A Snake-Based Approach to Automated Tongue Image Segmentation
Tongue diagnosis, one of the most important diagnosis methods of Traditional Chinese Medicine, is considered a very good candidate for remote diagnosis methods because of its simplicity and noninvasiveness. Recently, considerable research interests have b
- PDF / 587,918 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 92 Downloads / 240 Views
A Snake-Based Approach to Automated Tongue Image Segmentation
Abstract Tongue diagnosis, one of the most important diagnosis methods of Traditional Chinese Medicine, is considered a very good candidate for remote diagnosis methods because of its simplicity and noninvasiveness. Recently, considerable research interests have been given to the development of automated tongue segmentation technologies, which is difficult due to the complexity of the pathological tongue, variance of the tongue shape, and interference of the lips. In this chapter, we propose a novel automated tongue segmentation method via combining a polar edge detector and active contour model (ACM) technique. First, a polar edge detector is presented to effectively extract the edge of the tongue body. Then we design an edge filtering scheme to avoid the adverse interference from the nontongue boundary. After edge filtering, a local adaptive edge bi-thresholding algorithm is introduced to perform the edge binarization. Finally, a heuristic initialization and an ACM are proposed to segment the tongue body from the image. The experimental results demonstrate that the proposed method can accurately and effectively segment the tongue body. A quantitative evaluation on 200 images indicates that the normalized mean distance to the closest point is 0.48%, and the average true positive percent of our method is 97.1%.
4.1
Introduction
As previously stated, adverse factors, such as noise, diffuse boundaries, and redundant edges, seriously affect the effectiveness of the segmentation algorithm. For example, boundaries may be blurred due to the movement of the target, miss-focus of camera, the low signal-to-noise ratio of the capture device, or the similarity of the surrounding tissues. In such cases, performance of the regular image segmentation techniques would be greatly degraded, and prior knowledge would be very effective in circumventing the underdetermined nature of the automatic segmentation process.
© Springer Science+Business Media Singapore 2017 D. Zhang et al., Tongue Image Analysis, DOI 10.1007/978-981-10-2167-1_4
71
72
4 A Snake-Based Approach to Automated Tongue Image Segmentation
The active contour model (ACM), characterized by shape initialization, representation, and the evolution rule, has been very successful in medical image segmentation. The performance of the regular ACM, however, is seriously affected by the result obtained using edge detection. Usually, edge detection has a great effect on the shape initialization and evolution of the edge-based active contour technique. If the edge maps are very noisy or are contaminated with spurious edges, false initialization or error segmentation are then obtained. For example, previous works (Cai, 2002; Pang, Wang, Zhang, & Zhang, 2002) on tongue segmentation usually used the classical gradient operators to detect the boundary of tongue body, and then utilized an ACM to crop the tongue area. The gradient on parts of the tongue boundary was sometimes very weak and inconsecutive, which made it d
Data Loading...
