Spot segmentation and verification based on improve marker controlled watershed transform

Two-dimensional gel electrophoresis (2D-GE) is the powerful technique used by biochemists to resolve and visualize protein samples. The 2D-GE images depict protein signals as spots of various intensities and sizes. Currently, the most popular technique for spot detection in 2D-GE image is the watershed transform (WST) due to its robustness. However presence of noise in 2D-GE images forces WST to oversegment them. In this paper, we present a two-stage protein spot detection approach, which is achieved by improve marker controlled watershed transform (MCWST) followed by spot verification. Experiments results show that the proposed method is robust in noised image and results in low spurious spot detection rate.