Questions 2: Suppose that an image has the following intensity distributions, where Pl(r) and P2(r) correspond to the background and foreground, respectively. Assume that the probability of a pixel to be in the background is 3 times that of being in the foreground. (a) Find the optimal threshold between object and background pixels that minimizes the total misclassification error. (b) Use the optimal threshold obtained in (a) to compute true positive and true negative rates (the ratio of foreground and background pixels that are correctly labeled). (c) Repeat (a) and (b) for Otsu method. Piir) 2/3 1/2 P2ir) 1 2 2 3 3 Questions 2: Suppose that an image has the following intensity distributions, where Pl(r) and P2(r) correspond to the background and foreground, respectively. Assume that the probability of a pixel to be in the background is 3 times that of being in the foreground. (a) Find the optimal threshold between object and background pixels that minimizes the total misclassification error. (b) Use the optimal threshold obtained in (a) to compute true positive and true negative rates (the ratio of foreground and background pixels that are correctly labeled). (c) Repeat (a) and (b) for Otsu method. Piir) 2/3 1/2 P2ir) 1 2 2 3 3