A) The field of study that enables computers to interpret and understand visual information from the real world.
B) The use of computer screens to display images.
C) The study of how human vision works.
D) The process of filtering and enhancing visual images.

A) Randomly distorting images.
B) Enhancing image quality and reducing noise for better analysis.
C) Blurring images for artistic effect.
D) Changing the image dimensions.

A) Combining multiple images into one.
B) Creating a mirror image of the original.
C) Removing colors from an image.
D) Dividing an image into meaningful regions or objects for analysis.

A) R-squared
B) Mean Squared Error
C) Accuracy
D) F1 Score

A) Using smaller batch sizes
B) Increasing the learning rate
C) Adding more layers to the network
D) Dropout regularization

A) Using pre-trained models and fine-tuning for a specific task.
B) Transferring image pixels to a new image.
C) Transferring images between different devices.
D) Transferring gradients during backpropagation.

A) Reducing the spatial dimensions of the input.
B) Normalizing input values.
C) Introducing non-linearity to the network.
D) Increasing the number of parameters.

A) Tanh
B) ReLU (Rectified Linear Unit)
C) Linear
D) Sigmoid

A) Creating composite images.
B) Converting images to grayscale.
C) Summarizing the performance of a classification model using true positive, false positive, true negative, and false negative values.
D) Blurring images for privacy protection.

A) Selective Image Filtering Technique
B) Segmentation of Image Features and Textures
C) Semi-Integrated Face Tracking
D) Scale-Invariant Feature Transform

A) Spam dataset
B) ImageNet
C) Song lyrics dataset
D) Weather dataset

A) Computerized Neuron Network
B) Complex Neuron Network
C) Controlled Neural Network
D) Convolutional Neural Network

A) Softmax
B) ReLU
C) Tanh
D) Sigmoid

A) Feature extraction
B) Image classification
C) Object detection
D) Image segmentation

A) Activation layer
B) Fully connected layer
C) Convolutional layer
D) Pooling layer

A) Mean Squared Error
B) L1 Loss
C) Cross-Entropy Loss
D) Binary Cross-Entropy Loss

A) Applying color filters to images.
B) Smoothing pixel intensities.
C) Converting images to black and white.
D) Identifying and delineating individual objects within a scene.

A) Adding noise to images
B) Increasing image resolution
C) Non-local means denoising
D) Rotating images

A) K-Nearest Neighbors (KNN)
B) Convolutional Neural Networks (CNNs)
C) Support Vector Machines (SVM)
D) Principal Component Analysis (PCA)

A) Normalizing image histograms.
B) Mapping one image onto another image plane.
C) Blurring image boundaries.
D) Detecting object edges.

A) InceptionNet
B) AlexNet
C) ResNet (Residual Network)
D) VGGNet

A) Noise Injection
B) Transfer Learning
C) Image Cropping
D) PCA Dimensionality Reduction

A) Fourier transform
B) Histogram equalization
C) Lucas-Kanade method
D) Gaussian blur