“…A number of automated techniques have been proposed to detect the upwelling areas in oceanographic satellite images. Some of the most popular approaches include the use of the histogram-based separation (Nieto, Demarcq, and McClatchie 2005), which relies on the fact that upwelling fronts are usually regarded as boundaries between two water masses of constant temperature; neural networks (Chaudhari, Balasubramanian, and Gangopadhyay 2008), where the SST image is trained based on k-means segmentation results and a quantitative criterion is developed to test the existence of upwelling in each segmented image; hybrid method (Marcello, Marques, and Eugenio 2005), that has also been developed to identify the area covered upwelling waters, using region of interest histogram and region-growing process.…”