0% found this document useful (0 votes)
42 views3 pages

Ip CV QB 1

image processng and computer vision question bank
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
42 views3 pages

Ip CV QB 1

image processng and computer vision question bank
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

IP CV QB

1. Apply your understanding of image sampling and quantization to a practical scenario.


Suppose you are tasked with digitizing an analog medical X-ray image. Describe the steps
you would take to sample and quantize the image properly.
2. Given a scenario where you need to design a digital image processing system for
autonomous vehicles, apply your knowledge of the components of an image processing
system.
3. Apply your knowledge of visual perception to improve the design of an image processing
algorithm for enhancing low-contrast images.
4. Apply the principles of linear and nonlinear operations to enhance an image that suffers
from Gaussian noise and impulse noise. Describe the specific steps and techniques you
would use to address each type of noise.
5. You are tasked with designing an image acquisition system for a satellite imaging project.
Apply your knowledge of image sensing and acquisition to recommend the types of sensors
and methods for digitizing the captured images. Explain your choices and how they meet
the requirements of high-resolution satellite imagery.
6. Apply the concepts of pixel connectivity and distance measures to design an algorithm for
object detection in a binary image. Outline the steps your algorithm would take to identify
and label connected components.
7. Apply the concepts of histogram processing to enhance the contrast of a low-contrast image.
Describe the steps involved in histogram equalization and histogram matching.
8. You are given an image suffering from motion blur and Gaussian noise. Apply your
understanding of image restoration techniques to design a process for restoring the image.
9. Describe how you would use contrast stretching and log transformations in this scenario,
and explain the effect of each transformation on the image's histogram.
10. Given a high-resolution image suffering from periodic noise, apply your knowledge of
frequency domain techniques to design a process for removing this noise.
11. Apply your understanding of color models to convert an image from the RGB color model
to the HSI color model. Describe the steps involved in this conversion process and explain
the advantages of using the HSI color model for certain image processing tasks.
12. Using the concept of image segmentation, propose a method for segmenting objects of
interest in a satellite image. Describe the step-by-step process, including preprocessing
steps and the selection of segmentation techniques. Justify your choices and discuss
potential challenges that may arise during the segmentation process.
13. Explain the role of opening and closing operations in morphological image processing.
Illustrate how these operations can be used to remove noise and fill gaps in binary images.
Provide a practical example to demonstrate the effects of opening and closing on the
structure of objects in an image.
14. Propose an algorithm using the Sobel operator for edge detection in grayscale images.
Outline the steps and discuss potential optimizations for real-time applications.
15. Compare the effects of different structuring elements on morphological operations like
erosion and dilation. Provide visual examples and discuss their impact on binary image
outcomes.
16. Explain the concept of super pixels in image segmentation. Describe a popular algorithm
like SLIC and its advantages over pixel-based approaches with an example.
17. Describe the process of converting a 2D image to a 3D model using projective geometry.
Outline the steps involved and discuss how homography is utilized in this context.
18. Compare the functionalities and applications of a monochromatic camera and a color
camera in computer vision tasks. Provide examples of scenarios where each type of camera
would be preferred.
19. Using Marr’s theory of vision, describe a step-by-step approach for edge detection in a
given image. Explain how this theory helps in understanding the 3D structure of objects.
20. Analyze the role of points and hyperplanes in projective space for 3D vision tasks. Compare
how these concepts are applied in homography and the single perspective camera model.
21. Explain how predictive compression methods are used in image data compression. Describe
a specific example of such a method and how it reduces image size while maintaining
quality.
22. Compare JPEG and MPEG image compression techniques. Discuss their coding methods,
applications, and the trade-offs between compression efficiency and image quality.
23. Describe the process of optical flow computation in motion analysis. Explain how optical
flow is utilized in detecting specific motion patterns within a video sequence.
24. Discuss the advantages and disadvantages of hierarchical and progressive compression
methods in image data compression. Provide examples of scenarios where each method
would be most suitable.
25. Examine the differential motion analysis methods used in motion analysis. Compare and
contrast block-based and pixel-based approaches, discussing their respective strengths and
weaknesses.
26. Explain the concept of video tracking and its importance in computer vision. Describe the
process of background modeling and how it contributes to robust object tracking in videos.

• Utilize illumination and reflectance components to generate digital images.

• Construct a digitized image using sampling and quantization.

• Explain the fundamental steps in Digital Image Processing. Solve to test for Linearity,
Considering any two images A and B matrix.
• Explain components of an Image Processing System with a neat diagram.
• Plot the curve for basic intensity transformation. Explain the following basic Intensity
transformation:
• Power-law (Gamma) transformations.
• Bit plane Slicing
• Explain smoothing spatial filters with an example for each.
• Suppose that a 3-bit image (L=8) of size 64 X 64 pixels (MN=4096) has the intensity
distribution 790, 1023, 850, 656, 329, 245, 122, 81 where the intensity levels are
integers in the range [0, L-1] = [0, 7]. Apply histogram equalization transformation
function to obtain values of equalized histogram.
• Explain the algorithm for Histogram and Histogram Matching. Apply this concept
using suitable example

• Solve the Discrete Fourier Transform (DFT) of Two Variables and explain the
properties of 2D DFT
• Model the Image Degradation / Restoration Process with the help of neat diagram and
equations.
• Construct the RGB Color Model with the help of mathematical
• Construct the CMY Color Model with the help of mathematical expressions
• Experiment with the following color image conversion process using suitable
expressions and sketches
• RGB to HSI and
• HSI to RGB
• Experiment with the Erosion and Dilation concept using mathematical model
• Model the following concept of with the help of suitable mathematical expressions
• Opening and Closing
• Hit – or - Miss Transform
• Apply the concept of Edge detection and various types of edge detection process with
suitable expressions

• Explain the Image representation and image analysis tasks with the help of a neat flow
diagram
• Explain the 3D vision tasks using the concept of Marr’s theory

• Construct the Analog CCD camera and Digital CCD camera with the help of a neat
diagram
• Identify the basics of projective geometry, Points and hyperplanes in projective space
with the help of expressions
• What is compression? Model the Hierarchical and Progressive Compression Methods in
detail
• Model the Schematic of JPEG–2000 data compression
• Identify the detection of specific motion pattern with the help of mathematical
expressions
• Explain how Kernel-based object tracking works in video tracking process also Model
the algorithm of Kernel-based object tracking

You might also like