Contrast Enhancement of Cancer Cell Images Using Fuzzy Logic

Image contrast enhancement is a widely used technique in image processing, which aims to improve the contrasts of degraded images. Low contrast is one of the most common defects of photographic, medical and electronic images and consequently enhancing the contrasts of the degraded images becomes necessary. In the present study, four contrast enhancement methods, Fuzzy Inference System (FIS), Global Histogram Equalization (GHE), Brightness preserving Bi-Histogram Equalization (BBHE) and Brightness Preserving Dynamic Fuzzy Histogram Equalization (BPDFHE) were applied on MATLAB popular images and also on microscopic images of in vitro cell migration assay. Efficiency of the techniques in contrast enhancement and mean brightness preservation were compared based on the output images and the resulted histograms. In general, Histogram Equalization (HE) based methods could enhance the contrast of the images better than the introduced Fuzzy Inference system. BPDFHE demonstrated the highest efficiency in contrast enhancement and mean brightness preservation of the images, representing great potential for further applications in photographic, electronic and medical image processing.

Katayoun Sayar holds Bachelor of Electrical and Electronics Engineering from University of Malaya (UM). Her research interests particularly focus on Artificial Intelligence and Fuzzy Logic, Biomedical Image Processing, Tissue Engineering and the Engineering of Cell Microenvironment based on Novel Magnetic Hydrogel.