BCS616B – Computer Vision Solved Important Question with answers 22 Scheme
Module 1
1] Define Computer Vision. Why is it considered difficult or an inverse problem?
2] Describe various real-world industrial and consumer applications of computer vision
3] Write a short note on the history of Computer Vision.
4] Explain the concept of Photometric Image Formation. Discuss its important effects
5] Discuss about Bidirectional reflectance distribution function (BRDF)
6] Explain the steps involved in Image sensing pipeline (Computer Vision pipeline) with suitable diagrams.
7] Explain point operators used in image processing.
8] Explain the steps involved in computing Histogram equalization of a given image.
9] Explain about linear filtering and its types with examples.
10] Differentiate between industrial and consumer applications of Computer Vision with real-world examples.
11] Explain challenges in building vision systems with examples.
12] Compare human and computer vision systems.
13] Discuss the role of image processing in Computer Vision applications.
Note: Focus on the first 9 questions thoroughly as they are more important. Once done, move on to the remaining questions.
Module 2
1] Discuss neighborhood operators in Image processing:
i) Non-linear filtering(median filtering)
ii) Bilateral filtering
iii) Guided image filtering
2] Explain Binary Image processing
3] Describe Fourier transforms, Two-dimensional Fourier transforms( wiener filtering and Discrete cosine transform). Mention Applications.
4] Explain is interpolation (upsample) in the context of image processing, and why is it important when increasing the resolution of an image?
5] Explain why do we downsample images, and what role does decimation play in reducing image resolution effectively?
6] Mention some practical applications of image pyramids in computer vision and graphics.
7] Describe Wavelets. How are two-dimensional wavelets constructed?
8] Explain Geometric transformations and Parametric transformations
9] Explain Forward warping algorithm for transforming an image f(x) into an image g(x) through the parametric transform x= h(x)
10] Explain Inverse warping algorithm for creating an image g(x) from an image f(x) using the parametric transform x= h(x).
11] Explain Mesh-based warping.
Module 3
1] Explain the Image Degradation/Restoration Model.
2] Explain the different Noise Models used in digital image processing.
3] Describe periodic noise in images. How can we estimate noise parameters?
4] Explain spatial filtering for image restoration in the presence of noise. Describe different mean filters with equations.
5] What are Order-Statistic Filters? Explain various types of Order-Statistic Filters with equations.
6] Explain Adaptive Filters. Describe Adaptive Local Noise Reduction Filter and Adaptive Median Filter with necessary conditions and equations.
7] Explain how periodic noise can be removed using frequency domain filtering. Describe the notch filtering and optimum notch filtering techniques.
8] Explain the fundamentals of image segmentation. List and explain the conditions that a segmented image must satisfy.
9] Explain Point, Line, and Edge Detection using first and second-order derivatives.
10] Explain detection of isolated points, lines, and edges in an image.
11] Explain Segmentation by Region Growing and Region Splitting & Merging.
Module 4
1] Explain Color Fundamentals.
2] Explain the purpose and types of color models used in digital image processing.
3] Explain Pseudocolor Image Processing. Describe intensity slicing and color coding with a neat diagram.
4] Explain the basics of full-color image processing. How are color images represented and processed? Also explain component-wise vs vector-based processing with examples.
5] Explain the concept of Color Transformations in digital image processing. Discuss the formulation, types of transformations (like color complements, color slicing), and their applications.
6] Explain Color Image Smoothing and Sharpening. How are these operations extended from grayscale to full-color images?
7] Explain the role of color in image segmentation and edge detection.
8] Write a short note on Noise in Color Images.
Module 5
1] Write short notes on the Preliminaries of Mathematical Morphology.
2] Explain Erosion and Dilation in Mathematical Morphology with equations and examples.
3] Explain Morphological Opening and Closing with definitions, equations, and examples.
4] Explain the Hit-or-Miss Transform (HMT) in Morphological Image Processing.
5] Explain boundary preprocessing in image processing. Describe the Moore boundary following algorithm with steps and illustrations.
6] Explain Freeman Chain Codes. How are chain codes generated and normalized? Discuss the role of resampling in boundary representation.
7] Explain Pattern Vectors and Structural Patterns in the context of image pattern classification. Give suitable examples.
8] Explain the concept of Pattern Classification by Prototype Matching. Describe the Minimum-Distance Classifier.
