Image segmentation is a central problem in image analysis. It consists of extracting objects from an image and separating between the background and the regions of interest. In the literature, there are mainly two dual approaches, namely the region-based segmentation and the edge-based segmentation. In this article, we propose to take advantage of Game theory in image segmentation by results fusion. Thus, the presented game is cooperative in a way that both players represented by the two segmentation modules (region-based and edge-based) try coalitionary to enhance the value of a common characteristic function. This is a variant of the parallel decision-making procedure based on Game theory proposed by Chakraborty and Duncan [1]. The involved pixels are those generated from the cooperation by results fusion between the edge detector (Active contour) and the region detector (Region growing) posing a decision-making problem. Adding or removing a pixel (to/from) the region of interest depends strongly on the value of the characteristic function. Then, and to study the effectiveness and noise robustness of our approach we proposed to generalize our experimentations, by applying this technique on a variety of images of different types taken mainly from two known test databases.