Andere Kunden interessierten sich auch für
![An Improved Hybrid Hierarchical Model for Breast Cancer Detection]( "An Improved Hybrid Hierarchical Model for Breast Cancer Detection")
An Improved Hybrid Hierarchical Model for Breast Cancer Detection51,99 €![Development and Performance Evaluation of Texture Based CBIR Algorithm]( "Development and Performance Evaluation of Texture Based CBIR Algorithm")
Development and Performance Evaluation of Texture Based CBIR Algorithm46,99 €![DM AND NPDR DETECTION USING TONGUE COLOR, TEXTURE AND GEOMETRY FEATURES]( "DM AND NPDR DETECTION USING TONGUE COLOR, TEXTURE AND GEOMETRY FEATURES")
DM AND NPDR DETECTION USING TONGUE COLOR, TEXTURE AND GEOMETRY FEATURES26,99 €![Compact Patch Antenna Array for Breast Cancer Detection]( "Compact Patch Antenna Array for Breast Cancer Detection")
Compact Patch Antenna Array for Breast Cancer Detection32,99 €![Diagnosis of Physiological Anomalies From Natural Speech]( "Diagnosis of Physiological Anomalies From Natural Speech")
Diagnosis of Physiological Anomalies From Natural Speech36,99 €![Certain Survey on Microwave Imaging for Breast Cancer Diagnosis System]( "Certain Survey on Microwave Imaging for Breast Cancer Diagnosis System")
Certain Survey on Microwave Imaging for Breast Cancer Diagnosis System26,99 €![Spectrum Efficiency Maximization in Cognitive Radio Systems]( "Spectrum Efficiency Maximization in Cognitive Radio Systems")
Spectrum Efficiency Maximization in Cognitive Radio Systems51,99 €
A dataset of 322 images from Mammographic Image Analysis Society (MIAS). The images are pre-processed with Adaptive Median filter for noise removal and image enhancement. For ROI extraction original image having 1024 x1024 pixels are cropped into 256x256 pixels. The images are segmented using Gaussian Mixture Model for extracting the actual tumour area. We have considered 20 benign, 20 malignant and 20 normal images cases of circumscribed, speculated and ill-defined masses from the database. Each mass is represented with 22 texture features. The PNN classifier is used to perform the classification tasks on 60 images. The input images are classified into three different training -testing datasets as 50-50%,70-30% and 80-20%. With the help of PNN classifier, Sensitivity, Specificity and Accuracy are calculated for each of the dataset. For 50-50% training-testing dataset, Specificity, Sensitivity and Accuracy obtaining are 50%, 50% and 50% respectively. For 70-30% training-testing dataset, Specificity, Sensitivity and Accuracy obtaining are 75%, 100% and 100% respectively. 80-20% training-testing dataset gave the promising results with the Specificity, Sensitivity and Accuracy of 100%