Color indexing
TL;DR: In this paper, color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models, and they can differentiate among a large number of objects.
Abstract: Computer vision is moving into a new era in which the aim is to develop visual skills for robots that allow them to interact with a dynamic, unconstrained environment. To achieve this aim, new kinds of vision algorithms need to be developed which run in real time and subserve the robot's goals. Two fundamental goals are determining the identity of an object with a known location, and determining the location of a known object. Color can be successfully used for both tasks.
This dissertation demonstrates that color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models. It shows that color histograms are stable object representations in the presence of occlusion and over change in view, and that they can differentiate among a large number of objects. For solving the identification problem, it introduces a technique called Histogram Intersection, which matches model and image histograms and a fast incremental version of Histogram Intersection which allows real-time indexing into a large database of stored models. It demonstrates techniques for dealing with crowded scenes and with models with similar color signatures. For solving the location problem it introduces an algorithm called Histogram Backprojection which performs this task efficiently in crowded scenes.
Citations
More filters
20 Sep 1999
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Abstract: An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low residual least squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
16,989 citations
17 Jun 2006
TL;DR: This paper presents a method for recognizing scene categories based on approximate global geometric correspondence that exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories.
Abstract: This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting "spatial pyramid" is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralbas "gist" and Lowes SIFT descriptors.
8,736 citations
TL;DR: The working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap are discussed, as well as aspects of system engineering: databases, system architecture, and evaluation.
Abstract: Presents a review of 200 references in content-based image retrieval. The paper starts with discussing the working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap. Subsequent sections discuss computational steps for image retrieval systems. Step one of the review is image processing for retrieval sorted by color, texture, and local geometry. Features for retrieval are discussed next, sorted by: accumulative and global features, salient points, object and shape features, signs, and structural combinations thereof. Similarity of pictures and objects in pictures is reviewed for each of the feature types, in close connection to the types and means of feedback the user of the systems is capable of giving by interaction. We briefly discuss aspects of system engineering: databases, system architecture, and evaluation. In the concluding section, we present our view on: the driving force of the field, the heritage from computer vision, the influence on computer vision, the role of similarity and of interaction, the need for databases, the problem of evaluation, and the role of the semantic gap.
6,447 citations
TL;DR: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed, which employs a metric derived from the Bhattacharyya coefficient as similarity measure, and uses the mean shift procedure to perform the optimization.
Abstract: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed. The feature histogram-based target representations are regularized by spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity functions suitable for gradient-based optimization, hence, the target localization problem can be formulated using the basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyya coefficient as similarity measure, and use the mean shift procedure to perform the optimization. In the presented tracking examples, the new method successfully coped with camera motion, partial occlusions, clutter, and target scale variations. Integration with motion filters and data association techniques is also discussed. We describe only a few of the potential applications: exploitation of background information, Kalman tracking using motion models, and face tracking.
4,996 citations
TL;DR: This paper investigates the properties of a metric between two distributions, the Earth Mover's Distance (EMD), for content-based image retrieval, and compares the retrieval performance of the EMD with that of other distances.
Abstract: We investigate the properties of a metric between two distributions, the Earth Mover's Distance (EMD), for content-based image retrieval. The EMD is based on the minimal cost that must be paid to transform one distribution into the other, in a precise sense, and was first proposed for certain vision problems by Peleg, Werman, and Rom. For image retrieval, we combine this idea with a representation scheme for distributions that is based on vector quantization. This combination leads to an image comparison framework that often accounts for perceptual similarity better than other previously proposed methods. The EMD is based on a solution to the transportation problem from linear optimization, for which efficient algorithms are available, and also allows naturally for partial matching. It is more robust than histogram matching techniques, in that it can operate on variable-length representations of the distributions that avoid quantization and other binning problems typical of histograms. When used to compare distributions with the same overall mass, the EMD is a true metric. In this paper we focus on applications to color and texture, and we compare the retrieval performance of the EMD with that of other distances.
4,593 citations
References
More filters
TL;DR: Three recent developments that have yielded insight into information processing and flow within extrastriate cortex are focused on.
Abstract: The neuronal processes that lead to visual perception have attracted intense interest since Kuffier's studies of receptive field organization in cat retinal ganglion cells over three decades ago (Kuffier 1953). A variety of ana tomical and physiological approaches have been employed to analyze the organization of thc visual pathway between the retina and striate cortex (VI ) and the transformations of visual information that occur at each stage (see Hubel & Wiesel 1977, Stone 1 983, Shapley & Lennie 1985). The growth in understanding of the retinostriate pathway has been accompanied by increasing interest in visual processing in the expanse of extrastriate cortex beyond V I . Studies of extrastriate cortex in many spec ies showed that it comprises a mosaic of visual areas that can be dis tinguished by several anatomical and physiological criteria (reviewed by Kaas 1 978, Zeki 1 978, Cowey 1979, Van Essen 1 979, 1985, Wagor et al 1980, Tusa et al 1 98 1) . The literature in this field is large, and we do not attempt to review all relevant studies. Rather, we concern ourselves with three recent devel opments that have yielded insight into information processing and flow within extrastriate cortex. The first of these is the convergence of ana tom-
1,227 citations
TL;DR: A model of human preattentive texture perception that can predict the salience of texture boundaries in any arbitrary gray-scale image and Quantitative predictions of the degree of discriminability of different texture pairs match well with experimental measurements of discriminateability in human observers.
Abstract: We present a model of human preattentive texture perception. This model consists of three stages: (1) convolution of the image with a bank of even-symmetric linear filters followed by half-wave rectification to give a set of responses modeling outputs of V1 simple cells, (2) inhibition, localized in space, within and among the neural-response profiles that results in the suppression of weak responses when there are strong responses at the same or nearby locations, and (3) texture-boundary detection by using wide odd-symmetric mechanisms. Our model can predict the salience of texture boundaries in any arbitrary gray-scale image. A computer implementation of this model has been tested on many of the classic stimuli from psychophysical literature. Quantitative predictions of the degree of discriminability of different texture pairs match well with experimental measurements of discriminability in human observers.
1,037 citations
01 Aug 1985-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: Visual analysis appears to be functionally divided between an early preattentive level of processing at which simple features are coded spatially in parallel and a later stage at which focused attention is required to conjoin the separate features into coherent objects.
Abstract: Visual analysis appears to be functionally divided between an early preattentive level of processing at which simple features are coded spatially in parallel and a later stage at which focused attention is required to conjoin the separate features into coherent objects. Evidence supporting this dichotomy comes from behavioral studies of visual search, from differences in the ease of texture segregation, from reports of illusory conjunctions when attention is overloaded, from subjects' ability to identify simple features correctly even when they mislocate them, and from the substantial benefit of pre-cuing the location of a relevant item when the task requires that features be conjoined but not when simple features are sufficient. Some further studies of search have revealed a striking asymmetry between several pairs of stimuli which differ in the presence or absence of a single part or property. The asymmetry depends solely on which of the pair is allocated the role of target and which is replicated to form the background items. It suggests that search for the presence of a visual primitive is automatic and parallel, whereas search for the absence of the same feature is serial and requires focused attention. The search asymmetry can be used as an additional diagnostic to help define the functional features extracted by the visual system.
915 citations
TL;DR: A computational method for estimating surface spectral reflectance when the spectral power distribution of the ambient light is not known is described, which can be reliably estimated despite changes in the ambient lighting conditions.
Abstract: Human and machine visual sensing is enhanced when surface properties of objects in scenes, including color, can be reliably estimated despite changes in the ambient lighting conditions. We describe a computational method for estimating surface spectral reflectance when the spectral power distribution of the ambient light is not known.
840 citations