A) The process of filtering and enhancing visual images. B) The field of study that enables computers to interpret and understand visual information from the real world. C) The study of how human vision works. D) The use of computer screens to display images.
A) Randomly distorting images. B) Changing the image dimensions. C) Enhancing image quality and reducing noise for better analysis. D) Blurring images for artistic effect.
A) Creating a mirror image of the original. B) Removing colors from an image. C) Combining multiple images into one. D) Dividing an image into meaningful regions or objects for analysis.
A) Mean Squared Error B) Accuracy C) R-squared D) F1 Score
A) Increasing the learning rate B) Using smaller batch sizes C) Adding more layers to the network D) Dropout regularization
A) Using pre-trained models and fine-tuning for a specific task. B) Transferring gradients during backpropagation. C) Transferring images between different devices. D) Transferring image pixels to a new image.
A) Increasing the number of parameters. B) Normalizing input values. C) Reducing the spatial dimensions of the input. D) Introducing non-linearity to the network.
A) ReLU (Rectified Linear Unit) B) Linear C) Tanh D) Sigmoid
A) Blurring images for privacy protection. B) Summarizing the performance of a classification model using true positive, false positive, true negative, and false negative values. C) Converting images to grayscale. D) Creating composite images.
A) Weather dataset B) Song lyrics dataset C) ImageNet D) Spam dataset
A) Smoothing pixel intensities. B) Converting images to black and white. C) Applying color filters to images. D) Identifying and delineating individual objects within a scene.
A) Detecting object edges. B) Normalizing image histograms. C) Blurring image boundaries. D) Mapping one image onto another image plane.
A) Gaussian blur B) Fourier transform C) Lucas-Kanade method D) Histogram equalization
A) VGGNet B) ResNet (Residual Network) C) AlexNet D) InceptionNet
A) Cross-Entropy Loss B) L1 Loss C) Mean Squared Error D) Binary Cross-Entropy Loss
A) Softmax B) Sigmoid C) Tanh D) ReLU
A) Adding noise to images B) Rotating images C) Increasing image resolution D) Non-local means denoising
A) K-Nearest Neighbors (KNN) B) Support Vector Machines (SVM) C) Principal Component Analysis (PCA) D) Convolutional Neural Networks (CNNs)
A) Segmentation of Image Features and Textures B) Semi-Integrated Face Tracking C) Scale-Invariant Feature Transform D) Selective Image Filtering Technique
A) Complex Neuron Network B) Controlled Neural Network C) Computerized Neuron Network D) Convolutional Neural Network
A) Pooling layer B) Convolutional layer C) Fully connected layer D) Activation layer
A) Image Cropping B) Transfer Learning C) Noise Injection D) PCA Dimensionality Reduction
A) Object detection B) Image segmentation C) Image classification D) Feature extraction |