Aiming at the different texture characteristics of the forest and the smoke image
a smoke segmentation method about the improvement of differential box-counting(DBC)fractal dimension algorithm is proposed. Firstly
the improved algorithm expands the scope of child window based on the existing algorithm
calculates every pixel fractal dimension and analyses them. Then
it filters the pixels marked the smoke feature by choosing the fit threshold
it can realize smoke image segmentation. Finally
the expansive algorithm in the morphology is used to the connected processing. The experimental results demonstrate that the improved differential box-counting fractal dimension algorithm has a satisfying segmentation result.
关键词
Keywords
references
Chaudhuri B B, Sarkar N. An efficient approach to compute fractal dimension in texture image [J].Pattern Recognition,1992,25(9):1035-1041.
Sarkar N, Chaudhuri B B. An efficient differential box-counting approach to compute fractal dimension of image [J]. IEEE transactions on systems,man,and cybernetics,1994,24(1):115-120.