원문정보
초록
영어
In this paper, we apply a set of algorithms to classify normal and cancer nucleus from
uterine cervical pap-smear images. First, we use lightening compensation algorithm to re-
store color images that have defamation through the process of obtaining 400x microscope
magnification. Then, we remove the background from images with the histogram distribu-
tions of RGB regions. We extract nucleus areas from candidates by applying histogram
brightness, Kapur method, and our own 8-direction contour tracing algorithm. Various bi-
narization methods, cumulative entropy, masking algorithms are used in that process. Then,
we are able to recognize normal and cancer nucleus from those areas by using three mor-
phological features - directional information, the size of nucleus, and area ratio - with fuzzy
membership functions and deciding rules we devised. The experimental result shows our
method has low false recognition rate.
목차
1: Introduction
2: Cell Nucleus Area Extraction Process
2.1: Image Stabilization by Lighting Compensation
2.2: Removal of Background Using the Histogram Distribution
2.3: Separation of Cytoplasm and Nucleus Using the Intensity Value
2.4: Cell Nucleus Binarization by Kapur Method
3: Extraction of Cell Nucleus Characteristics
3.1: Directional Information of Cell Nucleus
3.2: Area ratio in Cell Nucleus
3.3: Size of Nucleus
4: Designing Membership Functions for Nucleus Recognition & Nucleus Recognition by Fuzzy Reasoning Rules
5: Methods and Results
6: Conclusion
References