Contrast Enhancement of Microscopic Malaria Images using Modified Linear Contrast Stretching with Color Preserving Framework

The digital image acquisition of blood smears using a microscope may result
in low-contrast images. Low contrast images make identifying Plasmodium-infected cells
difficult, which can lead to false diagnoses. Several methods of contrast improvement in
malaria images can cause color changes in the processed image. In this paper, we proposed
an improved method to enhance the contrast of color malaria images while retaining
the coloring structure of the original image. The proposed method used the average value
of local and global features to reduce the total dependency on each color component.
Furthermore, the color preservation framework was used to improve the maintenance
of color information. Based on the experimental results using the MP-IDB dataset, the
proposed IMLCS-CPF method gave the best PNSR and AMBE values compared to LCS,
MLCS, and IMLCS methods. Visually, the proposed method provided better contrast enhancement
while preserving the color information of the original image, thus clarifying
the appearance of Plasmodium and erythrocytes in the image of thin blood smears. The
enhanced images are expected to help improve the performance of visual examination
of malaria through a microscope or facilitate the segmentation process in an automatic
malaria diagnosis system.