Computer Aided Tongue Diagnosis System using Color and Texture Feature Extraction-based Deep Learning CNN
Main Article Content
Abstract
Tongue diagnosis is an important way of monitoring human health status in Indian ayurvedic medicine (IAM), which helps to identify the different diseases of human through tongue image analysis. Several machine learning models are presented to classify the diseases through tongue image analysis. However, they are suffering with the low classification performance due to variations in tongue appearance such as color, shape, coating, and texture properties. Therefore, this article focuses on deep learning convolutional neural network (DLCNN) for disease predication through tongue image analysis, which is hereafter named as Tongue-Net. Initially, fast nonlocal mean (FNLM) filtering is applied on given tongue image for preprocessing operations such as noise removal, and quality enhancement. Next, color features from preprocessed tongue image are extracted using color statistics such as mean, skewness, and standard deviation. In addition, grey level cooccurrence matrix (GLCM) and local binary pattern (LBP) approaches are used extract the texture and shape features. Finally, DLCNN classifier is used to classify the different diseases from extracted features. The proposed Tongue-Net model is capable of predicting six distinct diseases including the healthy, appendicitis, bronchitis, gastritis, heart disease, and pancreatitis disease. The simulation results shows that proposed Tongue-Net classification model obtained 97.90% of accuracy, and 98.01% of F1-score
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.