Results 1 - 10
of
30
COSMOS - A Representation Scheme for 3D Free-Form Objects
- IEEE Transactions on Pattern Analysis and Machine Intelligence
, 1995
"... We address the problem of representing and recognizing 3D free-form objects when (a) the object viewpoint is arbitrary, (b) the objects may vary in shape and complexity, and (c) no restrictive assumptions are made about the types of surfaces on the object. We assume that a range image of a scene is ..."
Abstract
-
Cited by 82 (2 self)
- Add to MetaCart
(Show Context)
We address the problem of representing and recognizing 3D free-form objects when (a) the object viewpoint is arbitrary, (b) the objects may vary in shape and complexity, and (c) no restrictive assumptions are made about the types of surfaces on the object. We assume that a range image of a scene is available, containing a view of a rigid 3D object without occlusion. We propose a new and general surface representation scheme for recognizing objects with freeform (sculpted) surfaces. In this scheme, an object is described concisely in terms of maximal surface patches of constant shape index. The maximal patches that represent the object are mapped onto the unit sphere via their orientations, and aggregated via shape spectral functions. Properties such as surface area, curvedness and connectivity which are required to capture local and global information are also built into the representation. The scheme yields a meaningful and rich description useful for object recognition. A novel conce...
3D Object Recognition from Range Images using Local Feature Histograms
- Proceedings of CVPR 2001
, 2001
"... This paper explores a view-based approach to recognize free-form objects in range images. We are using a set of local features that are easy to calculate and robust to partial occlusions. By combining those features in a multidimensional histogram, we can obtain highly discriminant classifiers witho ..."
Abstract
-
Cited by 68 (0 self)
- Add to MetaCart
(Show Context)
This paper explores a view-based approach to recognize free-form objects in range images. We are using a set of local features that are easy to calculate and robust to partial occlusions. By combining those features in a multidimensional histogram, we can obtain highly discriminant classifiers without the need for segmentation. Recognition is performed using either histogram matching or a probabilistic recognition algorithm. We compare the performance of both methods in the presence of occlusions and test the system on a database of almost 2000 full-sphere views of 30 free-form objects. The system achieves a recognition accuracy above 93% on ideal images, and of 89% with 20% occlusion.
B.: 3D free-form object recognition in range images using local surface patches
- Pattern Recognition Letters
, 2007
"... This paper introduces an integrated local surface de-scriptor for surface representation and object recognition. A local surface descriptor is defined by a centroid, its sur-face type and 2D histogram. The 2D histogram consists of shape indexes, calculated from principal curvatures, and angles betwe ..."
Abstract
-
Cited by 53 (2 self)
- Add to MetaCart
(Show Context)
This paper introduces an integrated local surface de-scriptor for surface representation and object recognition. A local surface descriptor is defined by a centroid, its sur-face type and 2D histogram. The 2D histogram consists of shape indexes, calculated from principal curvatures, and angles between the normal of reference point and that of its neighbors. Instead of calculating local surface descriptors for all the 3D surface points, we only calculate them for fea-ture points which are areas with large shape variation. Fur-thermore, in order to speed up the search process and deal with a large set of objects, model local surface patches are indexed into a hash table. Given a set of test local surface patches, we cast votes for models containing similar surface descriptors. Potential corresponding local surface patches and candidate models are hypothesized. Verification is per-formed by aligning models with scenes for the most likely models. Experiment results with real range data are pre-sented to demonstrate the effectiveness of our approach. 1.
Finger surface as a biometric identifier
, 2004
"... We present a novel approach for personal identification and identity verification which utilizes 3D finger surface features as a biometric identifier. Using 3D range images of the hand, a surface representation for the index, middle, and ring finger is calculated and used for comparison to determine ..."
Abstract
-
Cited by 22 (1 self)
- Add to MetaCart
(Show Context)
We present a novel approach for personal identification and identity verification which utilizes 3D finger surface features as a biometric identifier. Using 3D range images of the hand, a surface representation for the index, middle, and ring finger is calculated and used for comparison to determine subject similarity. We use the curvature based shape index to represent the fingersÕ surface. Gallery and probe shape index signatures are compared using the normalized correlation coefficient to compute a match score. A large unique database of hand images supports the research. We use data sets obtained over time to examine the performance of each individual finger surface as a biometric identifier as well as the performance obtained when combining them. Both identification and verification experiments are conducted. In addition, probe and gallery sets sizes are increased to further improve recognition performance in our experiments. Our approach yields good results for a first-of-its-kind biometric technique, indicating that this approach warrants further research.
Shape Spectrum Based View Grouping and Matching of 3D Free-Form Objects
- IEEE Trans. Pattern Analysis and Machine Intelligence
, 1997
"... We address the problem of constructing view aspects of 3D free-form objects for efficient matching during recognition. We introduce a novel view representation based on "shape spectrum" features, and propose a general and powerful technique for organizing multiple views of objects of c ..."
Abstract
-
Cited by 22 (1 self)
- Add to MetaCart
(Show Context)
We address the problem of constructing view aspects of 3D free-form objects for efficient matching during recognition. We introduce a novel view representation based on "shape spectrum" features, and propose a general and powerful technique for organizing multiple views of objects of complex shape and geometry into compact and homogeneous clusters. Our view grouping technique obviates the need for surface segmentation and edge detection. Experiments on 6,400 synthetically generated views of 20 free-form objects and 100 real range images of 10 sculpted objects demonstrate the good performance of our shape spectrum based model view selection technique.
The Image Shape Spectrum for Image Retrieval
, 1997
"... : We present an appearance-based technique for image characterization and retrieval. Our method is translation/rotation and scale- invariant and encodes the significant data in the image without using any segmentation. It is also very well suited to small viewpoint changes and is robust to noise and ..."
Abstract
-
Cited by 19 (2 self)
- Add to MetaCart
: We present an appearance-based technique for image characterization and retrieval. Our method is translation/rotation and scale- invariant and encodes the significant data in the image without using any segmentation. It is also very well suited to small viewpoint changes and is robust to noise and occlusion. We present several retrieval examples in large benchmark databases, including face databases and a database of 3D objects, for which the method reaches an ideal recognition rate. Key-words: image databases, image indexing, image retrieval, appearance, invariance. (R'esum'e : tsvp) Chahab.Nastar@inria.fr Unite de recherche INRIA Rocquencourt Domaine de Voluceau, Rocquencourt, BP 105, 78153 LE CHESNAY Cedex (France) Telephone : (33) 01 39 63 55 11 -- Telecopie : (33) 01 39 63 53 Le spectre de forme pour l'indexation d'images R'esum'e : Nous pr'esentons une technique fond'ee sur l'apparence pour caract 'eriser et rechercher des images dans une base. Notre m'ethode est invarian...
Human ear detection from side face range images
- Proc. Int. Conf. on Pattern Recognition
"... Ear detection is an important part of an ear recognition system. In this paper we address human ear detection from side face range images. We introduce a simple and effec-tive method to detect ears, which has two stages: offline model template building and on-line detection. The model template is re ..."
Abstract
-
Cited by 18 (3 self)
- Add to MetaCart
(Show Context)
Ear detection is an important part of an ear recognition system. In this paper we address human ear detection from side face range images. We introduce a simple and effec-tive method to detect ears, which has two stages: offline model template building and on-line detection. The model template is represented by an averaged histogram of shape index. The on-line detection is a four-step process: step edge detection and thresholding, image dilation, connect-component labeling and template matching. Experiment re-sults with real ear images are presented to demonstrate the effectiveness of our approach. 1.
Shape Spectra Based View Grouping for Free-Form Objects
- In Proc. Int. Conf. on Image Processing (ICIP-95), vol.3
, 1995
"... ..."
(Show Context)
On Computing Global Similarity in Images
"... The retrieval of images based on their visual similarity to an example image is an important and fascinating area of research. Here, a method to characterize visual appearance for determining global similarity in images is described. Images are filtered with Gaussian derivatives and geometric featu ..."
Abstract
-
Cited by 13 (3 self)
- Add to MetaCart
(Show Context)
The retrieval of images based on their visual similarity to an example image is an important and fascinating area of research. Here, a method to characterize visual appearance for determining global similarity in images is described. Images are filtered with Gaussian derivatives and geometric features are computed from the filtered images. The geometric features used here are curvature and phase. Two images may be said to be similar if they have similar distributions of such features. Global similarity may, therefore, be deduced by comparing histograms of these features. This allows for rapid retrieval and examples from collection of gray-level and trademark images are shown.
On Computing Local and Global Similarity in Images
, 1998
"... The retrieval of images based on their visual similarity to an example image is an important and fascinating area of research. Here, we discuss various ways in which visual appearance may be characterized for determining both global and local similarity in images. One popular method involves the co ..."
Abstract
-
Cited by 13 (6 self)
- Add to MetaCart
(Show Context)
The retrieval of images based on their visual similarity to an example image is an important and fascinating area of research. Here, we discuss various ways in which visual appearance may be characterized for determining both global and local similarity in images. One popular method involves the computation of global measures like moment invariants to characterize global similarity. Although this means that the image may be characterized using a few numbers, the performance is often poor. Techniques based on moment invariants often perform poorly. They require that the object be a binary shape without holes which is often not practical. In addition, moment invariants are sensitive to noise. Visual appearance is better represented using local features computed at multiple scales. Such local features may include the outputs of images filtered with Gaussian derivatives, differential invariants or geometric quantities like curvature and phase. Two images may be said to be similar if they have similar distributions of such features. Global similarity may, therefore, be deduced by comparing histograms of such features. This can be done rapidly. Histograms cannot be used to compute local similarity. Instead, the constraint that the spatial relationship between the features in the query be similar to the spatial relationship between the features of its matching counterparts in the database provides a means for computing local similarity. The methods presented here do not require prior segmentation of the database. In the case of local representation objects can be embedded in arbitrary backgrounds and both methods handle a range of size variations and viewpoint variations up to 20 or 25 degrees. Keywords: filter based representations, appearance based representations, scale ...