Results 1 - 10
of
56
Similarity Indexing: Algorithms and Performance
- In Proceedings SPIE Storage and Retrieval for Image and Video Databases
, 1996
"... Efficient indexing support is essential to allow content-based image and video databases using similaritybased retrieval to scale to large databases (tens of thousands up to millions of images). In this paper, we take an in depth look at this problem. One of the major difficulties in solving this pr ..."
Abstract
-
Cited by 125 (1 self)
- Add to MetaCart
(Show Context)
Efficient indexing support is essential to allow content-based image and video databases using similaritybased retrieval to scale to large databases (tens of thousands up to millions of images). In this paper, we take an in depth look at this problem. One of the major difficulties in solving this problem is the high dimension (6-100) of the feature vectors that are used to represent objects. We provide an overview of the work in computational geometry on this problem and highlight the results we found are most useful in practice, including the use of approximate nearest neighbor algorithms. We also present a variant of the optimized k-d tree we call the VAM k-d tree, and provide algorithms to create an optimized R-tree we call the VAMSplit R-tree. We found that the VAMSplit R-tree provided better overall performance than all competing structures we tested for main memory and secondary memory applications. We observed large improvements in performance relative to the R*-tree and SS-tree in secondary memory applications, and modest improvements relative to optimized k-d tree variants.-Nearest Neighbor Search-
Image-Based Object Recognition in Man, Monkey and Machine
, 1998
"... Theories of visual object recognition must solve the problem of recognizing 3D objects given that perceivers only receive 2D patterns of light on their retinae. Recent findings from human psychophysics, neurophysiology and machine vision provide converging evidence for `image-based' models i ..."
Abstract
-
Cited by 123 (8 self)
- Add to MetaCart
Theories of visual object recognition must solve the problem of recognizing 3D objects given that perceivers only receive 2D patterns of light on their retinae. Recent findings from human psychophysics, neurophysiology and machine vision provide converging evidence for `image-based' models in which objects are represented as collections of viewpoint-specific local features. This approach is contrasted with `structural-description' models in which objects are represented as configurations of 3D volumes or parts. We then review recent behavioral results that address the biological plausibility of both approaches, as well as some of their computational advantages and limitations. We conclude that, although the image-based approach holds great promise, it has potential pitfalls that may be best overcome by including structural information. Thus, the most viable model of object recognition may be one that incorporates the most appealing aspects of both image-based and structural-description theories. 1998 Elsevier Science B.V. All rights reserved Keywords: Object recognition; Image-based model; Structural description 1.
A sequence of object-processing stages revealed by fMRI in the human occipital lobe. Hum Brain Mapp 6:316--328
, 1998
"... Abstract: Functional magnetic resonance imaging was used in combined functional selectivity and retinotopic mapping tests to reveal object-related visual areas in the human occpital lobe. Subjects were tested with right, left, up, or down hemivisual field stimuli which were composed of images of nat ..."
Abstract
-
Cited by 114 (4 self)
- Add to MetaCart
(Show Context)
Abstract: Functional magnetic resonance imaging was used in combined functional selectivity and retinotopic mapping tests to reveal object-related visual areas in the human occpital lobe. Subjects were tested with right, left, up, or down hemivisual field stimuli which were composed of images of natural objects (faces, animals, man-made objects) or highly scrambled (1,024 elements) versions of the same images. In a similar fashion, the horizontal and vertical meridians were mapped to define the borders of these areas. Concurrently, the same cortical sites were tested for their sensitivity to image-scrambling by varying the number of scrambled picture fragments (from 16–1,024) while controlling for the Fourier power spectrum of the pictures and their order of presentation. Our results reveal a stagewise decrease in retinotopy and an increase in sensitivity to image-scrambling. Three main distinct foci were found in the human visual object recognition pathway (Ungerleider and Haxby [1994]: Curr Opin Neurobiol 4:157–165): 1) Retinotopic primary areas V1–3 did not exhibit significant reduction in activation to scrambled images. 2) Areas V4v (Sereno et al., [1995]: Science 268:889–893) and V3A (DeYoe et al., [1996]: Proc Natl Acad Sci USA 93:2382–2386; Tootell et al., [1997]: J Neurosci 71:7060–7078) manifested both retinotopy and decreased activation to highly scrambled images. 3) The essentially nonretinotopic lateral occipital complex (LO) (Malach et al., [1995]: Proc Natl Acad Sci USA 92:8135–8139; Tootell et al., [1996]: Trends
Training "Greeble" Experts: A Framework for Studying Expert Object Recognition Processes
, 1998
"... Twelve participants were trained to be experts at identifying a set of `Greebles', novel objects that, like faces, all share a common spatial configuration. Tests comparing expert with novice performance revealed: (1) a surprising mix of generalizability and specificity in expert object recogni ..."
Abstract
-
Cited by 100 (21 self)
- Add to MetaCart
Twelve participants were trained to be experts at identifying a set of `Greebles', novel objects that, like faces, all share a common spatial configuration. Tests comparing expert with novice performance revealed: (1) a surprising mix of generalizability and specificity in expert object recognition processes; and (2) that expertise is a multi-faceted phenomenon, neither adequately described by a single term nor adequately assessed by a single task. Greeble recognition by a simple neural-network model is also evaluated, and the model is found to account surprisingly well for both generalization and individuation using a single set of processes and representations. 1998 Elsevier Science Ltd. All rights reserved. Keywords: Configural encoding; Face recognition; Neural networks; Object categorization; Perceptual expertise 1. Introduction Are the mechanisms used by perceivers as they become increasingly familiar with an object class the same as those used by perceivers when they first en...
One-shot viewpoint invariance in matching novel objects
- VISION RESEARCH 39 (1999) 2885–2899
, 1999
"... Humans often evidence little difficulty at recognizing objects from arbitrary orientations in depth. According to one class of theories, this competence is based on generalization from templates specified by metric properties (MPs), that were learned for the various orientations. An alternative clas ..."
Abstract
-
Cited by 53 (6 self)
- Add to MetaCart
Humans often evidence little difficulty at recognizing objects from arbitrary orientations in depth. According to one class of theories, this competence is based on generalization from templates specified by metric properties (MPs), that were learned for the various orientations. An alternative class of theories assumes that non-accidental properties (NAPs) might be exploited so that even novel objects can be recognized under depth rotation. After scaling MP and NAP differences so that they were equally detectable when the objects were at the same orientation in depth, the present investigation assessed the effects of rotation on same-different judgments for matching novel objects. Judgments of a sequential pair of images of novel objects, when rendered from different viewpoints, revealed relatively low costs when the objects differed in a NAP of a single part, i.e. a geon. However, rotation dramatically reduced the detectability of MP differences to a level well below that expected by chance. NAPs offer a striking advantage over MPs for object classification and are therefore more likely to play a central role in the representation of
Class similarity and viewpoint invariance in the recognition of 3D objects
- Biological Cybernetics
, 1992
"... In human vision, the processes and the representations involved in identifying specific individuals are frequently assumed to be different from those used for basic-level classification, because classification is largely viewpoint-invariant, but identification is not. This assumption was tested in p ..."
Abstract
-
Cited by 52 (16 self)
- Add to MetaCart
(Show Context)
In human vision, the processes and the representations involved in identifying specific individuals are frequently assumed to be different from those used for basic-level classification, because classification is largely viewpoint-invariant, but identification is not. This assumption was tested in psychophysical experiments, in which objective similarity between stimuli (and, consequently, the level of their distinction) varied in a controlled fashion. Subjects were trained to discriminate between two classes of computer generated 3D objects, one resembling monkeys, and the other dogs. Both classes were defined by the same set of 56 parameters, which encoded sizes, shapes, and placement of the limbs, the ears, the snout, etc. Interpolation between parameter vectors of the class prototypes yielded shapes that changed smoothly between monkey and dog. Within-class variation was induced in each trial by randomly perturbing all the parameters. After the subjects reached 90% correct performa...
Deformable Prototypes for Encoding Shape Categories in Image Databases
- PATTERN RECOGNITION, SPECIAL ISSUE ON IMAGE DATABASES
, 1997
"... We describe a method for shape-based image database search that uses deformable prototypes to represent categories. Rather than directly comparing a candidate shape with all shape entries in the database, shapes are compared in terms of the types of nonrigid deformations (differences) that relate th ..."
Abstract
-
Cited by 47 (2 self)
- Add to MetaCart
(Show Context)
We describe a method for shape-based image database search that uses deformable prototypes to represent categories. Rather than directly comparing a candidate shape with all shape entries in the database, shapes are compared in terms of the types of nonrigid deformations (differences) that relate them to a small subset of representative prototypes. To solve the shape correspondence and alignment problem, we employ the technique of modal matching, an information-preserving shape decomposition for matching, describing, and comparing shapes despite sensor variations and nonrigid deformations. In modal matching, shape is decomposed into an ordered basis of orthogonal principal components. We demonstrate the utility of this approach for shape comparison in 2-D image databases.
Shape and the first hundred nouns
- Child Dev
, 2004
"... This paper reports evidence from a longitudinal study in which children’s attention to shape in a laboratory task of artificial noun learning was correlated with a rate shift in noun acquisitions. Eight children were tested in the laboratory at 3-week intervals beginning when they had less than 25 n ..."
Abstract
-
Cited by 42 (11 self)
- Add to MetaCart
(Show Context)
This paper reports evidence from a longitudinal study in which children’s attention to shape in a laboratory task of artificial noun learning was correlated with a rate shift in noun acquisitions. Eight children were tested in the laboratory at 3-week intervals beginning when they had less than 25 nouns in their productive vocabulary (M age5 17 months). Children were presented with a novel word generalization task at each session. Addi-tionally, the study examined the kinds of words the children learned early, based on parent reports, and the statistical regularities inherent in those vocabularies. The results indicate that as children learned nouns, they also learned to attend to shape in the novel word task. At the same time, children showed an acceleration in new noun production outside of the laboratory. Shape is a feature that human infants appear ready to notice (Johnson, 2001; Spelke, 1990). Attention to shape is essential to the everyday recognition of ob-jects (Biederman, 1987; Rosch, Mervis, Gray, Johnson, & Boyes-Braem, 1976) and to the nouns that domi-nate the speech young children hear (Poulin-Dubois, Graham, & Sippola, 1995; Sandhofer, Smith, & Luo, 2000). Much research has been devoted to establish-ing the importance of shape to successful noun learning. In studies that examine children’s under-standing of how nouns link to object categories, in-vestigators have found a general tendency to extend novel names to solid things that share a common
Do Viewpoint-Dependent Mechanisms Generalize Across Members of a Class?
, 1997
"... this paper is to investigate the nature of image-based class generalization, ..."
Abstract
-
Cited by 39 (8 self)
- Add to MetaCart
(Show Context)
this paper is to investigate the nature of image-based class generalization,
Beyond Categories: The Visual Memex Model for Reasoning About Object Relationships
"... The use of context is critical for scene understanding in computer vision, where the recognition of an object is driven by both local appearance and the object’s relationship to other elements of the scene (context). Most current approaches rely on modeling the relationships between object categorie ..."
Abstract
-
Cited by 37 (4 self)
- Add to MetaCart
(Show Context)
The use of context is critical for scene understanding in computer vision, where the recognition of an object is driven by both local appearance and the object’s relationship to other elements of the scene (context). Most current approaches rely on modeling the relationships between object categories as a source of context. In this paper we seek to move beyond categories to provide a richer appearancebased model of context. We present an exemplar-based model of objects and their relationships, the Visual Memex, that encodes both local appearance and 2D spatial context between object instances. We evaluate our model on Torralba’s proposed Context Challenge against a baseline category-based system. Our experiments suggest that moving beyond categories for context modeling appears to be quite beneficial, and may be the critical missing ingredient in scene understanding systems. 1
