ABSTRACT
Microarray technology is increasingly used as a means of high throughput analysis of human, non-human and plant genomes. Manual methods of array production using this technology lead to many inherent problems in the microarray image produced. The density of the spots in the images produced is very high, such that neighboring spots can overlap. The image background is often not uniform, containing noise that is often difficult to distinguish from actual spots. In this research, a projections-based approach is investigated for spot segmentation in paired radio probe microarray images. An important aspect of spot segmentation is the capability to perform corresponding spot-to-spot comparisons between the paired images. Experimental results are presented for spot segmentation in isolated and paired microarray images.
