Andere Kunden interessierten sich auch für
![Development of CADx System for detection of anomalies in breast]( "Development of CADx System for detection of anomalies in breast")
Development of CADx System for detection of anomalies in breast26,99 €![Human emotional state recognition using 3D facial expression features]( "Human emotional state recognition using 3D facial expression features")
Human emotional state recognition using 3D facial expression features38,99 €![Advancement in the Detection of Diabetic Retinopathy]( "Advancement in the Detection of Diabetic Retinopathy")
Advancement in the Detection of Diabetic Retinopathy40,99 €![Morphological Image Analysis]( "Morphological Image Analysis")
Morphological Image Analysis154,99 €![Morphological Image Analysis]( "Morphological Image Analysis")
Morphological Image Analysis147,99 €![Enabling active locomotion and advanced features in capsule endoscopy]( "Enabling active locomotion and advanced features in capsule endoscopy")
Enabling active locomotion and advanced features in capsule endoscopy40,99 €![Person Identification System using Handwritten signatures by ANN]( "Person Identification System using Handwritten signatures by ANN")
Person Identification System using Handwritten signatures by ANN26,99 €
Diabetes mellitus (DM) and its complications leading to diabetic retinopathy (DR) are among the leading causes of death and disabilities. This research advocates detection of DR and NPDR using tongue images by extracting features like color, texture and geometry. Color gamut with 12 colors represent tongue color features where percent amount of a particular color helps in detecting the type of disease, eight blocks located on tongue along with their texture values of each block characterize eight tongue texture features, further measurements, distances, areas, and their ratios of the geometry of the tongue represent 11 geometry features. Combination of all the 30 features together help to separate Healthy/DM as well as NPDR/DM-sans NPDR tongues along with their average accuracies. The classification is done using Artificial Neural Networks. The training dataset is used for training the classifier which is then tested with the testing dataset. Hence, this non-invasive method for DM and NPDR detection will be beneficial to patients for early detection of diseases.