The goal of this work is to build a better automatic segmentation method for microarray images. Segmentation is a partitioning process used to separate a spot area from a non-spot area in microarrays. It directly affects the accuracy of gene expression analysis in the data mining process that follows. A number of DNA microarray segmentation methods have been proposed in the area, but even modern segmentation methods seem to have accuracy problems. Image Analysis remains one of the major challenges in image Processing. Numerous segmentation algorithms have been developed for a variety of applications. Disappointing outcome has been stumble upon in some cases, for several existing segmentation methods. In our work , we have to improve Performance of the Globally Optimal Geodesic Active Contours method for image segmentation . Analysis will be done using standard images (i.e. The Stanford Microarray Database ). The qualitative analysis will be done to prove that the proposed methods are less perceptive with respect to noise. As such, the rate of in proper segmentation, pixel loss and trapped center at local minima problems can be avoided. In proposed method, we have to show the results of automatic GOGAC Segmentation method.