Skripsi
KOMBINASI METODE GAUSSIAN FILTER DAN GAMMA CORRECTION UNTUK PERBAIKAN CITRA PADA SEGMENTASI SEL NUKLEUS CITRA PAP SMEAR
The nucleus is an important element in cervical cells that will undergo significant changes if someone is exposed to cervical cancer. Early detection of cervical cancer can be done using pap smear image segmentation by separating the nuclear and cytoplasmic cells. However, the pap smear image from the Zenodo dataset is still not good, so an image improvement process is needed. The image improvement process carried out in this study is using the Gaussian filter and the gamma correction methods. The segmentation process is continued by using the Otsu thresholding method. This research used data from the Zenodo dataset as input for the Pap smear image and then this data is converted into a grayscale image and then continued with the image improvement process using the Gaussian filter and gamma correction methods. Furthermore, the segmentation process is carried out using the Otsu thresholding method. The performance output of image improvement with MSE (Mean Square Error) is 3.260395, 43.11875 dB for PSNR (Peak Signal to Noise Ratio) and 0.9980594 for SSIM (Structural Similarity Index Metrics). The performance of image segmentation results in the form of an accuracy of 96.31%, sensitivity of 96.84% and specificity of 94.55%. Based on the MSE, PSNR and SSIM values, the results of the image repair that have been carried out are good and the performance of the segmentation results obtained is quite accurate.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307006774 | T134788 | T1347882022 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available