Texture based segmentation is an important and challenging factor in image processing system which refers to the process of partitioning a digital image into multiple constituent segments. The goal of image segmentation is to cluster pixels into salient image regions, i.e. regions corresponding to individual surfaces, objects, or natural parts of objects. In this paper we propose a new Artificial Neural Network (ANN) Based texture classification or segmentation is typically used to locate objects of interest in an image. In this approach ANN is implemented to segment the image. Feed forward and back propagation of ANN is configured and trained so that it becomes capable of segmenting an image. The current work deals with a task where an object of interest is to be segmented out of a background for processes which can be carried out as part of extended applications.