1. What is the primary goal of computer vision?
A) To create software that can process natural language
B) To enable machines to interpret and understand visual information from the world
C) To develop algorithms for data encryption
D) To build efficient databases for large-scale data storage
Answer: B) To enable machines to interpret and understand visual information from the world
2. Which of the following is a common application of computer vision?
A) Text classification
B) Image recognition
C) Speech synthesis
D) Data compression
Answer: B) Image recognition
3. In computer vision, what does the term “object detection” refer to?
A) Identifying the type of an object within an image
B) Finding and locating objects within an image
C) Converting text into speech
D) Analyzing the sentiment of a text
Answer: B) Finding and locating objects within an image
4. Which algorithm is commonly used for object detection?
A) Support Vector Machines (SVM)
B) Convolutional Neural Networks (CNNs)
C) K-Means Clustering
D) Principal Component Analysis (PCA)
Answer: B) Convolutional Neural Networks (CNNs)
5. What is the purpose of the “Convolutional Layer” in a CNN?
A) To perform downsampling
B) To extract features from the input image
C) To merge multiple features
D) To flatten the input data
Answer: B) To extract features from the input image
6. Which of the following techniques is used for image classification?
A) Histogram of Oriented Gradients (HOG)
B) Scale-Invariant Feature Transform (SIFT)
C) Support Vector Machines (SVM)
D) Optical Character Recognition (OCR)
Answer: C) Support Vector Machines (SVM)
7. What does “Segmentation” refer to in computer vision?
A) Identifying the main object in an image
B) Dividing an image into multiple segments or regions
C) Extracting features from an image
D) Classifying objects in an image
Answer: B) Dividing an image into multiple segments or regions
8. Which model architecture is known for its deep layers and is commonly used in computer vision tasks?
A) Decision Trees
B) Random Forest
C) Convolutional Neural Networks (CNNs)
D) K-Nearest Neighbors (KNN)
Answer: C) Convolutional Neural Networks (CNNs)
9. What is “Image Augmentation” used for?
A) To increase the size of the dataset by creating modified versions of images
B) To decrease the number of images in a dataset
C) To perform feature extraction
D) To merge multiple images into one
Answer: A) To increase the size of the dataset by creating modified versions of images
10. Which of the following is a common dataset used for training image classification models?
A) MNIST
B) IMDB
C) UCI Machine Learning Repository
D) Yelp Reviews
Answer: A) MNIST
11. In computer vision, what does “Feature Extraction” involve?
A) Converting images into numerical features that can be used for machine learning
B) Identifying the class of objects in an image
C) Segmenting an image into different regions
D) Detecting the presence of objects in an image
Answer: A) Converting images into numerical features that can be used for machine learning
12. Which technique is used to detect edges in an image?
A) Gaussian Blur
B) Sobel Operator
C) Histogram Equalization
D) Hough Transform
Answer: B) Sobel Operator
13. What is “Object Tracking” in computer vision?
A) Identifying objects in an image
B) Following the movement of an object across a series of frames
C) Classifying objects into categories
D) Segmenting objects within an image
Answer: B) Following the movement of an object across a series of frames
14. Which of the following is used for detecting and recognizing faces in images?
A) Hough Transform
B) Haar Cascades
C) K-Means Clustering
D) Linear Discriminant Analysis (LDA)
Answer: B) Haar Cascades
15. What does “Depth Perception” refer to in computer vision?
A) Estimating the distance of objects from the camera
B) Detecting the color of objects in an image
C) Identifying the type of objects in an image
D) Extracting features from an image
Answer: A) Estimating the distance of objects from the camera
16. What is “Semantic Segmentation”?
A) Classifying each pixel in an image into predefined categories
B) Detecting and locating objects within an image
C) Combining different segments of an image into one
D) Performing image classification
Answer: A) Classifying each pixel in an image into predefined categories
17. Which algorithm is used for object recognition and localization?
A) YOLO (You Only Look Once)
B) K-Means Clustering
C) Linear Regression
D) Principal Component Analysis (PCA)
Answer: A) YOLO (You Only Look Once)
18. What is the purpose of “Transfer Learning” in computer vision?
A) Using pre-trained models on new but similar tasks
B) Generating new images from existing ones
C) Extracting features from raw image data
D) Performing dimensionality reduction
Answer: A) Using pre-trained models on new but similar tasks
19. Which of the following techniques is used for image denoising?
A) Histogram Equalization
B) Gaussian Blur
C) Edge Detection
D) Image Segmentation
Answer: B) Gaussian Blur
20. In the context of CNNs, what is “Pooling” used for?
A) Reducing the spatial dimensions of an image
B) Increasing the resolution of an image
C) Normalizing the pixel values of an image
D) Enhancing the contrast of an image
Answer: A) Reducing the spatial dimensions of an image
21. What does “Optical Character Recognition (OCR)” do?
A) Converts images of text into machine-encoded text
B) Detects and tracks objects in video sequences
C) Segments an image into different regions
D) Classifies objects in an image
Answer: A) Converts images of text into machine-encoded text
22. Which of the following is used to correct lens distortion in images?
A) Calibration
B) Segmentation
C) Feature Matching
D) Depth Estimation
Answer: A) Calibration
23. What is “Histogram of Oriented Gradients (HOG)” used for?
A) Extracting features for object detection
B) Detecting edges in an image
C) Performing image segmentation
D) Reducing the dimensionality of data
Answer: A) Extracting features for object detection
24. What is the function of “Color Space Transformation” in image processing?
A) Converting an image from one color space to another
B) Extracting edges from an image
C) Enhancing image resolution
D) Normalizing image brightness
Answer: A) Converting an image from one color space to another
25. Which of the following methods is used for image registration?
A) Matching features between images
B) Performing object detection
C) Classifying objects within an image
D) Segmenting images into regions
Answer: A) Matching features between images
26. In computer vision, what is “Feature Matching”?
A) Comparing features between different images to find correspondences
B) Classifying the type of objects in an image
C) Tracking objects over time
D) Enhancing the quality of images
Answer: A) Comparing features between different images to find correspondences
27. What does “3D Reconstruction” involve?
A) Creating a three-dimensional model from two-dimensional images
B) Converting images into grayscale
C) Extracting features from an image
D) Segmenting objects within an image
Answer: A) Creating a three-dimensional model from two-dimensional images
28. Which of the following is a common technique for image segmentation?
A) K-Means Clustering
B) Hough Transform
C) Principal Component Analysis (PCA)
D) Gaussian Mixture Models (GMM)
Answer: A) K-Means Clustering
29. What is “Image Stitching”?
A) Combining multiple images to create a single panoramic image
B) Identifying objects in an image
C) Segmenting an image into different regions
D) Extracting features from an image
Answer: A) Combining multiple images to create a single panoramic image
30. Which model is designed for handling temporal sequences in computer vision?
A) Recurrent Neural Networks (RNNs)
B) Decision Trees
C) Support Vector Machines (SVMs)
D) Random Forests
Answer: A) Recurrent Neural Networks (RNNs)
31. What is the purpose of “Semantic Segmentation”?
A) Labeling each pixel in an image with a class
B) Detecting and locating objects in an image
C) Extracting features from images
D) Identifying the edges in an image
Answer: A) Labeling each pixel in an image with a class
32. What does “Image Super-Resolution” aim to achieve?
A) Increasing the resolution of an image
B) Reducing the resolution of an image
C) Enhancing image contrast
D) Performing image segmentation
Answer: A) Increasing the resolution of an image
More MCQS on AI Robot
- Basic Electronics and Mechanics MCQs
- Circuit Theory MCQs
- Sensors and Actuators MCQs
- Mechanics and Dynamics MCQs
- Programming MCQs
- Python MCQs
- C/C++ MCQs
- MATLAB MCQs
- Control Systems MCQs
- Introduction to Robotics MCQs
Intermediate Topics:
- Advanced Kinematics and Dynamics MCQs
- Advanced Control Systems MCQs
- Artificial Intelligence and Machine Learning MCQs
- Robotic Operating System (ROS) MCQs
- Embedded Systems MCQs
- Microcontrollers MCQs
- Real-Time Operating Systems (RTOS) MCQs
- Embedded C Programming MCQs
- Path Planning and Navigation MCQs