Image Enhancement

Enhancing an image means modifying one or more of its visual features in order to increase the visibility of its content and enable its understanding. This is very important both in human as well as machine vision. Algorithms removing or lowering noise, shadows, artifacts or color casts due to the illumination under which an image has been acquired are highly relevant to a plethora of applications, including for instance robust object/people detection and tracking, analysis of medical images, image rendering for entertainment and augmented reality, 3D reconstruction.  

Image Enhancement Datasets

The page lists some datasets of real-world images, acquired by different devices, in indoor and outdoor environments, under different light conditions, including low-light and back-light. Many images are characterized by the co-existence of bright and dark regions with different size and proportion. These features make these datasets particularly appropriate to test image enhancers based on spatial color analysis.  

Datasets are stored as .tgz archives. You may use gunzip and tar to unzip them.


Datasets


[Size of compressed archive: 141.9 M]


[Size of compressed archive: 2.96 Gb]


[Size of compressed archive: 1.2 Gb]


[Size of compressed archive: 2.4 M]

The dataset SCA-30 has been used to this purpose in the paper [5]:

G. Simone, M. Lecca, G. Gianini, A. Rizzi, A Survey of Methods and Evaluation of Retinex-inspired Image Enhancers, to appear on JEI, 2022

The original images of SCA-30 and their versions enhanced by 35 Retinex-inspired enhancers are available here (see the sub directories Original and Filtered contained in the zipped archive).

[Size of compressed archive: 92.1 M]

Data and plots discussed in the paper above are downloadable here.   

[Size of compressed archive: 7.7 M]



[Size of compressed archive: 616 K]


[Size of compressed archive: 324 KB]



The size of the data-set is 4,5 MB, the downloadable archive requires 3,0 MB of space.


The size of the data-set downloadable archive is 7,5 MB. The data-set size is 8,12 MB. 


images from the dataset

MEXICO example - shutter speed from 3 ms to 30 ms


Software


Along with the datasets, we provide also the following software, that is provided as a .tgz archive along with license and instructions: 



References