Identifikasi Citra Pap Smear RepoMedUNM dengan Menggunakan
K-Means Clustering dan GLCM

Identifikasi Citra Pap Smear RepoMedUNM dengan Menggunakan
K-Means Clustering dan GLCM

Pap Smear, ThinPrep, Non-ThinPrep, RepoMedUNM, K-Means, GLCM

Cervical cancer’s a gynecological malignancy in women that’s very dangerous, even causes death. Prevention through early
detection of Pap smear test. It was carried out by pathologists with the help of a microscope still have obstacles in observations.
There’re many studies on Pap smear image processing for helping pathologists in cell identification. Availability of Pap smear
image dataset is needed in cervical cancer early detection research. The purpose of this study was to segment, feature extraction
and classify 180 Pap smear images of RepoMedUNM. The method used to identify Pap smear images begins with
preprocessing, namely changing the color in the image to L*a*b color, segmentation using the K-means method, extraction of
6 features, namely metric, eccentricity, contrast, correlation, energy, and homogeneity, and then identified by calculating the
closest distance between the training data features and the test data features with the Euclidean distance. The result of
identification ThinPrep Pap smear images in 3 classes achieve average accuracy of 93.33%, Non-ThinPrep Pap smear images
in 2 classes achieve 90% average accuracy and the average accuracy of the overall in the 4 classes reached 92%. These results
indicate that the proposed method can identify Pap smear images well.

Dwiza Riana1
, Sri Rahayu2
, Sri Hadianti3
, Frieyadie4
, Muhamad Hasan5
, Izni Nur Karimah6
, Rafly Pratama7

, Universitas Nusa Mandiri
2,3,6,7Informatika, Fakultas Teknologi Informasi, Universitas Nusa Mandiri
4,5Sistem Informasi, Fakultas Teknologi Informasi, Universitas Nusa Mandiri

1 februari 2022

Fajar bagus W

PDF

Indonesia

Text