Deeptongue: Tongue Segmentation Via Resnet

Bingqian Lin; Junwei Xle; Cuihua Li; Yanyun Qu

ICASSP 2018accepted0 citations

Deeptongue: Tongue Segmentation Via Resnet

Bingqian Lin, Junwei Xle, Cuihua Li, Yanyun Qu

Abstract

Accurate tongue image segmentation is helpful to acquire correct automatic tongue diagnosis result. However, traditional methods cannot bring satisfying results in most cases. This paper proposes an end-to-end trainable tongue image segmentation method using deep convolutional neural network based on ResNet. The proposed method, named DeepTongue, segments tongue by using a forward network without preprocessing. The proposed method has no restrictions of the illumination and size of tongue images. Experimental results show that the proposed DeepTongue improves the segmentation accuracy by a noticeable margin. In addition, DeepTongue is much faster than the existing tongue image segmentation methods.

BibTeX

@inproceedings{icassp2018_deeptonguetongue,
  title = {Deeptongue: Tongue Segmentation Via Resnet},
  author = {Bingqian Lin and Junwei Xle and Cuihua Li and Yanyun Qu},
  booktitle = {ICASSP 2018},
  year = {2018}
}