No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
TCM Tongue Segmentation and Analysis with a Mobile Device
In this paper, we propose a reusable and high-efficiency two-stage deep learning based method for surface defect inspection in industrial environment. Aiming to achieve trade-offs between efficiency and accuracy simultaneously, our method makes a novel combination of a segmentation stage (stage1) and a detection stage (stage2), which are consisted of two fully convolutional networks (FCN) separately. In the segmentation stage we use a lightweight FCN to make a spatially dense pixel-wise prediction to inference the area of defect coarsely and quickly. Those predicted defect areas act as the initialization of stage2, guiding the process of detection to refine the segmentation results. We also use an unusual training strategy: training with the patches cropped from the images. Such strategy has greatly utility in industrial inspection where training data may be scarce. We will validate our findings by analyzing the performance obtained on the dataset of DAGM 2007.
There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at
http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net
.
We demonstrate a novel method to segment the tongue image automatically with the mouth location method and active appearance model (AAM). With the help of a particular feature of the mouth,we could locate the dark hole's position easily and quickly. For the close relationship between the mouth and tongue, we would predict the approximate area of the tongue. Then we apply the AAM to segment the tongue from the image completely, which uses texture and shape of an object. During the AAM search, we constrain the initial displacement and size in the approximate area. For those images that failed to locate the mouth, we use a multi-initial displacement method during the AAM search to optimize the result. The experiment shows that our method is accurate and effective.
A robot wrote this entire article. Are you scared yet, human?
- B Reed
Android Image Cropper
- Arthurhub
ResNet v1.5 for PyTorch
- Nvidia
Analysis of Tongue Colour in Atlas of Tongue Picture in 230 Patients By Practitioners of TCM
- X L Wu
- X Z Lu
K-means Clustering: Algorithm, Applications, Evaluation Methods, and Drawbacks
- I Dabbura
Discussion on the application value of tongue manifestation in chronic pelvic inflammatory disease
- Tang
Chan: Dialogue with officials to propel TCM development
- G Wen
Role of digitalized tongue diagnosis in evaluating blood sugar, nutrient state and dietary structure in type 2 diabetics
- Wang
Role of digitalized tongue diagnosis in evaluating blood sugar, nutrient state and dietary structure in type 2 diabetics
- L Wang
- J Gao
- Y Q Wang
- F M Jin
- H Yang
- H Tang
Discussion on the application value of tongue manifestation in chronic pelvic inflammatory disease
- Q Tang
- J Chen
- J Li
- H Yan
Fully Convolutional Neural Networks for Safe Defect Inspection in Industrial Environment
- Yu