From Class 01 (This is the reading from word file)

01. What is computer vision? What is difference between image processing and computer vision?
Computer vision
Computer Vision tries to do what a human brain does with the retinal data that means
understanding the scene based on image data. That mainly involves segmentation, recognition
and reconstruction (3D) and these work together to give us the scene understanding.

Computer Vision:
Input: Images
Output: Knowledge of the scene (recognize objects, people, activity happening there, distance
of the object from camera and each other, ...)
Methods: Image processing, machine learning, ...
Image Processing:
Input: Images
Output: Images (Might be in different formats, for example compressed images). No knowledge
of the scene is given.
Methods: Different filtering, pixel processing, ...
02. What is difference among computer graphics, Computer vision and image processing?
Computer Graphics is about drawing things on the screen with pixels, using mathematics and
physics (trigonometry, lighting, shading, curvature, etc) to give the impression of objects to a
human viewer.
The output requirements can be simple eg arcade games, or complex eg realistic rendition for
movies.

Image Processing is about taking a digital input (black & white photo or colour photo or scanned
image or xerox copy etc) and using mathematics and physics (trigonometry, lighting, shading,
curvature, etc) to extract details of objects in that input.

The output requirements can be simple eg finding lines or detecting colours (which can be for
non-AI purposes) or complex eg finding faces or detecting emotions (which can be for AI
purposes)
03. Computer vision toolbox, computer vision tasks?
Computer Vision System Toolbox™ provides algorithms, functions, and apps for designing and
simulating computer vision and video processing systems. You can perform feature detection,
extraction, and matching; object detection and tracking; motion estimation; and video
processing.
e.g. IXION’s computer vision team develops innovative applications for complex needs, such as
monitoring and inspection of industrial facilities, guidance of a multicolor during its landing,
object recognition and evaluation of its status, classic surveillance applications (intrusion), field
analysis, underwater structure tracking, etc.
Computer vision tasks include methods for acquiring, processing, analyzing and understanding
digital images, and extraction of high-dimensional data from the real world in order to produce
numerical or symbolic information, e.g., in the forms of decisions.
 04. What is the necessity of optimization algorithm in computer vision?
Many important problems in computer vision, such as structure from motion and image
registration, involve model estimation in presence of a significant number of outliers. Due to the
outliers, simple estimation techniques such as least squares perform very poorly. To deal with
this issue, vision researchers have come up with a number of techniques that are robust to
outliers, such as Hough transform and RANSAC (random sample consensus). Recent advances in
robust model estimation includes sampling based techniques with guaranteed optimality for
low-dimensional problems and optimization of semi-robust norms for high-dimensional
problems. Optimized algorithms can solve low-dimensional estimation problems with over 99%
outliers in a few seconds, as well as can detect outliers in structure from motion problems with
thousands of variables.

05. Intelligence power inside human – in natural or artificial?

06. Rod and cone equivalent to which part of normal camera?

Rod equivalent to Silver Halide (AgBr)
Code equivalent to dye coupler.
07. Write similarity and dissimilarity between camera and eye?

08. Draw Eye vs camera

09. Differentiate eye vs camera

10. Transformation matrics 2D only?

Rotate point A(2,3) origin by 90 degree angle.
Reflect point A(-3,4) against x-axis?

From Class 02 (This study is from PDF)

01. What is image processing? What is pixel? What is digital image?

02. What is digital image processing? Origin of Digital Image Processing?
03. What is digitalization? What are sources for images?
04. What are the applications of DIP? What is Electro Magnetic spectrum?
05. What are the components of image processing system? Describe them with figure.
06. Draw a human eye? Describe the structure of human eye with components of eye?
07. What are the elements of visual perception? Describe them?
08. Image Acquisition process explain
09. Write about brightness adaption and discrimination
10. What is optical illusion
11. What are the fundamental steps in Digital image processing
12. Write down a simple image formation model?
13. What is image sampling and quantization
14. Write down digital image definition
15. Write on spatial and gray level resolution
 16. Write on zooming and shrinking of digital image?
17. What is interpolation? How many types of interpolation is there/ describe them with figure?
18.

Class 3, 4 (This study is from Lec-01 PPT)

01. Define pixel relationship? What are the basic relationships between pixels? Describe them with
figure and example
02. What is interpolation? Explain the types of interpolation?

03. What are the neighbors of a pixel? Example

04. Define and explain:

(i) Neighborhood
(ii) Paths
(iii) Adjacency
(iv) Regions and boundaries
(v) Connectivity
05. What is Adjacency? How many types of Adjacency are there? Explain with example
06. What is path? Show the paths in case of 4,8,m adjacency with figure
07. Find out relation between regions, foreground, and background?
08. Boundary, 4,8,m adjacency, paths in question 1-8
4 adjacency maximum value: 1
8 adjacency maximum value: 6
09. What is distance? How to measure the Distance indifferent way?
10. Explain Euclidean, city block, chess board distance with example
11. What is noise? What is noiseless image and corrupted image?
12. Write noise reducing math explain with picture of astronomical observation?
13. Explain with example and figure image subs-traction and multiplication?
14. Explain set and logical operations with math and different figure?
15. Spatial operation: single-pixel, neighborhood operations explain.
16. What is affine transformation? How many types of affine transformation? Explain them?
17. Explain image rotation and intensity interpolation
18. What is intensity assignment, forward mapping, and inverse mapping?
19. Explain: Image rotation and intensity interpolation
20. What is image registration explain it with figure.
21. Explain image transform

Sir’s suggestion: Lecture 1 PPT

01. Explain visual and infrared imaging. [Slide-12]

02. Automated visual inspection[Slide-15]
03. Example of radar image [slide-16]
04. Example of MRI (Radio Band) [Slide-17]
05. Example: Ultrasound Imaging. [slide-18]
06. Fundamental Steps in DIP [Slide-19]
Fundamental steps in image processing:
1. Image acquisition: to acquire a digital image
2. Image preprocessing: to improve the image in ways that increase the chances for success of
the other processes.
3. Image segmentation: to partitions an input image into its constituent parts or objects.
4. Image representation: to convert the input data to a form suitable for computer processing.
5. Image description: to extract features that result in some quantitative information of interest
or features that are basic for differentiating one class of objects from another.
6. Image recognition: to assign a label to an object based on the information provided by its
descriptors.
7. Image interpretation: to assign meaning to an ensemble of recognized objects.
07. Light and EM Spectrum [slide -22]
08. Image Acquisition [slide-23]
09. Image Acquisition process [slide-26]
10. A simple Image formation model [Slide-27]
11. Some typical ranges of reflectance [Slide-29]
12. Image sampling and Quantization.[Slide-30]
13. Spatial and Intensity Resolution[Slide-38]
14. Image Interpolation [Slide-42] everything related to interpolation.
15. Basic relationship between pixels – Neighborhood, Adjacency, Connectivity [Slide-54]
16. Nosie, corrupted, noiseless image [Slide-81,82,83,84]
17. Set and logical operation [Slide-88,89]
18. Affine Transformation [Slide-97]
19. Intensity Assignment [Slide-98]
20. Image Registration [Slide-100]
21. Image Transformation[Slide-105]
Class-5, Lecture -3 PPT file
22. Piece wise – Linear Transformation [Slide-16]
23. Bit-Plane Slicing [Slide-20, but need 19,20 and 21]
24. Histogram Equalization [Slide-25,26]
Given Lecture @ Class
25. Spatial domain process explain? [slide-5,6,7,9,11]
26. What is intensity transformation?
27. What is intensity transformation function?
28. Explain intensity transformation function: image negative, log transformation, power-law
(Gamma) transformation.
29. What is Linear Transformation? What is piece wise linear transformation?
30. Explain Bit-plane slicing?
31. What is Histogram? What is histogram processing?
32. How many Histogram processing are there?
33. Explain Histogram equalization?
Extra question by sir
34. What is image sensor?
 35. What is Intensity luminous brightness?
36. Explain gamma ray processing transformation?

22.

Image Extraction:

How many feature vector you can get from 800x600 resolution?

20 50 10
60 50 70
53 65 71

Find out the LBP from the grid and the feature vector?

What is image extraction?

What is Object recognition?

What is LBP?

Based on assumption that the texture is constituted of the two complementary aspects of pattern and
strength. Transform image into image with labels

- 3x3 neighborhood used to label the pixels.

Histogram of the LBP image is then constructed.

The facial image is divided into local regions and LBP texture descriptors are extracted from each region
independently. The descriptors are then concatenated to form a global description of the face.