AN AUTOMATED TONGUE COLOR IMAGE ANALYSIS FOR DISEASE DIAGNOSIS AND CLASSIFICATION USING DEEP LEARNING TECHNIQUES
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 7, Pages 4779-4796
AbstractTongue diagnosis is considered an effectual and non-invasive technique commonly used to carry out the secondary diagnosis at anytime and anywhere. Opportunely, computational models for image processing approaches in tongue are presented in the literature and obtained significant performance. Several tongue image analysis techniques are available, it is still needed to design an automated deep learning (DL) models for diagnosing the diseases through tongue image analysis. In this view, this paper devises a new automated DL based tongue color image analysis for disease diagnosis and classification. The presented technique makes use of distinct processes such as preprocessing, feature extraction, and classification. At the preprocessing stage, the presented model performsdata augmentation and gaussian filtering (GF) techniques for noise removal. Besides, the DL based Visual Geometry Group (VGG19), a convolutional neural network (CNN) model is applied to extract the useful set of feature vectors from the preprocessed image. In addition, the presented model utilizes two machine learning (ML) based classifiers such as random forest (RF) and gaussian naïve bayes (GNB) to perform classification processes. For theassessmentof the classification outcome of the presented technique, benchmark tongue image dataset is used. The experimental values pointed out that the presented VGG19-RF model has reached a higher precision, recall, accuracy, and F1-Score of 93.80%, 93.70%, 93.70%, and 93.68% respectively.
- Article View: 12
- PDF Download: 13