Image Thresholding based on 2-D Histogram θ-Division and Tsallis Entropy

 In view of the obvious wrong segmentation in commonly used 2-D histogram region division and the non-universality of oblique segmentation method for image thresholding proposed recently, considering that Tsallis entropy has universality and it is more efficient than Shannon entropy, in this paper a much more widely suitable thresholding method is proposed based on 2-D histogram θ-division and maximum Tsallis entropy. Firstly the 2-D histogram θ-division method is given. The region is divided by four parallel oblique lines and a line. Angel between its normal line and gray level axis is θ degree. Image thresholding is performed according to pixel’s weighted average value of gray level and neighbor average gray level. So the oblique segmentation method can be regarded as a special case with θ=45^oof the proposed method. Then the formulae and its fast recursive algorithm of the method are deduced. Finally the segmented results and running time with different θ values are listed in the experimental result, which show that the segmented image achieves more accurate borders with smaller θ value while obtains better antinoise with larger θ value. It can be selected according to the real image characteristics and the requirement of segmented result. Compared with the conventional 2-D Tsallis entropy method, the proposed method not only achieves more accurate segmentation result and more robust anti-noise, but also significantly reduces the running time and memory space.