y and the amplitude f(x,y) of an image are all finite, discrete quantities.
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

11. Digital Image (contd..) Digital image = a multidimensional
array of numbers
Each component in the image: Pixel
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

12. Digital Image (contd..)
Intensity image or monochrome image: Each pixel corresponds to light intensity normally represented in gray scale (gray level).
Gray scale values
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

13. Digital Image (contd..) RGB components
Color image or RGB image: each pixel contains a vector representing red, green and blue components.
RGB components
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

14. Digital Image (contd..) Binary data
Binary image or black and white image: Each pixel
contains one bit : 1 represent white 0 represents black
Binary data
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

15. Digital Image (contd..) Index value
Index image: Each pixel contains index number
pointing to a color in a color table
Color Table
Index No.
Red
component
Green
Blue 1
0.1
0.5
0.3 2
1.0
0.0 3 4 5
0.2
0.8
0.9 …
Index value
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

16. Representing Digital Images
The representation of an M×N numerical array as
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

17. Computer Vision
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

18. Computer Vision (contd..)
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

19. Digital Image Processing
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

20. Digital Image Processing
Low Level Process
Input: Image Output: Image
Examples: Noise removal
Mid Level Process
Input: Image Output: Attributes
Examples: Recognition, Segmentation
High Level Process
Input: Attributes
Output: Understanding
Examples: Scene understanding, Autonomous navigation
Important Stages in Digital Image Processing
Image Restoration
Morphological Processing
Segmentation
Representation & Description
Image Enhancement
Object Recognition
Problem Domain
Colour Image Processing
Image Compression
Image Acquisition
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

21. Morphological Processing Representation & Description
Image Acquisition
Image Restoration
Morphological Processing
Image Enhancement
Segmentation
Image Acquisition
Object Recognition
Colour Image Processing
Image Compression
Representation & Description
Problem Domain
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

22. Morphological Processing
Image Enhancement
Image Restoration
Morphological Processing
Image Enhancement
Segmentation
Image Acquisition
Object Recognition
Image Compression
Representation & Description
Colour Image Processing
Problem Domain
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

23. Image Restoration Problem Domain Image Restoration
Morphological Processing
Image Enhancement
Segmentation
Image Acquisition
Object Recognition
Representation & Description
Problem Domain
Colour Image Processing
Image Compression
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

24. Morphological Processing
Image Restoration
Morphological Processing
Image Enhancement
Segmentation
Image Acquisition
Object Recognition
Representation & Description
Problem Domain
Colour Image Processing
Image Compression
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

25. Segmentation Morphological Processing Image Enhancement
Image Restoration
Image Restoration
Morphological Processing
Morphological Processing
Image Enhancement
Image Enhancement
Segmentation
Segmentation
Image Acquisition
Image Acquisition
Object Recognition
Representation & Description
Problem Domain
Colour Image Processing
Image Compression
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

26. Representation & Description
Image Restoration
Morphological Processing
Image Enhancement
Segmentation
Image Acquisition
Object Recognition
Representation & Description
Problem Domain
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

27. Colour Image Processing
Image Restoration
Morphological Processing
Image Enhancement
Segmentation
Image Acquisition
Object Recognition
Colour Image Processing
Representation & Description
Problem Domain
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

28. Pre-processing
Pre-processing is used to improve quality of image by removing noise signals in images.
To provide `better' input for automated image processing techniques.
Categories of Image Enhancement: Spatial domain and Transform domain.
Spatial domain methods are based on direct manipulation of pixels in an image;
and Frequency domain processing techniques are based on modifying the Fourier transform of an image.
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017 28

29. Image Enhancement        
Spatial domain: Directly operate over the pixels, for example contrast enhancement, Gray-level clustering histogram equalization (GLC-CE)
           g(x, y) = T[ f(x, y)]
where f(x, y) is the input image, g(x, y), the processed image, and T, an operator on f(x, y) defined over some neighborhood of (x, y).
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

30. Histogram Equalization (Left) Contrast Enhancement (Right)
Examples       
Histogram Equalization (Left)
Contrast Enhancement (Right)
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

31. Spatial Domain Methods
Spatial Domain Techniques
Point Processing
Image Subtraction
Image Averaging
Spatial Filtering
Gabor Filtering
Weiner Filtering
Histogram Processing
Gray Scale Modification
Log
Transformation
Power Law Transformation
Piecewise Transformation
Contrast Stretching
Gray Level Slicing
Bit Plane Slicing
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

32. Contrast Stretching & Linear Stretching
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

33. Contrast Enhancement
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

34. Low-pass Filtering
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

35. Inverse Fourier Transform
Frequency Domain Methods 
Low pass filtering or smoothing domain filters,
High pass filtering or sharpening domain filters,
Homomorphic filtering, and
Color image enhancement.
Pre-processing
Fourier Transform
Post-Processing
Filter Function
H(u,v)
Inverse Fourier Transform
f(x,y)
Input Image
F(u,v)
H(u,v)F(u,v)
g(x,y)
Enhanced Image
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

36. Noise Statistics Characteristics of noise:
Noise type (additive, signal-dependent, multiplicative, impulse etc.)
PDF, variance, relative variance, probability of impulse noise, etc.
There are no universal methods for coping well with any type and level of noise.
Noise analysis and removal helps in change and target detection, multi-temporal image analysis, underwater imaging, ocean imaging, multimodal analysis, quality assessment, and image restoration.
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

37. Statistical parameters for Evaluation
PSNR (Peak-signal-to-noise-ratio)
CNR (Contrast-to-noise-ratio)
Invariant moments
Mean and Variance values
Histogram
SSIM
Invariant Moments
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

38. Segmentation
Main types: Pixel based, Region based and Contour based Segmentation methods
Pixel based: Thresholding, Histogram based adaptive thresholding, k-means clustering etc.
Region based: Region growing method
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017 38

39. Post Processing: Performance Measures
Size, shape, area, dimension, Shadow, tone, Color, Texture and Pattern
Shape parameters: Perimeter, distance, aspect ratio, major and minor axis
PSNR and CNR
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017 39

40. Spatial resolution High vs. Low?
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

41. Spatial resolution affects
2-bit Image (4 gray levels)
8-bit Image (256 gray levels)
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

42. Resources
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

43. Companies in India Sarnoff Corporation Kritikal Solutions
National Instruments
GE Laboratories
Ittiam, Bangalore
Interra Systems, Noida
Yahoo India (Multimedia Searching)
nVidia Graphics, Pune (have high requirements)
Microsoft research
DRDO labs
ISRO labs …
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

44. Books -------------------------------------- Digital Image Processing
Rafael C. Gonzalez and Richards E. Woods,
Addison Wesley
Rafael Gonzalez and Paul Wintz
Fundamentals of Digital Image Processing
Anil K. Jain
Prentice Hall, 1989.
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

45. Concluding Remarks with Roadmap
The applications of Image Processing strengthen the scope for potential research in the field of remote sensing, Astronomical Image Processing, underwater imaging, soil & plant health monitoring, biometrics, Medical Image Processing etc.
Image de-noising method (optimal implementation using neuro-fuzzy method) and a good segmentation method with optimal set of parameters would help in achieving good data classification and interpretation results.
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017

46. Sincere Thanks with Inspiring Equation c = 2 (Doubly enthused) E =4
E= mc2
E= Excellence, m = Motivation,
C =Commitment
c = 0.5 (Half hearted) E = ¼
c = 2 (Doubly enthused) E =4
Fundamentals of Image Processing Dr G R Sinha, FDP on DIP and Computer Vision th June 2017