The presence of dental calculus is highly correlated with the formation and advancement of periodontal disease. The occurrence and relapse of periodontal disease can be prevented only if dental calculus is completely removed. In this study, optical coherence tomography (OCT) is used to obtain two-dimensional cross-sectional images of tooth samples, in conjunction with a segmentation technique that enables automatic identification of dental calculus. We propose the vertical intensity transform function to correct the nonuniform instrument signal intensity caused by OCT. Afterwards, the detection ranges are defined by K-means or the Markov random field (MRF), and the candidate range is selected on the basis of mathematical morphology (MM). Finally, the features (thickness gradient, texture, and tooth surface slope) are quantified, and dental calculus is recognized and segmented. In the preliminary result, the sensitivity is 87.5%. The mean distance between the boundaries generated by the proposed algorithm and the corresponding manually delineated boundaries is 2.52 ± 3.54 pixels. Our proposed algorithm assists physicians to determine dental calculus more easily. Doctors no longer need to rely solely on their experiences to recognize dental calculus, but can refer to specific data to assist in diagnosis.