Methods of image segmentation based on entropy have been gaining increasing attention from researchers, mainly involving the search for automatic thresholds. A digital image can be thresholded with one or more threshold values, but the number of thresholds is still a point of controversy among researchers. Another issue that is widely discussed in the field concerns the quality of the segmentation, which fundamentally depends on human subjectivity. This project aims to advance these two problems, and aims to present methods based on meta-heuristics with entropic core for more efficient calculation of optimal thresholds. Also providing an alternative base of segmented human data that serves as the gold standard as a reference for the quality of answers. It is used for parallel execution of detailed methods that serve to limit the effective response.
News published in Agência FAPESP Newsletter about the scholarship: