A Tongue Image Segmentation Method Based on Enhanced HSV Convolutional Neural Network

Jiang, Li; Xu, Baochuan; Ban, Xiaojuan; Tai, Ping; Ma, Boyuan

doi:10.1007/978-3-319-66805-5_32

Cited by 16 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of those methods [4][5][6][7][8][9][10] attempts traditional image processing techniques such as watershed transform or adaptive threshold for object segmentation, which are sensitive to the clustered backgrounds or illumination changes and confuse lips from tongue body. More recently, with the fast development of deep learning, deep convolutional neural network based methods 3,[11][12][13] have been developed for more robust segmentation of tongue body. Benefiting from the powerful representation learning ability, those deep learning based methods achieve higher performance compared with the traditional tongue segmentation methods.…”

Section: Introductionmentioning

confidence: 99%

“…Benefiting from the powerful representation learning ability, those deep learning based methods achieve higher performance compared with the traditional tongue segmentation methods. However, there are still some weaknesses in those methods such as additional image enhancement preprocessing 11 or brightness discrimination, 12 which complicates the whole segmentation process and reduces the ability of generalization as an end-to-end deep model. Moreover, some of the supervised models 3,13 rely heavily on the fully-labeled data to supervise the training of the model which cannot make use of the large amounts of the unlabeled images, therefore, how to conduct semisupervised learning that requires only a small subset of fully labeled images along with a larger set of completely annotation-free samples for tongue segmentation, is still an open problem.…”

Section: Introductionmentioning

confidence: 99%

“…• We propose a reconstruction enhanced semisupervised framework for tongue segmentation, named SemiTongue. Different from previous deep learning based methods, 3,[11][12][13] which conduct segmentation in a fully supervised manner, in SemiTongue, image reconstruction constraint combined with adversarial learning is used to utilize a large number of completely annotation-free images, which improves the accuracy of tongue segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…However, there are few works of tongue segmentation base on deep learning because it is difficult to collect and annotate enough numbers of medical tongue images. Recently, there are several deep learning based tongue segmentation algorithms,3,[11][12][13] which outperforms most of the traditional tongue segmentation methods. A HSV color model enhanced CNN proposed in Reference 11 is employed to segment tongue body from tongue image; however, additional image enhancement preprocessing is required in this model, which makes the whole segmentation process more complicate.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Reconstruction enhanced probabilistic model for semisupervised tongue image segmentation

Zhou

Fan

Zhao

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Tongue segmentation is a key step of automatic tongue diagnosis, and the major challenges for the effective segmentation lie in the large appearance variations of tongue caused by different diseases, for example, tongue coating and tongue texture. Moreover, the limited labeled data also hinders traditional supervised methods from their powerful learning ability. To alleviate these challenges, in this work, we propose a reconstruction enhanced probabilistic model for semisupervised tongue segmentation, named SemiTongue, in which, image reconstruction constraint combined with adversarial learning is used to improve the accuracy of tongue segmentation. Specifically, based on a shared feature encoder that served as an inference model, two separate branches in SemiTongue as the generative model, which are composed of a segmentation decoder and a reconstruction decoder, are utilized to generate the tongue segmentation and reconstruct original tongue image respectively. Then, a discriminator is employed to differentiate the generated segmentation map from the ground truth segmentation distribution. Moreover, semisupervised learning is conducted through discriminator by discovering the reliable region in the generated segmentation map of unlabeled images, which is further utilized to supervise the segmentation branch. Experimental results compared with state-of-the-art methods on real-world datasets demonstrate the effectiveness of SemiTongue.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Reconstruction enhanced probabilistic model for semisupervised tongue image segmentation

Zhou

Fan

Zhao

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Most of those methods are based on the traditional image processing techniques, however, some of them are sensitive to the illumination changes or clustered backgrounds [3], [4], some of them confuse lips from tongue body [5]- [7], and some of them require additional preprocessing which makes the whole segmentation process more complex [8], [9]. More recently, deep learning based methods [10]- [12] have been proposed for automatic tongue segmentation. Although those deep learning based methods outperform the most traditional tongue segmentation methods, there are still some limits in those methods.…”

Section: Introductionmentioning

confidence: 99%

Tonguenet: Accurate Localization and Segmentation for Tongue Images Using Deep Neural Networks

Zhou

Fan

2019

IEEE Access

View full text Add to dashboard Cite

Tongue diagnosis is an important way of monitoring human health status in traditional Chinese medicine. As a key step of achieving automatic tongue diagnosis, the major challenges for robust and accurate segmentation and identification of tongue body in tongue images lay in the large variations of tongue appearance, e.g., tongue texture and tongue coating, caused by different diseases for different patients. To cope with these challenges, we propose a novel end-to-end model for multi-task learning of tongue localization and segmentation, named TongueNet, in which pixel-level prior information is utilized for supervised training of deep convolutional neural network. Firstly, we introduce a feature pyramid network based on the designed context-aware residual blocks for the extraction of multi-scale tongue features. Then, the region of interests (ROIs) of tongue candidates are located in advance from the extracted feature maps. Finally, finer localization and segmentation of tongue body are conducted based on the feature maps of ROIs. Quantitative and qualitative comparisons on real-world datasets show that the proposed TongueNet achieves state-of-the-art performance for the segmentation of tongue body in terms of both robustness and accuracy.

show abstract

An iterative transfer learning framework for cross‐domain tongue segmentation

Luo

Zhang

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

SummaryTongue diagnosis is an important clinical examination in Traditional Chinese Medicine. As the first step of the diagnosis, the accuracy of tongue image segmentation directly affects the subsequent diagnosis. Recently, deep learning‐based methods have been applied for tongue image segmentation and achieve promising results. However, these methods usually work well on one dataset and degenerate significantly on different distributed datasets. To deal with this issue, we propose a framework named Iterative cross‐domain tongue segmentation in the study. First, we train a tongue image segmentation U‐Net model on the source dataset. Then, we propose a tongue assessment filter to select satisfying samples based on predictions of the U‐Net model from the target dataset. Following, we fine‐tune the model on the selected samples along with the source domain. Finally, we iterate between the filtering and the fine‐tuning steps until the model is converged. Experimental results on two tongue datasets show that our proposed method can improve the dice score on the target domain from 70.11% to 98.26%, as well as outperform state‐of‐the‐art comparing methods.

show abstract

A Tongue Image Segmentation Method Based on Enhanced HSV Convolutional Neural Network

Cited by 16 publications

References 5 publications

Reconstruction enhanced probabilistic model for semisupervised tongue image segmentation

Reconstruction enhanced probabilistic model for semisupervised tongue image segmentation

Tonguenet: Accurate Localization and Segmentation for Tongue Images Using Deep Neural Networks

An iterative transfer learning framework for cross‐domain tongue segmentation

Contact Info

Product

Resources

About