Evaluation metrics to assess the similarity between two images.
Project description
Image Similarity measure
Implementation of four evaluation metrics to access the similarity between two images. The four metrics are as follows:
Peak signal-to-noise ratio (PSNR), Structural Similarity Index (SSIM), Information theoretic-based Statistic Similarity Measure (ISSM), and Feature-based similarity index (FSIM),
Instructions
The following step-by-step instructions will guide you through setting up the proper environment and libraries to be able to run these scripts.
Clone the repository
git clone https://github.com/up42/image-similarity-measures.git
cd image-similarity-measures
Then navigate to the folder via cd image-similarity-measures
.
Installing the required libraries
First create a new virtual environment called similarity-measures
, for example by using
virtualenvwrapper:
mkvirtualenv --python=$(which python3.7) similarity-measures
Activate the new environment:
workon similarity-measures
Install the necessary Python libraries via:
bash setup.sh
Parameters
--org_img_path : Path to the original image.
--pred_img_path : Path to the predicted or disordered image which is created from the original image.
--metric= : Name of the evaluation metric. Default set to be psnr. It can be one of the following: psnr, ssim, issm, fsim.
--mode : Image format. Default set to be "tif". can be one of the following: "tif", or "png", or "jpg".
--write_to_file : The final result will be written to a file. Set to False if you don't want a final file.
Evaluation
For doing the evaluation, you can easily run the following command:
python src/evaluate.py --org_img_path=path_to_first_img --pred_img_path=path_to_second_img --mode=tif
If you want to save the final result in a file you can add --write_to_file
at then end of above command.
Citation
Please use the following for citation purposes of this codebase:
Müller, M. U., Ekhtiari, N., Almeida, R. M., and Rieke, C.: SUPER-RESOLUTION OF MULTISPECTRAL SATELLITE IMAGES USING CONVOLUTIONAL NEURAL NETWORKS, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-1-2020, 33–40, https://doi.org/10.5194/isprs-annals-V-1-2020-33-2020, 2020.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for image-similarity-measures-0.0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7ef27d6afb6cf820b4f3eaea98818b26c8a963bc482d10dd5d26809d8830368b |
|
MD5 | 27e54d8bb0f20fcb3724a0a214fa6534 |
|
BLAKE2b-256 | a2a97264d35076a52ce7858c0e396ff02cee07fbf6b28f35ce18fdd1091bd7a0 |
Hashes for image_similarity_measures-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1a2421d55a4f4f062ff8acc475d9f6cfd7cd88727332cdf3fecb8dbf912f1860 |
|
MD5 | 76c7d20911370196454c07aace7335c8 |
|
BLAKE2b-256 | e93643289b41df7e8220cdd1e40662c7801694766a837c2c72d8e6658ca65101 |