Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

CSC171 > Computer Vision > Flashcards

Computer Vision Flashcards

1
Q

What is computer vision?

A

A field of artificial intelligence that enables computers to interpret and understand visual information from the world, such as images and videos.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

How do computers see images?

A

Images are represented as a grid of pixels, with each pixel having a numerical value corresponding to its color or intensity.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is a grayscale image?

A

An image where each pixel has a single value representing its light or dark intensity, typically ranging from 0 (black) to 255 (white).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is pixel analysis in computer vision?

A

The process of breaking down an image into tiny dots called pixels, each with a specific color and brightness value.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is feature extraction?

A

The analysis of an image to identify patterns, shapes, edges, and other features.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is the purpose of pattern recognition in computer vision?

A

To compare identified features to known patterns or objects that the computer has been trained to recognize.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What role does machine learning play in computer vision?

A

It uses statistical and computational methods to train models on large image datasets, allowing computers to understand visual data by learning from patterns.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is a Convolutional Neural Network (CNN)?

A

A type of artificial neural network designed to process and recognize patterns in images through multiple layers.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the significance of the year 1957 in computer vision?

A

The first known digital image scanner, the ‘Cyclograph,’ was developed, transforming images into grids of numbers.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Who are David Hubel and Torsten Wiesel?

A

Researchers whose experiments on the visual cortex of cats revealed how the brain processes visual information.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is Optical Character Recognition (OCR)?

A

A technology that solves the problem of recognizing text printed in any font or typeface.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is image classification?

A

The ability to classify an image into a specific category, such as identifying a dog or a person’s face.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is object detection?

A

The process of identifying and locating objects within an image or video.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What does image segmentation involve?

A

Dividing an image into distinct segments, each representing a specific object or region.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is semantic segmentation?

A

Classifying each pixel in an image into a specific class or category without distinguishing between different instances.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is instance segmentation?

A

Identifying and distinguishing individual objects within an image, providing precise masks for each object.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What is panoptic segmentation?

A

A hybrid method that combines both semantic and instance segmentation.

18
Q

What is keypoint detection?

A

Identifying specific, important points in an image to understand shapes, poses, or movements.

19
Q

What is image captioning?

A

Combining computer vision and natural language processing to generate descriptive text for an image.

20
Q

What are some applications of computer vision?

A
  • Self-driving cars
  • Medical imaging
  • Google Translate
  • Optical Character Recognition
  • Facial Recognition
  • Machine inspection / Surveillance
  • Fingerprint recognition and biometrics
  • QR Code Scanning
  • 3D model building
21
Q

What is a major challenge in computer vision related to data?

A

Training deep learning models requires large amounts of labeled data, which can be time-consuming and expensive to collect.

22
Q

What is domain adaptation in computer vision?

A

Techniques to improve model performance on data from a different domain, such as different lighting or camera angles.

23
Q

What programming language is often recommended for computer vision projects?

A

Python, due to its ease of use, versatility, and extensive libraries for computer vision applications.

24
Q

What is the ImageNet dataset?

A

A large-scale dataset with millions of labeled images across thousands of categories used for object recognition.

25
Q

What is OpenCV?

A

A library for image processing and traditional computer vision tasks.

26
Q

True or False: Convolutional Neural Networks (CNNs) are used in video applications.

A

False. CNNs are primarily used for image understanding; Recurrent Neural Networks (RNNs) are used for video applications.

27
Q

What is the benefit of using machine learning in computer vision?

A

Allows computers to learn from patterns in data, improving their ability to classify and detect objects without explicit programming.

28
Q

Fill in the blank: The first known digital image scanner was developed in _____ 1957.

A

the year

29
Q

What is the purpose of Google Open Image?

A

A massive dataset with millions of images annotated for object detection, segmentation, and relationships.

Supports a wide range of vision tasks.

30
Q

What is OpenCV used for?

A

Image processing and traditional computer vision tasks.

A widely-used library in the field.

31
Q

Name two popular deep learning frameworks for training and deploying models.

A
  • TensorFlow
  • PyTorch

These frameworks are commonly used for various machine learning applications.

32
Q

What is Keras?

A

A high-level neural network API that works well with TensorFlow.

Often used for prototyping.

33
Q

What is Scikit-image?

A

A Python library for image processing with tools for filtering, segmentation, and feature extraction.

Useful for various image analysis tasks.

34
Q

What are NumPy and Pandas used for?

A

Data manipulation and preprocessing.

Essential libraries in Python for data science.

35
Q

What libraries are used for data visualization and plotting results?

A
  • Matplotlib
  • Seaborn

These libraries help in visualizing data and results effectively.

36
Q

What is PyTorch Hub?

A

A library of pretrained models for PyTorch.

Provides easy access to state-of-the-art models for various tasks.

37
Q

What is TensorFlow Hub?

A

A repository of pretrained machine learning models for TensorFlow.

Models can be easily reused and fine-tuned for various tasks.

38
Q

What is YOLO known for?

A

Real-time object detection.

Can detect multiple objects in a single pass.

39
Q

What are the versions of YOLO mentioned?

A
  • YOLOv6
  • YOLOv7

Popular for applications requiring fast, accurate detection.

40
Q

What is ResNet used for?

A

Image classification tasks.

Notable for its deep architecture and residual connections.

41
Q

What is MASK RCNN?

A

A deep learning model for object instance segmentation.

Provides detailed masks for each instance of objects in an image.

42
Q

True or False: MASK RCNN is particularly popular in fields like medical imaging.

A

True

It is also used in applications requiring precise object localization.

CSC171 (2 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions