Detail Publikasi

Klasifikasi Statistikal Tekstur Sel Pap Smear Dengan Decesion Tree

• By TONI ARIFIN

Abstrak

This research presents the texture analysis and classification of cells pap smear image. Texture
analysis focused on the cell nucleus Pap smear image, the research method used the Gray Level
Co-occurrence Matrix (GLCM) method, by using five parameter that include contrast, correlation,
energy, homogeneity, entropy and brightness. The image used in this research using image data
Harlev. The images from 280 subjects are categorized into seven classes. Three classes of which
are normal cell image class categories that include Normal Superficial, Normal Intermediate, and
Normal Columnar, and the other four classes are categories of abnormal cell image class that
include Mild (Light) Dyplasia, Moderate Dysplasia, Severe Dysplasia and Carcinoma In Situ.
Based on the results of image processing that produces a matrix of values of each parameter were
calculated, Pap smear cell image will be classified according to the type of normal or abnormal
and based on the class using the decision tree treated with algorithm clasifier J48 in weka
applications. To the resulting accuracy of the classification normal and abnormal cells is 73% and
for seven class classification accuracy is 34,3%.

Kata Kunci:
Classification, Statistical Texture, Cell Pap Smear, Decision Tree