sewar 0.4.7

All image quality metrics you need in one package.

Sewar

Sewar is a python package for image quality assessment using different metrics. You can check documentation here.

Implemented metrics

• Mean Squared Error (MSE)
• Root Mean Squared Error (RMSE)
• Peak Signal-to-Noise Ratio (PSNR) [1]
• Structural Similarity Index (SSIM) [1]
• Universal Quality Image Index (UQI) [2]
• Multi-scale Structural Similarity Index (MS-SSIM) [3]
• Erreur Relative Globale Adimensionnelle de Synthèse (ERGAS) [4]
• Spatial Correlation Coefficient (SCC) [5]
• Relative Average Spectral Error (RASE) [6]
• Spectral Angle Mapper (SAM) [7]
• Spectral Distortion Index (D_lambda) [8]
• Spatial Distortion Index (D_S) [8]
• Quality with No Reference (QNR) [8]
• Visual Information Fidelity (VIF) [9]
• Block Sensitive - Peak Signal-to-Noise Ratio (PSNR-B) [10]

Todo

• Add command-line support for No-reference metrics

Installation

Just as simple as

pip install sewar

Running tests

pip install pytest pytest-cov
pytest --cov=sewar

Example usage

A simple example to use UQI. All metric functions expect numpy arrays in H x W x C format (height x width x channels):

>>> import numpy as np
>>> from PIL import Image
>>> from sewar.full_ref import uqi
>>> img1 = np.asarray(Image.open("image1.tif"))
>>> img2 = np.asarray(Image.open("image2.tif"))
>>> uqi(img1, img2)
0.8847521481522062

Example usage for command line interface

sewar [metric] [GT path] [P path] (any extra parameters)

An example to use SSIM

foo@bar:~$ sewar ssim images/ground_truth.tif images/deformed.tif -ws 13
ssim : 0.8947009811410856

Available metrics list

mse, rmse, psnr, rmse_sw, uqi, ssim, ergas, scc, rase, sam, msssim, vifp, psnrb 

Contributors

Special thanks to @sachinpuranik99 and @sunwj.

References

[1] "Image quality assessment: from error visibility to structural similarity." 2004)
[2] "A universal image quality index." (2002)
[3] "Multiscale structural similarity for image quality assessment." (2003)
[4] "Quality of high resolution synthesised images: Is there a simple criterion?." (2000)
[5] "A wavelet transform method to merge Landsat TM and SPOT panchromatic data." (1998)
[6] "Fusion of multispectral and panchromatic images using improved IHS and PCA mergers based on wavelet decomposition." (2004)
[7] "Discrimination among semi-arid landscape endmembers using the spectral angle mapper (SAM) algorithm." (1992)
[8] "Multispectral and panchromatic data fusion assessment without reference." (2008)
[9] "Image information and visual quality." (2006)
[10] "Quality Assessment of Deblocked Images" (2011)