A Novel Illumination Correction and Intensity Normalization Method on Cervigrams in the Early Detection of Uterine Cervical Cancer

Cervical Cancer is one of the ubiquitous forms of cancer afflicting the female population worldwide. A Colposcope is a self-illuminated microscope which acquires the image of the affected cervix and the image is known as a cervigram. The raw cervigram is preprocessed by removing the specular reflections and then the region of interest is sought. Before the image is made ready for implementing further image processing algorithms, our novel illumination correction and intensity normalization methods are applied. In the current paper we propose a novel method where we use the polynomial-type Newton’s divided difference interpolation for illumination correction. Based on our research findings, we conclude that the peak of the entire cervix region intensity distribution is strongly correlated with the peak of the SE region intensity distribution.