Image analysis and segmentation using gray connected components

We investigated a new definition for the connected components of gray images, which are called (ε,δ)-components, that takes into account both the gray values of the pixels and the differences of the gray values of the neighboring pixels. In this paper, we describe a method to understand the structure of the gray images in an intermediate level through the (ε,δ)-component histograms. Also, for appropriate values of ε and δ, an object in an image may be represented by an (ε,δ)-component reasonably well. We discuss a method to adjust the values of ε and δ so that object extraction and segmentation may be done by locating the corresponding (ε,δ)-components. Since we do not make any assumptions about the formation model of the image data, our proposed method could be applied to many types of images. Thus, our approach provides a possible method of transition from low level computer vision to a higher level vision