A ROI Extraction Algorithm Based on Entropy Function Using Weights

The traditional two-dimensional Otsu can only divide the targets from the backgrounds. However, the targets are not all useful. So, a further process is needed. This paper proposes an optimized entropy function algorithm. The images are only regarded as the targets and backgrounds. Meanwhile, the weights can determine the proportion of the targets' and the backgrounds' entropy in the entire entropy function for selecting regions of interest (ROI), and then identify the ROIs from the targets which are divided by the method of two-dimensional Otsu by comparing the entropy function containing weights with the given threshold. Eventually, processing and analyzing the images obtained from the tar furnace combustion proved the feasibility, accuracy, and efficiency of the method proposed in this paper.