... This paper provides an up-to-date critical survey of still- and video-based face recognition research. There are two underlying motivations for us to write this survey paper: the first is to provide an up-to-date review of the existing literature, and the second is to offer some insights into the studies of machine recognition of faces. To provide a comprehensive survey, we not only categorize existing recognition techniques but also present detailed descriptions of representative methods within each category. In addition,

Abstract — We study the problem of detecting objects in still, grayscale images. Our primary focus is development of a learning-based approach to the problem, that makes use of a sparse, part-based representation. A vocabulary of distinctive object parts is automatically constructed from a set of sample images of the object class of interest; images are then represented using parts from this vocabulary, together with spatial relations observed among the parts. Based on this representation, a learning algorithm is used to automatically learn to detect instances of the object class in new images. The approach can be applied to any object with distinguishable parts in a relatively fixed spatial configuration; it is evaluated here on difficult sets of real-world images containing side views of cars, and is seen to successfully detect objects in varying conditions amidst background clutter and mild occlusion. In evaluating object detection approaches, several important methodological issues arise that have not been satisfactorily addressed in previous work. A secondary focus of this paper is to highlight these issues and to develop rigorous evaluation standards for the object detection problem. A critical evaluation of our approach under the proposed standards is presented.

The paper is a overview of the major qualitative spatial representation and reasoning techniques. We survey the main aspects of the representation of qualitative knowledge including ontological aspects, topology, distance, orientation and shape. We also consider qualitative spatial reasoning including reasoning about spatial change. Finally there is a discussion of theoretical results and a glimpse of future work. The paper is a revised and condensed version of [33, 34].

We report four experiments that investigated the representation of novel three-dimensional (3D) objects by the human visual system. In the first experiment, canonical views were demonstrated for novel objects seen equally often from all test viewpoints. The next two experiments showed that the canonical views persisted under repeated testing, and in the presence of a variety of depth cues, including binocular stereo. The fourth experiment probed the ability of subjects to generalize recognition to unfamiliar views of objects previously seen at a limited range of attitudes. Both mono and stereo conditions yielded the same increase in the error rate with misorientation relative to the training attitude. Taken together, these results support the notion that 3D objects are represented by multiple specific views, possibly augmented by partial viewer-centered 3D information. 3D object recognition Canonical views Novel views Stereo 1.

Abstract not found

Advanced perceptual systems are faced with the problem of securing a principled relationship between the world and its internal representation. I propose a unified approach to visual representation, based on Shepard's (1968) notion of second-order isomorphism. According to the proposed theory, a shape is represented internally by the responses of a few tuned modules, each of which is broadly selective for some reference shape, whose similarity to the stimulus it measures. The result is a philosophically appealing, computationally feasible, biologically credible, and formally veridical representation of a distal shape space. This approach supports representation of and discrimination among shapes radically different from the reference ones, while bypassing the need for the computationally problematic decomposition into parts; it also addresses the needs of shape categorization, and can be used to derive a range of models of perceived similarity. Representation is Representation of Sim...

We study the problem of object classification when training and test classes are disjoint, i.e. no training examples of the target classes are available. This setup has hardly been studied in computer vision research, but it is the rule rather than the exception, because the world contains tens of thousands of different object classes and for only a very few of them image, collections have been formed and annotated with suitable class labels. In this paper, we tackle the problem by introducing attribute-based classification. It performs object detection based on a human-specified high-level description of the target objects instead of training images. The description consists of arbitrary semantic attributes, like shape, color or even geographic information. Because such properties transcend the specific learning task at hand, they can be pre-learned, e.g. from image datasets unrelated to the current task. Afterwards, new classes can be detected based on their attribute representation, without the need for a new training phase. In order to evaluate our method and to facilitate research in this area, we have assembled a new largescale dataset, “Animals with Attributes”, of over 30,000 animal images that match the 50 classes in Osherson’s classic table of how strongly humans associate 85 semantic attributes with animal classes. Our experiments show that by using an attribute layer it is indeed possible to build a learning object detection system that does not require any training images of the target classes. 1.

Many researchers interested in connectionist models accept that such models are "neurally inspired " but do not worry too much about whether their models are biologically realistic. While such a position may be perfectly justifiable, the present paper attempts to illustrate how biological information can be used to constrain connectionist models. Two particular areas are discussed. The first section deals with visual information processing in the primate and human visual system. It is argued that speed with which visual information is processed imposes major constraints on the architecture and operation of the visual system. In particular, it seems that a great deal of processing must depend on a single bottum-up pass. The second section deals with biological aspects of learning algorithms. It is argued that although there is good evidence for certain coactivation related synaptic modification schemes, other learning mechanisms, including back-propagation, are not currently supported by experimental data.

We propose a model of the spatial visual processes underlying the identification and representation of the shape of primitive spatial regions. We propose that a region's boundaries are sensed at multiple scales by boundariness detectors that give graded responses, that stimulated boundariness detectors of similar scale, s, connect to one another across a distance that is proportional to their scale, and that they connect via cores, where a core encodes the middles and widths of the region and hence is a trace in (x,y,s), i.e., 3D scale space. 3 INTRODUCTION One of the more impressive feats that the human visual system performs is the identification of individual objects from the continuous distribution of light that falls on the retina. To accomplish this task, the observer uses information from the image to identify regions of interest on the basis of spatial changes in luminance, color, texture, motion, etc. He also interprets information from the image on the basis of prior experi...

We describe some techniques that can be used to represent and detect deformable shapes in images. The main di#culty with deformable template models is the very large or infinite number of possible non-rigid transformations of the templates. This makes the problem of finding an optimal match of a deformable template to an image incredibly hard. Using a new representation for deformable shapes we show how to e#ciently find a global optimal solution to the non-rigid matching problem. The representation is based on the description of objects using triangulated polygons. Our matching algorithm can minimize a large class of energy functions, making it applicable to a wide range of problems. We present experimental results of detecting shapes in medical images and images of natural scenes. Our method does not depend on initialization and is very robust, yielding good matches even in images with high clutter.