1. . Computer Vision (CV) is:
(A) Backup only
(B) Encrypting images only
(C) Compressing datasets only
(D) A field of AI that enables computers to interpret and process visual data such as images and videos
2. . Image preprocessing in computer vision includes:
(A) Resizing, normalization, noise reduction, and color space conversion
(B) Encrypting images
(C) Compressing images
(D) Backup only
3. . Convolutional Neural Networks (CNNs) are widely used in CV because they:
(A) Automatically detect and learn spatial hierarchies of features
(B) Encrypt image features
(C) Compress image features
(D) Backup only
4. . The convolutional layer in CNN performs:
(A) Backup only
(B) Encrypting layers
(C) Compressing layers
(D) Feature extraction using learnable filters or kernels
5. . Pooling layers in CNN help to:
(A) Compress features
(B) Encrypt pooled data
(C) Reduce spatial dimensions and computational complexity while retaining important features
(D) Backup only
6. . Fully connected layers in CNN are used for:
(A) Combining extracted features to make predictions
(B) Encrypting layers
(C) Compressing layers
(D) Backup only
7. . Image classification assigns:
(A) Encrypting labels
(B) A label to an input image from a predefined set of classes
(C) Compressing labels
(D) Backup only
8. . Object detection involves:
(A) Backup only
(B) Encrypting objects
(C) Compressing objects
(D) Identifying and locating objects within an image using bounding boxes
9. . Common object detection algorithms include:
(A) YOLO, Faster R-CNN, SSD
(B) Encrypting algorithms
(C) Compressing algorithms
(D) Backup only
10. . Semantic segmentation assigns:
(A) Compressing pixels
(B) Encrypting pixels
(C) A class label to each pixel in the image
(D) Backup only
11. . Instance segmentation differs from semantic segmentation because it:
(A) Identifies each object instance separately in addition to class labels
(B) Encrypts instances
(C) Compresses instances
(D) Backup only
12. . Edge detection in computer vision is used to:
(A) Compress edges
(B) Encrypt edges
(C) Identify boundaries of objects within an image
(D) Backup only
13. . Optical Character Recognition (OCR) is:
(A) Encrypting text
(B) Converting printed or handwritten text in images into machine-readable text
(C) Compressing text
(D) Backup only
14. . Image augmentation is performed to:
(A) Increase dataset size and improve model generalization by applying transformations like rotation, flipping, and scaling
(B) Encrypt images
(C) Compress images
(D) Backup only
15. . Feature maps in CNN represent:
(A) Encrypting features
(B) The output of convolutional layers highlighting important features
(C) Compressing feature maps
(D) Backup only
16. . Transfer learning in CV involves:
(A) Encrypting models
(B) Using pre-trained models on new tasks to reduce training time and improve performance
(C) Compressing models
(D) Backup only
17. . Common pre-trained models in CV include:
(A) Compressing models
(B) Encrypting models
(C) VGGNet, ResNet, Inception, MobileNet
(D) Backup only
18. . Convolution in CV helps to:
(A) Backup only
(B) Encrypt convolutions
(C) Compress features
(D) Detect features such as edges, textures, and patterns in images
19. . Object tracking is:
(A) Encrypting objects
(B) Following the movement of objects across video frames
(C) Compressing objects
(D) Backup only
20. . The main purpose of computer vision is to:
(A) Enable machines to understand, interpret, and make decisions based on visual information
(B) Encrypt all images
(C) Compress datasets
(D) Backup only