Robust thresholding by calibration

Although image segmentation technology has achieved rapid development, threshold method is still an indispensable part in many practical applications. The most advanced methods do not perform well in the segmentation of many different types of images. Therefore, it is expected that the optimal segmentation method can be obtained for images with different modalities. In this paper, a robust threshold method is proposed to calibrate the parameters to obtain the best accuracy. The proposed threshold method is tested in the composite image and the actual image. The experimental results show that the proposed method is superior to the existing technology.