Changen Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Changen Zhou has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Zuoyong Li
Minjiang University
2 shared publications - Candong Li
Fujian University of Traditional Chinese Medicine
1 shared publication Haoyi Fan
School of Computer Science and Technology Harbin University of Science and Technology Harbin China
1 shared publication- Haoyi Fan
School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China
1 shared publication Hongben Xu
Research Base of Traditional Chinese Medicine Syndrome Fujian University of Traditional Chinese Medicine Fuzhou China
1 shared publicationHuangwei Lei
Research Base of Traditional Chinese Medicine Syndrome Fujian University of Traditional Chinese Medicine Fuzhou China
1 shared publication
Latest Publications
- 14 August 2020
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 32 (22)
Reconstruction enhanced probabilistic model for semisupervised tongue image segmentation
Summary: 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.
- 14 August 2020
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 32 (22)
Reconstruction enhanced probabilistic model for semisupervised tongue image segmentation
Summary: 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.
- Open Access
- 11 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 148779-148789
Tonguenet: Accurate Localization and Segmentation for Tongue Images Using Deep Neural Networks
- 11 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 148779-148789
Open AccessTonguenet: Accurate Localization and Segmentation for Tongue Images Using Deep Neural Networks