Perception-Based Image Segmentation Using the Bounded Irregular Pyramid Rebeca Marfil, Antonio Bandera, and Francisco Sandoval Grupo ISIS, Dpto. Tecnolog´ ıaElectr´onica ETSI Telecomunicaci´on, Universidad de M´alaga Campus de Teatinos 29071-M´ alaga (Spain) Abstract. This paper presents a bottom-up approach for fast segmen- tation of natural images. This approach has two main stages: firstly, it detects the homogeneous regions of the input image using a colour-based distance and then, it merges these regions using a more complex distance. Basically, this distance complements a contrast measure defined between regions with internal region descriptors and with attributes of the shared boundary. These two stages are performed over the same hierarchical framework: the Bounded Irregular Pyramid (BIP). The performance of the proposed algorithm has been quantitatively evaluated with respect to ground-truth segmentation data. 1 Introduction Image segmentation is typically defined as the low-level process of grouping pixels into clusters which present homogeneous photometric properties. However, if the goal of the segmentation process is to divide the input image in a manner similar to human beings, then this definition is not valid. Natural images are generally composed of physically disjoint objects whose associated groups of image pixels may not be visually uniform. This makes extremely difficult to formulate what should be recovered as a region from an image or to separate complex objects from a natural scene [4]. In order to reduce the complexity of segmenting real objects from their back- ground, the particular application could be taken into account. In these cases, the higher-level information is known a priori and it can be used to group the image pixels into logical regions that resemble the real objects. To maintain the generality of use, several authors have proposed generic segmentation methods which are based neither on a priori knowledge of the image content nor on any ob- ject model [1,3]. These approaches typically combine a pre-segmentation stage with a subsequent perceptual grouping stage. Basically, the pre-segmentation stage conducts the low-level definition of segmentation as a process of grouping pixels into homogeneous clusters and the perceptual grouping stage performs a domain-independent grouping which is mainly based on properties like the prox- imity, similarity, closure or continuity. Although the final obtained regions do not always correspond to the natural image objects, they provides a mid-level seg- mentation which is more coherent with the human-based image decomposition. F.A. Hamprecht, C. Schn¨orr, and B. J¨ahne (Eds.): DAGM 2007, LNCS 4713, pp. 244–253, 2007. c  Springer-Verlag Berlin Heidelberg 2007