A Double Layered Segmentation Algorithm for Cervical Cell Images based on GHFCM and ABC

• Published in: International journal of image, graphics and signal processing Vol. 9; no. 11; pp. 39 - 47
• Main Authors: Anna Lakshmi, G., Ravi, S.
• Format: Journal Article
• Language: English
• Published: Hong Kong Modern Education and Computer Science Press 08.11.2017
• Subjects: Adaptive filters; Algorithms; Diagnostic systems; Equalization; Image contrast; Image enhancement; Image quality; Image segmentation; Medical science; Sensitivity analysis; Swarm intelligence
• ISSN: 2074-9074; 2074-9082; 2074-9082
• DOI: 10.5815/ijigsp.2017.11.05

Cancer is a life threatening disease and it engulfs the lives of many women. Due to the technology advancement, the medical science is drastically improved. A statistical report claims that the diagnostic decisions of radiologists show more false positive rates, which is very dangerous. However, when the radiologists are supported by computer aided applications, the false positive results are considerably reduced. Understanding the potentiality of computer aided applications, this paper presents a double layered segmentation algorithm for cervical cell images. The entire work is subdivided into three important phases, which are cervical image pre-processing, coarse and fine level segmentation. The pre-processing phase attempts to remove the noise and enhance the image quality by means of adaptive mean filter and Contrast Limited Adaptive Histogram Equalization (CLAHE) technique respectively. The coarse level segmentation process is achieved by Generalized Hierarchical Fuzzy C Means (GHFCM) and the fine level segmentation process is carried out by Artificial Bee Colony (ABC) algorithm. The performance of the proposed segmentation algorithm is analysed in terms of accuracy, sensitivity and specificity. The experimental results show the efficacy of the proposed segmentation algorithm.