Scribd
Upload
56 views2 pages

Midterm Sample

This document outlines fundamental and intermediate questions about computer vision topics including image processing, features, classification, detection, segmentation and tracking. It asks about color representations, local vs global features, extraction methods, evaluation metrics and the role of deep learning in computer vision tasks.

Uploaded by

Thảo Lưu
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
56 views2 pages

Midterm Sample

This document outlines fundamental and intermediate questions about computer vision topics including image processing, features, classification, detection, segmentation and tracking. It asks about color representations, local vs global features, extraction methods, evaluation metrics and the role of deep learning in computer vision tasks.

Uploaded by

Thảo Lưu
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/ 2

A.

Fundamental questions:
1. Define computer vision and outline its primary goals. How does computer vision relate to other
fields such as image processing and machine learning?
2. What is image processing, and why is it a crucial step in computer vision tasks? Provide two
examples of basic image processing operations and their purposes.
3. Explain the difference between RGB and grayscale color representations in images. When might
you choose one representation over the other in a computer vision application?
4. Define image features and provide an example of a common feature used in computer vision.
How are these features helpful in tasks such as object recognition?
5. Explain the difference between image classification and object detection.

B. Intermediate questions:
6. Define local features in the context of computer vision. How are local features different from
global features, and why are they important for tasks like object matching?
7. Explain the concept of object matching in computer vision. How do local features contribute to
the process of matching objects in images?
8. Describe two common methods for extracting local features from an image. How do these
methods capture distinctive information about key points in the image?
9. Discuss two techniques used for matching local features between images. Provide a brief
comparison of their strengths and weaknesses.
10. Identify and explain three key components involved in image object recognition. Provide a brief
description of the role each component plays in the overall recognition process.
11. Describe two common methods for feature extraction in image object recognition. How do
these methods help in capturing important information about objects in an image?
12. Briefly explain how deep learning techniques, particularly convolutional neural networks (CNNs),
are employed in image object recognition. What advantages do CNNs offer for this task?
13. Discuss at least two evaluation metrics commonly used to assess the performance of image
object recognition algorithms. How do precision, recall, and accuracy contribute to the
evaluation process?
14. Define image object detection in computer vision. How does object detection differ from object
recognition, and what are the main challenges in detecting objects in images?
15. Briefly explain two common techniques used in image object detection. Provide an example
scenario where each technique might be particularly useful.
16. Describe the concept of bounding boxes in the context of object detection. How are bounding
boxes utilized for object localization, and why is this information important?
17. Explain how deep learning, specifically convolutional neural networks (CNNs), has revolutionized
object detection. What advantages do CNNs offer over traditional methods for object
detection?
18. Identify and explain two commonly used evaluation metrics for assessing the performance of
object detection algorithms. How do metrics like precision, recall, and mean average precision
contribute to the evaluation process?
19. Explain the importance of semantic segmentation in computer vision applications. Provide an
example scenario where semantic segmentation is crucial for understanding the content of an
image.
20. Describe how instance segmentation distinguishes between multiple objects of the same class in
an image. What information does instance segmentation provide beyond semantic
segmentation?
21. Describe two common methods used in object tracking. Provide a brief explanation of the
strengths and limitations of each method.

You might also like