Discover published sets by community

Mean Squared Error (MSE) is the average of the squared differences between the original and compressed images. Used to quantify the image quality degradation.

Gradient Magnitude Similarity Deviation (GMSD) utilizes the gradient magnitude of images to assess the quality of an image by capturing image detail and structure. Used for evaluation when edge information is crucial.

Mean Absolute Deviation (MAD) is a measure of the average deviation of data points from their mean. Used to summarize the spread or variability in a data set.

Universal Image Quality Index (UIQI) assesses the quality of an image by measuring three factors: loss of correlation, luminance distortion, and contrast distortion. Used for quality assessment in image processing.

Mean Absolute Error (MAE) measures the average magnitude of the errors in a set of predictions, without considering their direction. Used to summarize the errors in a predictive model.

Structural Similarity Index (SSIM) compares local patterns of pixel intensities of predicted and reference images. Used for measuring the perceived quality of digital images.

Feature Similarity Index (FSIM) measures the similarity between two images based on low-level features. Used to compare the quality of images with reference to structural details.

Peak Signal-to-Noise Ratio (PSNR) measures the peak error between the original and a compressed image. Used to assess the quality of reconstructed images.

Visual Information Fidelity (VIF) metric quantifies how much visual information is shared between a reference and a distorted image. Used when visual fidelity is the main concern.