is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism

background regions of the image to be quickly discarded while spending more computation on promising object-like regions. A set of experiments in the domain of face detection are presented. The system yields face detection performace comparable to the best previous systems [18, 13, 16, 12, 1]. Implemented

-in numerous regions containing completely different structures and surrounding backgrounds. In addition, no limitations are imposed on the topology of the region to be inpainted. Applications of this technique include the restoration of old photographs and damaged film; removal of superimposed text like dates

In the QBIC (Query By Image Content) project we are studying methods to query large on-line image databases using the images' content as the basis of the queries. Examples of the content we use include color, texture, and shape of image objects and regions. Potential applications include

sets and with a unique superset. In the regions delimited by the membranes there are placed objects; the obtained construct is called a super-cell. These objects are assumed to evolve: each object can be transformed in other objects, can pas through a membrane, or can disolve the membrane in which

like Treasury bonds, and (2) low-grade bonds are more sensitive to stock returns. The implications of these studies may be limited in many situations of interest, however. For example, hedge funds often take highly levered positions in corporate bonds while hedging away interest rate risk by shorting

is not discriminative enough, the outputs of these algorithms are usually not object consistent. To tackle this problem, we introduce the concept of object-like regions as a new and higher level processing primitive. We first experimentally showed that using groundtruth segments as pro-cessing primitives can boost

implicitly and independently of declarative memory. However, these studies have relied on dot pattern stimuli that, unlike most real-world objects, are difficult to verbalize and cannot be broken into component features. It is therefore unclear how relevant such studies are to an understanding

representations of the foreground regions (moving objects) that support their tracking and support occlusion reasoning. The probability density functions (pdfs) associated with the background and foreground are likely to vary from image to image and will not in general have a known parametric form. We accordingly

Detection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. In this paper, we introduce a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects