Software and Data

Software and Data

As a result of our research and development various software have been developed.  We have decided to make these available to the research community free of charge. If you download and use the content on this page in your research, we kindly ask that you reference this website and our papers listed below.

ICC3D - A color management application

ICC3D (Interactive Color Correction in 3 Dimensions) is an application designed to help people understand and meet the challenges of color and image reproduction, especially gamut mapping.

The main application is temporarily available from here. The source code can be found here. For questions regarding the application, please contact colourlab@hig.no.  

Citation : Farup, Ivar; Hardeberg, Jon Yngve; Bakke, Arne Magnus; Kopperud, Stale & Rindal, Anders. Visualization and Interactive Manipulation of Color Gamuts. Tenth Color Imaging Conference: Color Science and Engineering Systems, Technologies, Applications. ISBN / ISSN: 0-89208-241-0, Pages 250-255, Scottsdale, Arizona, USA, Nov, 2002. [PDF]

Colourlab Image Database: Image Quality (CID:IQ)

The Colourlab Image Database: Image Quality (CID:IQ) contain 23 pictorial images are selected as the reference images with six different distortions over 5 levels. The distortions are JPEG compression, JPEG2000 compression, Poisson noise, blurring, and two gamut mapping algorithms. CID:IQ contains the subjective scores of 17 observers. The database is available for download.

Citation : Xinwei Liu, Marius Pedersen, and Jon Yngve Hardeberg,  "CID:IQ - A New Image Quality Database," To be presented at the International Conference on Image and Signal Processing 2014 (ICISP 2014), June 30-July 2, 2014, Cherbourg, Normandy, France. [URL]

Colourlab Image Database: Multi-Illuminant scene (CID:MI)

The database can be downloaded here.

Citation:  Ziko, Imtiaz Masud; Beigpour, Shida & Hardeberg, Jon Yngve. Design and Creation of a Multi-illuminant Scene Image Dataset. Image and Signal Processing, Lecture Notes in Computer Science, Springer International Publishing, Volume 8509, Pages 531-538, 2014. [URL]

Colourlab Image Database: Imai’s ColorCheckers (CID:ICC)

The database can be downloaded here

Citation: Garcia Capel, Luis E. & Hardeberg, Jon Y. Automatic Color Reference Target Detection. The 22nd Color and Imaging Conference (CIC), IS&T, Pages 119-124, Boston, MA, USA, Nov, 2014. [PDF]

Spectral Image Database for Quality (SIDQ)

The SIDQ contains nine original 160-band hyperspectral images (MATLAB *.mat files) of scenes representing pseudo-flat surfaces of different materials (textile, wood, skin. . . ) with a spectral range between 410 and 1000nm. Five spectral distortions were designed, applied to the spectral images and subsequently compared in a psychometric experiment, in order to provide a basis for applications such as the evaluation of spectral image difference measures. The resulting 45 reproductions and raw subjective scores are also provided in the database.

The database can be downloaded here

Citation:  Steven Le Moan, Sony George, Marius Pedersen, Jana Blahova, and Jon Yngve Hardeberg. "A database for spectral image quality" in Image Quality and System Performance XII, San Francisco, CA, USA, February 2015, vol. 9396, p. 25, IS&T/SPIE.

QuickEval

QuickEval is a web-based tool for psychometric image evaluation. It supports rank order, paired comparison and category judgement. The tool is provided by the Norwegian Colour and Visual Computing Laboratory. QuickEval is available on www.quickeval.no   

Source code available at https://github.com/khaivngo/QuickEval  

Citation:  Ngo, K. V.; Dokkeberg, C. A.; Storvik, J. J.; Farup, I. & Pedersen, M. Quickeval: a web application for subjective image quality assessment, Image Quality and System Performance XII, 2015, 9396, 9396-24

Automatic Color Reference Target Detection

The software processes a batch of images using CCFind MainTempMatching: Code to process a batch of images using the provided template matching approach CCFind. 

Citation:  Garcia Capel, Luis E. & Hardeberg, Jon Y. Automatic Color Reference Target Detection. The 22nd Color and Imaging Conference (CIC), IS&T, Pages 119-124, Boston, MA, USA, Nov, 2014. [PDF]

Colourlab Image Database:Perceptual Projection Sharpness (CID:PPS)

This Colourlab Image Database:Perceptual Projection Sharpness (CID:PPS) contains 7 original images distorted 6 levels of blur. They were shown using a projection system, and subjective scores have been gathered from 15 human observers. The database can be downloaded here.

Citation : Zhao, Ping, Yao Cheng, and Marius Pedersen. "Objective assessment of perceived sharpness of projection displays with a calibrated camera." Colour and Visual Computing Symposium (CVCS), 2015. IEEE, 2015. 

Data Hiding in CDBS Halftones using Orientation Modulation

This package (zip file) contains: an MS Windows demo application for data embedding in chrominance channels of CDBS halftones, Matlab scripts for data detection in RGB scans of CDBS prints, and the 6 test images used for the evaluation provided in the paper below.

Citation : V. Kitanovski and M. Pedersen, “Orientation Modulation for Data Hiding in Chrominance Channels of Direct Binary Search Halftone Prints”,Journal of Imaging Science and Technology, Vol. 60, No. 5, pp. 050407-1–050407-9, 2016.

Colon capsule endoscopy images

The data contains colon capsule endoscopy images with pathologies and normal diagnosis from different parts of the colon. There are 30 images chosen by an expert for image enhancement comparison. There are four image folder that contain implementation of two image decomposition [1, 2] techniques along with original and our proposed method. Download link.

Citation: Mohammed Ahmed, Ivar Farup, Marius Pedersen, Hovde, Øistein, Sule Yildirim. Stochastic Capsule Endoscopy Image Enhancement. Under review. 

Data Hiding by White Modulation in Color Direct Binary Search Halftones

This package (zip file) contains the CDBSWM MS-Windows demo application for hiding binary visual patterns in CDBS halftones by modulating the fractional white coverage.

Citation: V. Kitanovski, R. Eschbach, M. Pedersen, J. Y. Hardeberg, “Data Hiding by White Modulation in Color Direct Binary Search Halftones”, to appear in IS&T Journal of Imaging Science and Technology.

Detection thresholds in chrominance channels of natural images

This package (zip file) contains the images, the log-Gabor target, and the collected thresholds for detecting the target inserted in the Cr and Cb channels of natural sRGB images. For more info, please read the readme.txt inside the zip file, or check the paper "Masking in Chrominance Channels of Natural Images - Data, Analysis, and Prediction" from Vlado Kitanovski and Marius Pedersen.

The Colourlab Contrast Enhanced Image Dataset (CCEID)

The Colourlab Contrast Enhanced Image Dataset (CCEID) contains a set of images, their contrast enhanced images and their corresponding subjective scores developed by the Norwegian Colour and Visual Computing Laboratory at Gjøvik University College. 
If you use this work please cite: 
Amirshahi, Seyed Ali, Altynay Kadyrova, and Marius Pedersen. "How do image quality metrics perform on contrast enhanced images?." 2019 8th European Workshop on Visual Information Processing (EUVIP). IEEE, 2019. 
Download here.

The Colourlab Image Dataset for 2.5D Quality Assessment

The data contains five folders based on five sets of quality variations, each containing original image and  height map(s). The 2.5D images were rendered through Canon Touchstone software in Adobe Photoshop.   

If you use this work please cite: Kadyrova, A., Kitanovski, V. and Pedersen, M., 2020. A study on attributes for 2.5 D print quality assessment. In Twenty-eight Color and Imaging Conference. The Society for Imaging Science and Technology.

Download here.

The Colourlab Image Dataset for Geometric Distortions

The Colourlab Image Database: Geometric Distortions (CID:GD) has49 different reference images that include three different types of geometrical distortions; seam carving, lens distortion, and image rotation. The images have been evaluated by observers in a category judgement experiment 

If you use this work please cite: Pedersen, M. and Amirshahi. S.A., 2021. Colourlab Image Database: Geometric Distortions. In Color and Imaging Conference. The Society for Imaging Science and Technology.

Download here

Image enhancement dataset for evaluation of image quality metrics

We introduce a dataset with enhanced images. The images have been enhanced by five end users, and these have been evaluated by observers in an online image quality experiment. The dataset contains 16 natural colour images (i.e., original), and in total  96 images. 

If you use this work please cite: Altynay Kadyrova, Marius Pedersen, Bilal Ahmad, Dipendra J. Mandal, Mathieu Nguyen, Pauline Hardeberg Zimmermann; Image enhancement dataset for evaluation of image quality metrics. Image Quality and System Performance XIX. January 2022. 

Download here

 

Subjective Enhanced Image Dataset (SEID)

The SEID dataset 15 observers are asked to enhance the quality of 30 reference images which are shown to them once at a low and another time at a high contrast. The dataset contains 30 reference images, along with the high and low contrast images provided to the observers. A Matlab program is also provided to the user to be able to recreate the enhanced images for each observer.

Please cite the following paper if you use the database: Azimian, Sahar, Farah Torkamani Azar, and Seyed Ali Amirshahi. "How Good is Too Good? A Subjective Study on Over Enhancement of Images." Color and Imaging Conference. Vol. 2021. No. 29. Society for Imaging Science and Technology, 2021.

Download here

 

Analyzing the Variability of Subjective Image Quality Ratings for Different Distortions

Dataset from paper "Analyzing the Variability of Subjective Image Quality Ratings for Different Distortions" by Olga Cherepkova, Seyed Ali Amirshahi, Marius Pedersen. 

Download here

 

Subjective quality evaluation: what can be learnt from cognitive science?

The raw data from two image quality experiments conducted online.  In Experiment 1 40 observers rated 235 images. In Experiment 2 32 observers rated 10 images. The experiments were conducted for the article:

Subjective quality evaluation: what can be learnt from cognitive science?

The article will be presented and eventually printed in Proceedings of the 11th Colour and Visual Computing Symposium 2022 (CVCS 2022)

Citation: Del Pin, Simon Hviid & Amirshahi, Seyed Ali. Subjective quality evaluation: what can be learnt from cognitive science? (IN PRESS)

Download here

Wireless Capsule Endoscopy Synthetic Atlas

Synthetic dataset for Wireless capsule endoscopy with different pathological and anatomical variations, including ulcerative colitis, polyps, different severities and types of inflammation, ulcers etc., as well as different levels of occlusion.

Citation: Deep learning for training and education in capsule endoscopy : Evaluating clinical diversity and plausibility of synthetic images. Anuja Vats, Marius Pedersen, Ahmed Mohammed, and Øistein Hovde. Under review. 2022.

Download here 

 

From labels to priors in capsule endoscopy

Pretrained weights from our paper From labels to priors in capsule endoscopy: a prior guided approach for improving generalization with few labels . 

Citation: Vats, A., Mohammed, A. and Pedersen, M., 2022. From labels to priors in capsule endoscopy: a prior guided approach for improving generalization with few labels. Scientific Reports12(1), p.15708.

Download

 

Image Demosaicing: subjective analysis and evaluation of image quality metrics

The dataset includes a psychmetric experiment in a controlled environment for investigating
several demosaicing algorithms. The images, used in the subjective experiment, are generated using a camera imaging pipelinewith ISETCam. Demosaicing algorithms are incorporated while
transforming sensor images to RGB images. 

Download here

CID:SFA-hytexila

This dataset is composed of Spectral Filter Arrays images of the HyteXila objects.

If you use this dataset, please refer to: Elezabi, O.; Guesney-Bodet, S.; Thomas, J.-B. Impact of Exposure and Illumination on Texture Classification Based on Raw Spectral Filter Array Images. Sensors 2023, 23, 5443.  https://doi.org/10.3390/s23125443

The dataset can be downloaded here

CIE Functions

Python module, GUI app, and web app for computing the CIE TC1-97 colorimetric functions. Available at https://github.com/ifarup/ciefunctions

 

Individual Contrast Preferences Database

This database contains contrast preference values for 22 observers across 499 images. Observers were instructed to select the image with their preferred contrast level. A Three-Alternative Choice algorithm was used in the experiment for selection. Outliers have been removed. The database is available for download and use in future research on Personalized Image Quality Assessment. Link for download

Reference: Cherepkova, O., Amirshahi, S. A., & Pedersen, M. (2024). Individual Contrast Preferences in Natural Images. Journal of Imaging, 10(1), 25.

 

Contrast preference: Three-Alternative Choice vs slider-based experiment.

This dataset contains individual contrast preference values from 15 observers for 499 images. The data were gathered through two separate experiments: a Three-Alternative Choice experiment and a slider-based experiment. The results from the two experiments are significantly different. Further details and analysis can be found in the associated paper referenced below. Outliers have been excluded from the dataset. The data is available for download and further analysis.

Reference: Cherepkova, O.; Amirshahi, S. and Pedersen, M. (2024). A Comparative Analysis of the Three-Alternative Forced Choice Method and the Slider-Based Method in Subjective Experiments: A Case Study on Contrast Preference Task. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8; ISSN 2184-4321, SciTePress, pages 425-435. DOI: 10.5220/0012360500003660

 

Colourlab Imaging Database: Optical Aberrations

We introduce a new image quality database called “Imaging Database: Optical Aberrations (CID: OA)” that incorporates new aberration types namely, defocus, astigmatism, and spherical aberration, that exist in the real world but are not incorporated in existing databases. Download here.

Reference: Colourlab Imaging Database: Optical Aberrations. Raed Hlayhel , Mobina Mobini , Bidossessi Emmanuel Agossou , Marius Pedersen , and Seyed Ali Amirshahi. London Imaging Meeting. 2024. 

 

NeRF-4Scenes: A Video Dataset for Subjective Assessment of NeRF

The NeRF-4Scenes dataset contains NeRF-generated videos collected from four real-world scenes. Each of the scenes are further trained on three NeRF models and generated on three dynamic paths for each case. Therefore, the dataset consists of 36 videos (4 scenes × 3 models × 3 paths). 

A subjective assessment data is also provided, collected from 18 observers through conducting a pairwise comparison for selecting observer preferred best-model and best-path for each scene.

[Dataset download link]

Citation:

Tabassum, Shaira; Amirshahi, Seyed Ali, "Quality of NeRF Changes with the Viewing Path an Observer Takes: A Subjective Quality Assessment of Real-time NeRF Model", 2024 16th International Conference on Quality of Multimedia Experience (QoMEX)

Tabassum, Shaira; Amirshahi, Seyed Ali, 2024, "NeRF-4Scenes: A Video Dataset for Subjective Assessment of NeRF", https://doi.org/10.18710/LFHFJN, DataverseNO, V1

25 Jun 2024