AN ADAPTIVE THRESHOLD SEGMENTATION FOR DETECTION OF NUCLEI IN CERVICAL CELLS USING WAVELET SHRINKAGE ALGORITHMS
2013
PAP smear test is the most efficient and easy procedure to detect any abnormality in cervical cells. It becomes difficult for the cytologist to analyse a large set of PAP smear test images when there is a rapid increase in the incidence of cervical cancer. On the replacement, image analysis could swap manual interpretation. This paper proposes a method for the detection of cervical cells in pap smear images using wavelet based thresholding. First, Wiener filter is used for smoothing to suppress the noise and to improve the contrast of the image. Second, optimal threshold is been obtained for segmenting the cell by various Wavelet shrinkage techniques like VisuShrink, BayesShrink and SureShrink thresholding which segment the foreground from the background and detect cell component like nucleus from the clustered cell images. From the results, it is proved that the performance of the adaptive Wiener filter with combination of SureShrink thresholding performs better in terms of threshold values and Mean Squared Error than the other comparative methods. The succeeding research work can be carried out based on the size of the segmented nucleus which therefore helps in differentiating abnormality among the cells.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
7
References
3
Citations
NaN
KQI