Drawing an isothermal contour map using a tree search strategy

The authors present a global algorithm for drawing an isothermal contour map in thermal images. The problem of isothermal contour detection is reduced to the problem of finding an optimal path in a weighted tree. The properties of the contour are embedded in the structure of the tree, and search algorithms are used to find the optimal solution. To search the optimal isothermal contour, a heuristic search algorithm, which is used in artificial intelligence, is adopted. It is shown that the tree approach can be used to draw acceptable contours even in noise-added thermal images, but the computation time for detecting an isothermal contour increases sharply with increased noise. The strategy is expected to the helpful in decision-making or diagnosis from thermal images