In a memorable scene from The Wizard of Oz, Dorothy is catapulted by a ferocious tornado from a drab, grey-scale Midwest existence into the land of Oz, a world that is portrayed in full-scale, technocolor vision. In the film, the transition from black-and-white to color images is a striking cinematographic technique alerting Dorothy and the audience that we are indeed 'not in Kansas anymore'. However, whilst the aesthetic value of color in the visual arts is undeniable, the contribution of color to everyday vision, especially the stage of vision concerned with object recognition, is more controversial. Does the presence of color help us recognize objects in our world? Are we any faster or more accurate in recognizing an apple when it is seen in color versus black-and-white? This article focuses on the functional contributions that color makes to the way humans perceive and recognize objects. Drawing upon converging evidence from behavioral, neuroimaging and neuropsychological methodologies, we present a framework that emphasizes the interaction between object color perception and object color knowledge in recognition. Color in low-level vision Neurophysiological research has revealed that a significant amount of visual processing is dedicated to the analysis of color information. When light enters the eye, the composition of wavelength energy is captured by specialized retinal photoreceptors (cones), which in turn send their outputs to specific cells in the lateral geniculate nucleus (LGN) (Ref. 1). Wavelengthcoded signals from the LGN, which are essential for the processing and perception of color information, are then transmitted along specialized pathways to cortical visual areas V1, V2 and V4 (Ref. 2). Given that the brain has developed specialized mechanisms to handle the color information in the visual environment, it is a fair question to ask what functional role color might play in everyday vision. Whereas other mammals possess dichromatic or monochromatic color vision, it is only primates that are endowed with three types of cone photoreceptors and thereby have trichromatic color vision. What ecological advantage does this give primates over animals with dichromatic or monochromatic vision? Recently, Sumner and Mollon found that the photopigments of primates are optimized for differentiating edible fruits and young leaves amongst a background of mature leaves 3 . In this case, the additional dimension of trichromatic color vision gives primates a behavioral advantage when having to select edible fruits and plants from a complex scene. Similarly, during the early stages of low-level visual processing, it has been shown that color is a useful cue for segregating and organizing visual input into three-dimensional objects and scenes Color in high-level vision Although keen color vision might give humans an adaptive edge in the early stage of visual processing, the role that color plays in later stages of object recognition has been a point of contention in the literature. On one side of the issue, 'edge-based' theories, such as Biederman's recognition-bycomponents model 8 , claim that objects are recognized solely on the basis of their shape properties. According to the edge-based approach, representations mediating initial object recognition contain information about an object's shape, but no information about the surface properties of an object, such as its color or texture. By contrast, 'surface-plus-edge-based' theories allow for object representations to include information, not only about an object's shape, but also about its surface properties, such as color and texture The competing claims of the two approaches should be testable in behavioral experiments by examining whether there is an advantage for recognizing the chromatic version of an object over its achromatic version. However, this relatively straightforward test has yielded mixed results. Some studies have shown that recognition times are essentially unaffected when objects are presented in their appropriate colors (e.g. a yellow banana), inappropriate colors (e.g. a purple banana) or in black-and-white 11-13 , which would support the Traditional theories of object recognition have emphasized the role of shape information in high-level vision. However, the accumulating behavioral, neuroimaging and neuropsychological evidence indicates that the surface color of an object affects its recognition. In this article, we discuss the research that examines the conditions under which color influences the operations of high-level vision and the neural substrates that might mediate these operations. The relationship between object color and object recognition is summarized in the 'Shape + Surface' model of high-level vision.

This paper examines issues arising in applying a previously developed edit-distance shock graph matching technique to indexing into large shape databases. This approach compares the shock graph topology and attributes to produce a similarity metric, and results in 100% recognition rate in querying a database of approximately 200 shapes.

www.elsevier.com/locate/visres

To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Daily life situations, however, typically require categorization, rather than recognition, of objects. Due to the openended character both of natural kinds and of artificial categories, categorization cannot rely on interpolation between stored examples. Nonetheless, knowledge of several representative members, or prototypes, of each of the categories of interest can still provide the necessary computational substrate for the categorization of new instances. The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readil...

Does color improve object recognition? If so, is the improvement greater for images with low spatial resolution in which there is less shape information? Do people with low visual acuity benefit more from color? Three experiments measured reaction time (RT) and accuracy for naming food objects displayed in 4 types of images: gray scale or color, and high or low spatial resolution (produced by blur). Normally sighted Ss had faster RTs with color, but the improvement was not significantly greater for images with low spatial resolution. Low vision subjects were also faster with color, but the difference did not depend significantly on acuity. In 2 additional experiments, it was found that the faster RTs for color stimuli were related to objects ' prototypicality but not to their color diagnosticity. It was concluded that color does improve object recognition, and the mechanism is probably sensory rather than cognitive in origin. What is the function of color vision? Does it facilitate object recognition? Despite the impressive neural resources devoted to color vision and the perceptual salience of color, people with color-vision deficits (about 4 % of the popula-tion) experience very few difficulties. In fact, many color-

This paper describes how technical illustrations containing opaque and non-opaque objects can be automatically generated. Traditional methods to show transparency in manual drawings are evaluated to extract a small and effective set of rules for computer-based rendering of technical illustrations, leading to a novel view-dependent transparency model. We propose a hardware-accelerated depth sorting algorithm in image-space which specifically meets the requirements of our transparency model. In this way, real-time rendering of semi-transparent technical illustrations is achieved. Finally, it is described how our approach can be combined with other methods in the field of non-photorealistic rendering in order to enhance the visual perception of technical illustrations.

The use of outline shape in recognizing objects was investigated in four experiments. In Experiment 1, subjects matched a shaded image to either another shaded image or a silhouette. In Experiment 2, subjects initially named shaded images; later they named either shaded images or silhouettes. Performance in both experiments was predicted by changes in the outline shape of the stimuli. The same matching (Experiment 3) and priming (Experiment 4) paradigms were then used to investigate recognition with objects that were rotated between presentations so as to change the outline shape of the object. Recognition was predicted by changes to outline shape. These results place constraints on models of object recognition, and are most compatible with viewpoint-dependent models of recognition.

This paper addresses view-invariant object detection and pose estimation from a single image. While recent work focuses on object-centered representations of point-based object features, we revisit the viewer-centered framework, and use image contours as basic features. Given training examples of arbitrary views of an object, we learn a sparse object model in terms of a few view-dependent shape templates. The shape templates are jointly used for detecting object occurrences and estimating their 3D poses in a new image. Instrumental to this is our new mid-level feature, called bag of boundaries (BOB), aimed at lifting from individual edges toward their more informative summaries for identifying object boundaries amidst the background clutter. In inference, BOBs are placed on deformable grids both in the image and the shape templates, and then matched. This is formulated as a convex optimization problem that accommodates invariance to non-rigid, locally affine shape deformations. Evaluation on benchmark datasets demonstrates our competitive results relative to the state of the art. 1.

The partitioning of 2D shapes into subparts is an important component of shape analysis. This paper defines a formulation of convexity as a criterion of good part decomposition. Its appropriateness is validated by applying it to some simple shapes as well as against showing its close correspondence with Hoffman and Singh's part saliency factors.

Haptic identification of real objects is superior to that of raised two-dimensional (2-D) depic-tions. Three explanations of real-object superiority were investigated: contribution of material information, contribution of 3-D shape and size, and greater potential for integration across the fingers. In Experiment 1, subjects, while wearing gloves that gently attenuated material infor-mation, haptically identified real objects that provided reduced cues to compliance, mass, and part motion. The gloves permitted exploration with free hand movement, a single outstretched finger, or five outstretched fingers. Performance decreased over these three conditions but was superior to identification of pictures of the same objects in all cases, indicating the contribution of 3-D structure and integration across the fingers. Picture performance was also better with five fingers than with one. In Experiment 2, the subjects wore open-fingered gloves, which provided them with material information. Consequently, the effect of type of exploration was substantially reduced but not eliminated. Material compensates somewhat for limited access to object struc-ture but is not the primary basis for haptic object identification. It has been amply demonstrated that people's ability to identify raised line drawings of common objects, using touch alone, is quite poor (Ikeda & Uchikawa, 1978;