Scribd
Upload
23 views5 pages

Image Processing and Computer Vision Q&A

The document is a comprehensive question bank for a course on Image Formation and Processing, covering five units: Introduction to Image Formation, Feature Detection and Segmentation, Feature-Based Alignment and Motion Estimation, 3D Reconstruction, and Image-Based Rendering and Recognition. Each unit contains questions categorized into three parts: Part A (2 Marks), Part B (13 Marks), and Part C (15 Marks), addressing key concepts, techniques, and applications in the field. The questions range from definitions and explanations to detailed discussions of various methods and models used in image processing and computer vision.

Uploaded by

karthikbe197
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
23 views5 pages

Image Processing and Computer Vision Q&A

The document is a comprehensive question bank for a course on Image Formation and Processing, covering five units: Introduction to Image Formation, Feature Detection and Segmentation, Feature-Based Alignment and Motion Estimation, 3D Reconstruction, and Image-Based Rendering and Recognition. Each unit contains questions categorized into three parts: Part A (2 Marks), Part B (13 Marks), and Part C (15 Marks), addressing key concepts, techniques, and applications in the field. The questions range from definitions and explanations to detailed discussions of various methods and models used in image processing and computer vision.

Uploaded by

karthikbe197
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

NAME: P.

KARTHIKA /AP/ DEPT: AI&DS

QUESTION BANK

UNIT I : INTRODUCTION TO IMAGE FORMATION AND PROCESSING

Part – A (2 Marks)

1. Define Computer Vision.


2. What are geometric primitives?
3. Define photometric image formation.
4. What is a point operator?
5. What is linear filtering?
6. Define convolution.
7. What is Fourier Transform?
8. What is image pyramid?
9. Define wavelets.
10. What is global optimization?

Part – B (13 Marks)

1. Explain the digital camera model with neat diagram.


2. Describe photometric image formation in detail.
3. Explain point operators and their applications.
4. Discuss linear filtering and neighborhood operators.
5. Explain Fourier transform and its role in image processing.
6. Describe image pyramids and wavelets with examples.
7. Explain geometric transformations used in computer vision.

Part – C (15 Marks)

1. Explain the complete image formation pipeline from scene to digital image.
2. Discuss spatial domain vs frequency domain processing in detail.
3. Explain global optimization techniques used in computer vision.
UNIT II : FEATURE DETECTION, MATCHING AND SEGMENTATION

Part – A (2 Marks)

1. What is feature detection?


2. Define corner point.
3. What is edge detection?
4. Define segmentation.
5. What are active contours?
6. What is mean shift?
7. Define graph cut.
8. What is normalized cut?
9. What is region splitting?
10. What is mode finding?

Part – B (13 Marks)

1. Explain point and patch based feature detection.


2. Describe edge detection techniques.
3. Explain line detection methods.
4. Discuss image segmentation approaches.
5. Explain active contour models.
6. Describe split and merge segmentation.
7. Explain mean shift algorithm.

Part – C (15 Marks)

1. Explain graph cuts and energy-based segmentation methods.


2. Discuss normalized cuts for image segmentation with example.
3. Compare feature detection and segmentation techniques.
UNIT III: FEATURE-BASED ALIGNMENT & MOTION ESTIMATION

Part – A (2 Marks)

1. Define feature-based alignment.


2. What is pose estimation?
3. Define camera calibration.
4. What is triangulation?
5. What is structure from motion?
6. Define bundle adjustment.
7. What is optical flow?
8. Define parametric motion.
9. What is layered motion?
10. What is translational alignment?

Part – B (13 Marks)

1. Explain 2D feature-based alignment.


2. Describe 3D feature-based alignment.
3. Explain camera intrinsic calibration.
4. Discuss triangulation process.
5. Explain two-frame structure from motion.
6. Describe optical flow estimation.
7. Explain parametric motion models.

Part – C (15 Marks)

1. Explain factorization and bundle adjustment in motion estimation.


2. Discuss spline-based and layered motion models.
3. Explain optical flow and its applications.
UNIT IV: 3D RECONSTRUCTION

Part – A (2 Marks)

1. What is 3D reconstruction?
2. Define shape from X.
3. What is active range finding?
4. Define surface representation.
5. What is point-based representation?
6. Define volumetric representation.
7. What is model-based reconstruction?
8. What is texture mapping?
9. Define albedo.
10. What is depth map?

Part – B (13 Marks)

1. Explain shape from shading.


2. Describe active range finding techniques.
3. Explain surface representations.
4. Discuss point-based and volumetric representations.
5. Explain model-based reconstruction.
6. Describe texture map recovery.

Part – C (15 Marks)

1. Explain various 3D reconstruction techniques in detail.


2. Discuss volumetric representation and its advantages.
3. Explain texture and albedo recovery methods.
UNIT V: IMAGE-BASED RENDERING AND RECOGNITION

Part – A (2 Marks)

1. What is image-based rendering?


2. Define view interpolation.
3. What is light field?
4. Define Lumigraph.
5. What is object detection?
6. Define face recognition.
7. What is instance recognition?
8. What is category recognition?
9. What is scene understanding?
10. What are recognition databases?

Part – B (13 Marks)

1. Explain view interpolation techniques.


2. Describe layered depth images.
3. Explain light fields and Lumigraphs.
4. Discuss video-based rendering.
5. Explain object detection methods.
6. Describe face recognition systems.
7. Explain instance and category recognition.

Part – C (15 Marks)

1. Explain image-based rendering techniques in detail.


2. Discuss object, face, and scene recognition systems.
3. Explain recognition databases and performance evaluation.

You might also like