Automated tongue segmentation is a critical component of tongue diagnosis, especially in Traditional Chinese Medicine (TCM), where it has been practiced for thousands of years and is generally considered pain-free and non-invasive. Therefore, a more precise, fast, and robust tongue segmentation system to automatically segment tongue images from its raw format is necessary. Previous algorithms segmented the tongue in different ways, where the results are either inaccurate or time-consuming. Furthermore, none of them developed a dedicated, automatic segmentation system. In this paper, we proposed TongueNet, which is a precise and fast automatic tongue segmentation system. U-net is utilized as the segmentation backbone applying a small-scale image dataset. Besides this, a morphological layer is proposed in the latter stages of the architecture. The proposed system when applied to a tongue image dataset with 1000 images, achieved the highest Pixel Accuracy of 98.45% and consumed 0.267 s per picture on average, which outperformed conventional state-of-the-art tongue segmentation methods in both accuracy and speed. Extensive qualitative and quantitative experiments showed the robustness of the proposed system concerning different positions, poses, and shapes. The results indicate a promising step in achieving a fully automated tongue diagnosis system.

Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.

A high sensitive refractive index sensor based on the cladding etched photonic crystal fiber (PCF) Mach-Zehnder interferometer (MZI) is proposed, which is spliced a section of photonic crystal fiber between two single modes fibers (SMFs).The interference fringe of the MZI shifts with the variation of the ambient refractive index (RI). It is found that the RI sensitivity slightly decrease with an increase in the interference length. The sensitivities of MZI with 35 mm PCF, 40 mm PCF, and 45 mm PCF are 106.19 nm/RIU, 93.33 nm/RIU, and 73.64 nm/RIU, respectively, in the range of 1.333 to 1.381. After etched, the RI sensitivity of the MZI could be improved obviously. The RI sensitivities of the MZI with 35 mm PCF are up to 211.53 nm/RIU and 359.37 nm/RIU when the cladding diameter decreases to 112 μm and 91 μm, respectively. Moreover, the sensor is insensitive to temperature, and the measured sensitivity is only 9.21 pm/ with the range from 20 ℃ to 500 ℃. In ℃ addition, the sensor has advantage of simple fabrication, low cost, and high RI sensitivity.

No abstract

No abstract