scispace - formally typeset
Search or ask a question
Author

Mingfeng Zhu

Bio: Mingfeng Zhu is an academic researcher from Jiangxi University of Traditional Chinese Medicine. The author has contributed to research in topics: Tongue & Evaluation function. The author has an hindex of 2, co-authored 8 publications receiving 20 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: A novel method is suggested, which applies multiobjective greedy rules and makes fusion of color and space information in order to extract tongue image accurately.
Abstract: Tongue image with coating is of important clinical diagnostic meaning, but traditional tongue image extraction method is not competent for extraction of tongue image with thick coating. In this paper, a novel method is suggested, which applies multiobjective greedy rules and makes fusion of color and space information in order to extract tongue image accurately. A comparative study of several contemporary tongue image extraction methods is also made from the aspects of accuracy and efficiency. As the experimental results show, geodesic active contour is quite slow and not accurate, the other 3 methods achieve fairly good segmentation results except in the case of the tongue with thick coating, our method achieves ideal segmentation results whatever types of tongue images are, and efficiency of our method is acceptable for the application of quantitative check of tongue image.

9 citations

Proceedings ArticleDOI
11 Jun 2009
TL;DR: A novel approach for tongue image extraction that utilizes greedy rules to combine color information and space information to search object tongue area in the 2-dimensional sample space, and the start position of the search, intensity threshold and hue threshold are selected fully automatically.
Abstract: Tongue inspection is one of the most important methods of Traditional Chinese Medicine diagnoses. Traditional tongue inspection mainly depends on observations to tongue substance, tongue coating and tongue pattern and diagnostic experience of the doctors. Diagnostic results are restricted by doctor's knowledge level, their experience as well as other subjective factors and affected by the light and temperature of external environment. In order to solve this problem, we should combine Traditional Chinese Medicine experts' diagnostic experience with modern information technologies, check and analyze tongues quantitively and objectively, and make scientific diagnoses. However, to realize quantitive and objective tongue checks and analyses, extracting tongue from the mouth and face is the first important step. A novel approach for tongue image extraction is proposed to solve this problem in this article. It utilizes greedy rules to combine color information and space information to search object tongue area in the 2-dimensional sample space, and the start position of the search, intensity threshold and hue threshold are selected fully automatically. Comparison experiment results indicate that this method can extract tongue from the raw image effectively and we have made a breakthrough in extracting the tongues with thick coating. Moreover, the tongue images extracted by this method can be used as valid bases for the later quantitive analyses.

7 citations

Patent
08 Jul 2015
TL;DR: In this article, a random walk tongue image extraction method based on multi-rule fusion is proposed, which is high in intelligent degree, the whole extraction process is completed in a full-automatic mode, the efficiency of the random walk algorithm is greatly improved, the time required by tongue extraction is shortened, and a tongue image can be successfully and accurately extracted from the image containing a tongue coating.
Abstract: A random walk tongue image extraction method based on multi-rule fusion comprises the following steps that initial segmentation is performed on an original image by utilizing a toboggan algorithm with a reduced rule, so an initial range set is acquired; a composite weighting function is utilized for establishing a weighted graph, and simplification is performed; final cluster segmentation is performed by utilizing a random walk tongue image extraction method based on multi-rule fusion, so a tongue body area image is generated; finally, a target area is trimmed through mathematical morphology operators, so pinholes in the tongue image area are eliminated, and a target tongue image is obtained. The random walk tongue image extraction method is high in intelligent degree, the whole extraction process is completed in a full-automatic mode, the efficiency of the random walk algorithm is greatly improved, the time required by tongue image extraction is shortened, and a tongue image can be successfully and accurately extracted from the image containing a tongue coating.

2 citations

Proceedings ArticleDOI
13 Nov 2015
TL;DR: An improved BP-ANN with self-adaptive network structure is introduced to solve the problem of tongue color recognition and is more accurate than the traditional one.
Abstract: Tongue color recognition is one of important research in objective tongue diagnosis. Since the network structure of traditional BP-ANN can greatly affect the recognition rates of tongue color, a kind of improved BP-ANN with self-adaptive network structure is introduced to solve the problem of tongue color recognition. In this method, according to the recognition rates, the node number of the hidden layer is automatically selected, i. e. the network structure is self-adaptive. As the experimental results show, our improved BP-ANN with self-adaptive network structure is more accurate than the traditional one.

2 citations

Book ChapterDOI
01 Jan 2014
TL;DR: An integrated type of TCM clinical decision support system is introduced and a method of heuristic reasoning is suggested in IRS that is much faster than traditional method of full matching and the matching degrees are the same as those of traditional one when using the same data.
Abstract: This paper introduced an integrated type of TCM clinical decision support system. The components and principles of our system are illustrated. TCM CDSS are divided into eight components. They are TCM DSEMRS, TCM EMRTMS, PIMS, UIMS, IRS, UIR, PIR and KR respectively. Principles of TCM DSEMRS and principles of TCM EMRTMS are discussed in this paper. Among these components, IRS is the core of TCM CDSS. Principles of IRS are discussed in detail in this paper. In IRS, a method of heuristic reasoning is suggested. And the comparison experiment results show our method of heuristic reasoning is much faster than traditional method of full matching and the matching degrees of our method are the same as those of traditional one when using the same data.

1 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: The diagnostic method of diabetes on the basis of tongue images in Traditional Chinese Medicine (TCM) is of great value, indicating the feasibility of digitalized tongue diagnosis.
Abstract: Objective. The purpose of this research is to develop a diagnostic method of diabetes based on standardized tongue image using support vector machine (SVM). Methods. Tongue images of 296 diabetic subjects and 531 nondiabetic subjects were collected by the TDA-1 digital tongue instrument. Tongue body and tongue coating were separated by the division-merging method and chrominance-threshold method. With extracted color and texture features of the tongue image as input variables, the diagnostic model of diabetes with SVM was trained. After optimizing the combination of SVM kernel parameters and input variables, the influences of the combinations on the model were analyzed. Results. After normalizing parameters of tongue images, the accuracy rate of diabetes predication was increased from 77.83% to 78.77%. The accuracy rate and area under curve (AUC) were not reduced after reducing the dimensions of tongue features with principal component analysis (PCA), while substantially saving the training time. During the training for selecting SVM parameters by genetic algorithm (GA), the accuracy rate of cross-validation was grown from 72% or so to 83.06%. Finally, we compare with several state-of-the-art algorithms, and experimental results show that our algorithm has the best predictive accuracy. Conclusions. The diagnostic method of diabetes on the basis of tongue images in Traditional Chinese Medicine (TCM) is of great value, indicating the feasibility of digitalized tongue diagnosis.

70 citations

Journal ArticleDOI
TL;DR: A conceptual framework for the automated tongue diagnostic system on mobile enabled platform is proposed that will be able to connect tongue diagnosis with the future point-of-care health system.
Abstract: Tongue diagnosis can be an effective, noninvasive method to perform an auxiliary diagnosis any time anywhere, which can support the global need in the primary healthcare system. This work reviews the recent advances in tongue diagnosis, which is a significant constituent of traditional oriental medicinal technology, and explores the literature to evaluate the works done on the various aspects of computerized tongue diagnosis, namely preprocessing, tongue detection, segmentation, feature extraction, tongue analysis, especially in traditional Chinese medicine (TCM). In spite of huge volume of work done on automatic tongue diagnosis (ATD), there is a lack of adequate survey, especially to combine it with the current diagnosis trends. This paper studies the merits, capabilities, and associated research gaps in current works on ATD systems. After exploring the algorithms used in tongue diagnosis, the current trend and global requirements in health domain motivates us to propose a conceptual framework for the automated tongue diagnostic system on mobile enabled platform. This framework will be able to connect tongue diagnosis with the future point-of-care health system.

36 citations

Journal ArticleDOI
TL;DR: In this paper, the authors developed models based on computer tongue image analysis technology to observe the tongue characteristics of 1778 participants (831 cases of NAFLD and 947 cases of non-NAFLD).

16 citations

Journal ArticleDOI
TL;DR: A novel method is suggested, which applies multiobjective greedy rules and makes fusion of color and space information in order to extract tongue image accurately.
Abstract: Tongue image with coating is of important clinical diagnostic meaning, but traditional tongue image extraction method is not competent for extraction of tongue image with thick coating. In this paper, a novel method is suggested, which applies multiobjective greedy rules and makes fusion of color and space information in order to extract tongue image accurately. A comparative study of several contemporary tongue image extraction methods is also made from the aspects of accuracy and efficiency. As the experimental results show, geodesic active contour is quite slow and not accurate, the other 3 methods achieve fairly good segmentation results except in the case of the tongue with thick coating, our method achieves ideal segmentation results whatever types of tongue images are, and efficiency of our method is acceptable for the application of quantitative check of tongue image.

9 citations

Proceedings ArticleDOI
01 Jan 2016
TL;DR: The morphological processing showed better result to separate the tongue from its background which can be further employed for geometric shape based disease diagnosis, and RGB was unveiled to have a better enactment than others.
Abstract: Tongue diagnosis is an auxiliary, effective and non-invasive technique to evaluate the condition of a patient's internal organ in traditional East Asian medicine. The diagnosis process relies on expert's opinion based on visual inspection of colour, substance, coating, form and motion of the tongue. This work explores the computational complexity of image processing techniques to analyse chromatic properties and textural features for tongue image segmentation. The dynamic and novel approach of this work involves consideration of skin colour covering various range of contrast diversity while image segmentation, making it distinct from existing works. The aim of this research is to seek for an algorithm with reduced computational complexity suitable to be implemented in an enhanced mobile enable solution. The algorithm for tongue image processing needs to be fast and less complex making the system apt for mobile devices executing automatic tongue diagnosis entailing clinical decision support system. Analysing the performance of different colour models, RGB was unveiled to have a better enactment than others. The performance of edge detection techniques were evaluated on images with close contrast difference based on segmentation result and processing time. The morphological processing showed better result to separate the tongue from its background which can be further employed for geometric shape based disease diagnosis.

7 citations