Results 1  10
of
13
Contentbased image retrieval at the end of the early years
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 2000
"... The paper presents a review of 200 references in contentbased image retrieval. The paper starts with discussing the working conditions of contentbased retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap. Subsequent sections discuss computational steps for imag ..."
Abstract

Cited by 1618 (24 self)
 Add to MetaCart
The paper presents a review of 200 references in contentbased image retrieval. The paper starts with discussing the working conditions of contentbased 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.
Curvatureaugmented tensor voting for shape inference from noisy 3D data
 IEEE Trans
"... AbstractÐWe improve the basic tensor voting formalism to infer the sign and direction of principal curvatures at each input site from noisy 3D data. Unlike most previous approaches, no local surface fitting, partial derivative computation, nor oriented normal vector recovery is performed in our meth ..."
Abstract

Cited by 27 (2 self)
 Add to MetaCart
(Show Context)
AbstractÐWe improve the basic tensor voting formalism to infer the sign and direction of principal curvatures at each input site from noisy 3D data. Unlike most previous approaches, no local surface fitting, partial derivative computation, nor oriented normal vector recovery is performed in our method. These approaches are known to be noisesensitive since accurate partial derivative information is often required, which is usually unavailable from real data. Also, unlike approaches that detect signs of Gaussian curvature, we can handle points with zero Gaussian curvature uniformly, without first localizing them in a separate process. The tensor voting curvature estimation is noniterative, does not require initialization, and is robust to a considerable amount of outlier noise, as its effect is reduced by collecting a large number of tensor votes. Qualitative and quantitative results on synthetic and real, complex data are presented. Index TermsÐTensor, curvature, shape description, surfaces and curves. 1
Robust Estimation of Curvature Information from Noisy 3D Data for Shape Description
, 1999
"... We describe an effective and novel approach to infer sign and direction of principal curvatures at each input site from noisy 3D data. Unlike most previous approaches, no local surface fitting, partial derivative computation of any kind, nor oriented normal vector recovery is performed in our method ..."
Abstract

Cited by 25 (1 self)
 Add to MetaCart
We describe an effective and novel approach to infer sign and direction of principal curvatures at each input site from noisy 3D data. Unlike most previous approaches, no local surface fitting, partial derivative computation of any kind, nor oriented normal vector recovery is performed in our method. These approaches are noisesensitive since accurate, local, partial derivative information is often required, which is usually unavailable from real data because of the unavoidable outlier noise inherent in manymeasurement phases. Also, we can handle points with zero Gaussian curvature uniformly (i.e., without the need to localize and handle them first as a separate process). Our approach is based on Tensor Voting, a unified, salient structure inference process. Both the sign and the direction of principal curvatures are inferred directly from the input. Each input is first transformed into a synthetic tensor. A novel and robust approach based on tensor voting is proposed for curvature inf...
Curvaturebased algorithms for nonrigid motion and correspondence estimation
 PAMI
, 2003
"... Two new algorithms for estimation of nonrigid motion in range data in the absense of correspondence information are presented. We derive a new relationship between Gaussian curvatures and other differentialgeometric parameters before and after small deformation. This relationship depends linearly ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
(Show Context)
Two new algorithms for estimation of nonrigid motion in range data in the absense of correspondence information are presented. We derive a new relationship between Gaussian curvatures and other differentialgeometric parameters before and after small deformation. This relationship depends linearly on derivatives of a motion model, which provides a closedform, least squares solution for motion estimation. The first algorithm built solely on the new relationship demonstrates significant improvement of motion and correspondence estimation accuracy on certain artificial shapes; however, its poor numerical conditioning results in higher error in the presense of inaccurate values of differentialgeometric parameters. The second algorithm combines the Gaussian curvature relationship with the previously known relationship between unit normals before and after deformation. The combined algorithm achieves higher accuracy of motion and correspondence estimation. 1
Making colors worth more than a thousand words
 Proceedings of the 2008 ACM symposium on Applied computing
, 2008
"... Contentbased image retrieval (CBIR) is a challenging task. Common techniques use only lowlevel features. However, these solutions can lead to the socalled ‘semantic gap ’ problem: images with high feature similarities may be different in terms of user perception. In this paper, our objective is t ..."
Abstract

Cited by 5 (1 self)
 Add to MetaCart
(Show Context)
Contentbased image retrieval (CBIR) is a challenging task. Common techniques use only lowlevel features. However, these solutions can lead to the socalled ‘semantic gap ’ problem: images with high feature similarities may be different in terms of user perception. In this paper, our objective is to retrieve images based on color cues which may present some affine transformations. For that, we present CSIR: a new method for comparing images based on discrete distributions of distinctive color and scale image regions. We validate the technique using images with a large range of viewpoints, partial occlusion, changes in illumination, and various domains.
unknown title
"... A new approach to estimate the surface curvatures from 3D triangular mesh surfaces with Gaussian curvature’s geometry interpretation is proposed in this work. Unlike previous work, the proposed method does not use local surface fitting, partial derivative computation, or oriented normal vector recov ..."
Abstract
 Add to MetaCart
(Show Context)
A new approach to estimate the surface curvatures from 3D triangular mesh surfaces with Gaussian curvature’s geometry interpretation is proposed in this work. Unlike previous work, the proposed method does not use local surface fitting, partial derivative computation, or oriented normal vector recovery. Instead, the Gaussian curvature is estimated at a vertex as the area of its small neighborhood under the Gaussian map divided by the area of that neighborhood. The proposed approach can handle vertices with the zero Gaussian curvature uniformly without localizing them as a separate process. The performance is further improved with the local Bezier curve approximation and subdivision. The effectiveness of the proposed approach for meshes with a large range of coarseness is demonstrated by experiments. The application of the proposed method to 3D surface segmentation and 3D mesh feature extraction is also discussed.
Color and Scale representative Image Regions (CSIR) ∗
, 2007
"... The contents of this report are the sole responsibility of the authors. O conteúdo do presente relatório é de única responsabilidade dos autores. Image Retrieval based on discrete distributions of distinctive ..."
Abstract
 Add to MetaCart
(Show Context)
The contents of this report are the sole responsibility of the authors. O conteúdo do presente relatório é de única responsabilidade dos autores. Image Retrieval based on discrete distributions of distinctive
Relative Magnitude of Gaussian Curvature Using Neural Network and Object Rotation of Two Degrees of Freedom
"... We�propose a new approach to recover the relative magnitude of Gaussian curvature�from multiple images. Previous approaches recover the sign of Gaussian curvature from the spatial relationship of points mapped onto a sphere. Here, the relative magnitude of Gaussian curvature is recovered at each poi ..."
Abstract
 Add to MetaCart
(Show Context)
We�propose a new approach to recover the relative magnitude of Gaussian curvature�from multiple images. Previous approaches recover the sign of Gaussian curvature from the spatial relationship of points mapped onto a sphere. Here, the relative magnitude of Gaussian curvature is recovered at each point. No calibration object is required. Instead, the test object itself is rotated in both the vertical and horizontal directions to estimate the position coordinates of a marker�point. An RBF neural network learns the mapping of intensities to marker� position coordinates along a virtual sphere. That is, selfcalibration is performed by moving a marker�point. The neural network represents the mapping of observed image intensities�to coordinates on a virtual sphere.