Scribd
Upload
55 views2 pages

Ai For Computer Vision PYQ

Uploaded by

CG
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
55 views2 pages

Ai For Computer Vision PYQ

Uploaded by

CG
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
You are on page 1/ 2

Unit I: Introduction to Image Formation and Processing

1. Computer Vision:

 What is computer vision, and how does it differ from traditional image processing?

 Explain the role of computer vision in image processing.

2. Photometric Image Formation:

 Define image enhancement and discuss its importance in image processing with
examples.

3. Linear Filtering:

 Describe the role of convolution in image filtering and the process of applying a filter
(kernel) to an image.

4. Fourier Transforms:

 Discuss techniques in the frequency domain for image enhancement with examples.

 Differentiate between spatial and frequency domain image enhancement.

5. Geometric Transformations:

 Explain data type conversion in image processing and its impact on image quality
and storage.

 Define image transformation and its significance in digital image processing.

6. Photogrammetric Processing:

 Briefly outline the process of photogrammetric processing from 2D to 3D.

Unit II: Feature Detection, Matching, and Segmentation

1. Edges and Lines:

 Explain the Canny Edge detection algorithm, including key steps and the significance
of its parameters.

 Describe line detection in images and the masks used for this purpose.

2. Segmentation:

 Define image segmentation and its relationship to image recognition. Outline the
steps for segmenting objects within an image.

 Discuss segmentation techniques that focus on region finding.

 Explain erosion and dilation operations in binary image processing and their
applications in noise removal and object size modification.

3. Active Contours and Energy-based Methods:

 How do you measure the properties of regions in a labeled image?


4. Thresholding:

 Define thresholding in binary image processing and methods for selecting an optimal
threshold value.

 Discuss the uses and limitations of thresholding.

Unit III: Feature-based Alignment & Motion Estimation

1. Pose Estimation and Motion Estimation:

 Describe the conversion process from the RGB color model to the HIS color model.

 Explain the inverse perspective projection algorithm.

2. Optical Flow and Layered Motion:

 Discuss the application of neural networks in image shape recognition.

Unit IV: 3D Reconstruction

1. Surface Representations and Model-based Reconstruction:

 Explain boundary descriptors in detail, including a diagram.

2. Recovering Texture Maps and Albedos:

 Discuss the significance of shape recognition in image processing.

Unit V: Image-based Rendering and Recognition

1. Object Detection and Recognition:

 Provide an algorithm for connected component analysis on a binary image and


explain the steps involved.

 Write notes on feature extraction.

 Discuss the role of neural networks in image shape recognition.

2. Vehicle Vision System:

 Explain how road signs are identified within a vehicle vision system.

You might also like