CS-803-A Image Processing and Computer Vision - Jun 2025 Question Paper

Under each question, How to answer lists the points an answer should cover, outlined by CampusPrep from the syllabus. Check the details against your textbook.

1. 7 Marks
   aDiscuss the evolution and history of Computer Vision and Image Processing (CVIP). How have advancements in technology influenced the development of CVIP?
   How to answer

   • Define Computer Vision and Image Processing (CVIP)
   • Stages of evolution/history from early vision to deep learning era
   • Key technological advancements: hardware, sensors, algorithms, AI
   • Impact of advancements on CVIP development and applications
2. 7 Marks
   bExplain the steps involved in image conditioning, labeling, and grouping for image recognition.
   How to answer

   • Define image conditioning, labeling and grouping
   • Steps in conditioning: enhancement, filtering, normalization
   • Labeling: segmentation and region labeling
   • Grouping for recognition and role in image recognition pipeline
3. 7 Marks
   aDefine morphological image processing and describe the operations of dilation and erosion on binary images.
   How to answer

   • Define morphological image processing and structuring element
   • Definition and operation of dilation on binary images
   • Definition and operation of erosion on binary images
   • Effects, duality and illustrative example
4. 7 Marks
   bDescribe thinning and thickening operations. Provide an example of an application where these operations are useful.
   How to answer

   • Define thinning operation
   • Define thickening operation
   • Relation to hit-or-miss transform and sequential process
   • Example application e.g., skeletonization, fingerprint, OCR
5. 7 Marks
   aWhat are boundary and region descriptors in image processing? Explain their importance in image analysis.
   How to answer

   • Define boundary descriptors
   • Define region descriptors
   • Examples: chain code, Fourier, moments, texture, area
   • Importance in image analysis and recognition
6. 7 Marks
   bExplain the concept of segmentation in binary machine vision. Discuss the methods of thresholding and connected component labeling.
   How to answer

   • Define segmentation in binary machine vision
   • Concept and steps of thresholding
   • Concept and steps of connected component labeling
   • Comparison and use in object separation
7. 7 Marks
   aExplain spatial moments and gray-level moments in region analysis. How are these properties used in object recognition.
   How to answer

   • Define spatial moments in region analysis
   • Define gray-level moments
   • Formulas for moments, central and normalized moments
   • Use in object recognition: invariance, shape and intensity features
8. 7 Marks
   bExplain the distance relational approach in the context of image matching. Compare it with ordered structural matching.
   How to answer

   • Define distance relational approach for image matching
   • Define ordered structural matching
   • Comparison on basis of structure, order, invariance, complexity
   • Advantages/limitations of each
9. 7 Marks
   aDescribe the facet model recognition method. How is it applied to shape classification in images?
   How to answer

   • Define facet model recognition method
   • Steps: facet extraction, planar approximation, attributes
   • Application to shape classification
   • Advantages for 3D/range image shape description
10. 7 Marks
    bExplain projective geometry and its role in interpreting 3D objects from 2D images.
    How to answer

    • Define projective geometry: points, lines, vanishing points
    • Projection from 3D to 2D and loss of depth
    • Role in recovering 3D structure, pose and invariants
    • Applications in camera modeling and 3D interpretation
11. 7 Marks
    aDefine the following: i) Inverse perspective projection ii) Shape numbers used in boundary analysis
    How to answer

    • Define inverse perspective projection
    • Define shape numbers in boundary analysis
    • Formula/concept of shape number and order
    • Use in shape representation and matching
12. 7 Marks
    bIllustrate the back-tracking algorithm used in shape recognition. Provide a scenario where this algorithm is applied.
    How to answer

    • Outline back-tracking algorithm steps
    • Search tree, constraints and backtracking mechanism
    • Illustrative scenario e.g., shape/part matching
    • Advantages and complexity considerations
13. 7 Marks
    aExplain the Hough transform and discuss how it is used in detecting simple objects in images.
    How to answer

    • Principle of Hough transform and parameter space
    • Steps for line/circle detection and voting
    • Peak detection and handling noise
    • Use for detecting simple objects like lines, circles
14. 7 Marks
    bWhat is Principal Component Analysis (PCA)? Describe its role in feature extraction for object recognition.
    How to answer

    • Define PCA and its mathematical basis
    • Steps: covariance, eigenvectors, dimensionality reduction
    • Role in feature extraction for object recognition
    • Benefits: compact representation, noise reduction
15. 14 Marks
    Write short notes on (any two):

    1. a)Machine learning and neural networks in image shape recognition.
    2. b)Knowledge-Based Vision.
    3. c)Curve Fitting (Least-square fitting).
    How to answer

    • For chosen two topics: definition and key concepts
    • Main steps/methods and diagrams where relevant
    • Applications in image shape recognition/vision
    • Advantages and limitations