Processing of Underwater Colour Images Applied to Live Aquarium Videos

D. Semani, M. Chambah, and P. Courtellemont


Underwater imaging, colour constancy, automatic colour correction, video segmentation, segmentation quality evaluation


The underwater images are characterized by a strong and non- uniform colour cast due to the aquatic environment and to artificial (and/or natural) lighting. We present in this paper some aspects of colour restoration of underwater images and an application to live fish segmentation and recognition. The proposed automatic colour correction techniques are based on the perceptual ACE model, and PHM colour constancy method. The restored images give better results when displayed or processed (fish segmentation and recognition). The presented results are very satisfying and promising.

Important Links:

Go Back