âšī¸ Informasi Berkas Arsip: Metadata koleksi ini tersedia di database, namun berkas fisik --drsarivazh-567-1-vol3no10-6.pdf belum disalin ke direktori penyimpanan server (./files/disk1/ atau ./files/uploads/). Anda tetap dapat membaca/mencetak lembar katalog ini atau mengunggah berkas PDF melalui menu Edit Koleksi.
Skin Disease Classification by Extracting Independent Components
Penulis: Dr. S.Arivazhagan, Mrs. R.Newlin Shebiah, Ms. K.Divya, Ms. M.P.Subadevi •
Identifier: --drsarivazh-567
This paper proposes an automated system based on texture analysis for recognizing human skin diseases. The spatial distributions of melanin and hemoglobin in human skin are separated by independent component analysis of skin color image. The texture features were derived from Gray Level Run Length Matrices. Minimum Distance Classifier is used to classify the type of human skin diseases. About 350 images from DERMNET database are used for evaluation and the recognition rate is found to be satisfactory.