Phos is a color image database of 15 scenes captured under different illumination conditions. More particularly, every scene of the database contains 15 different images: 9 images captured under various strengths of uniform illumination, and 6 images under different degrees of non-uniform illumination. The images contain objects of different shapes, colors, and textures.

Uniform illumination is achieved by using multiple diffusive light sources, evenly distributed around the objects, as well as a Lambertian white background. The different strengths of uniform illumination are captured by adjusting the shutter speed and as a result, the exposure of the camera varies between -4 and +4 stops from the original correctly exposed image. Thus, for every scene, there are four underexposed and four overexposed images with uniform illumination along with the photo captured under the correct exposure.

Non-uniform illumination is accomplished by adding a strong directional light source to the diffusive lights located around the objects. By adjusting the strength of the diffusive lights, six different mixtures of uniform and non-uniform illumination were created, ranging from both directional and uniform illumination to directional illumination only.

All collections are in lossless compressed png format and in full 24bit color. The size of the entire image collection captured at the original resolution (12.1MP) is exceptionally large and we publish it for reference purposes only. Thus, we provide downsampled versions of the original ones down to even 0.2MP. Researchers can view each scene below and choose to either download each one separately or the entire database as one compressed file in different resolutions.

If you use this dataset please cite:

V. Vonikakis, D. Chrysostomou, R. Kouskouridas and A. Gasteratos, A biologically inspired scale-space for illumination invariant feature selection, Measurement Science and Technology, vol. 24, no. 7, p. 074024 (13pp), 2013.

V. Vonikakis, D. Chrysostomou, R. Kouskouridas and A. Gasteratos, Improving the Robustness in Feature Detection by Local Contrast Enhancement, in Proceedings of the IEEE International Conference on Imaging Systems and Techniques (IST ’12), pp. 158 – 163, Manchester, United Kingdom, 16-17 July 2012.