Mathematical Morphology Based Enhancement for Chromosome Images

Chromosome images were acquired by microscopic imaging of metaphase or prophase cells on specimen slides. Digitized chromosome images usually suffer from poor image quality, particularly lack of contrast and presence of shading and artifacts. So these images must be enhanced. This paper presented an enhancement algorithm for chromosome images based on mathematical morphology. Firstly, the top-hat transform and bot-hat transform were used to improve the contrast of the images. Then, the iterative threshold segment, closing operation and opening operation were operated on the result respectively. The final result was obtained by the and operation being operated on the two results. To validate the effect of this algorithm, the Canny edge detection operator was used to detect the edges of chromosomes in the original images and those being enhanced by this algorithm respectively. The experiment proved that the algorithm can improve the contrast of the image effectively and also can remove noise of the image.