Multiscale 3D feature extraction and matching with an application to 3D face recognition

Fadaifard, Hadi; Wolberg, George; Haralick, R. H.

doi:10.1016/j.gmod.2013.01.002

Cited by 16 publications

(17 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Originally limited to meshes, recent approaches have been proposed to extend diffusion and geodesic distances to point clouds [42], [43]. These approaches do not fit our requirement since they cannot automatically detect the scale associated to detected features [44] and thus do not help to estimate the scale between two models. Moreover, they require to solve the diffusion equation globally on the entire object, which makes their use impractical with acquired 3D objects defined by millions of points.…”

Section: Multi-scale Geometry Analysismentioning

confidence: 99%

“…In our case we need to work with point-clouds, which makes such techniques unusable without prior remeshing. We refer the reader to the recent work of [44] for a practical and up-to-date comparison of mesh-based scale-space techniques. Recently, Mellado et al have proposed a technique called Growing Least Squares (GLS) [5], which aims at extending the scale-space formalism to point-set surfaces using implicit kernels evaluated at growing scales.…”

Section: Multi-scale Geometry Analysismentioning

confidence: 99%

See 1 more Smart Citation

Relative Scale Estimation and 3D Registration of Multi-Modal Geometry Using Growing Least Squares

Mellado

Dellepiane

Scopigno

2016

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

The advent of low cost scanning devices and the improvement of multi-view stereo techniques have made the acquisition of 3D geometry ubiquitous. Data gathered from different devices, however, result in large variations in detail, scale, and coverage. Registration of such data is essential before visualizing, comparing and archiving them. However, state-of-the-art methods for geometry registration cannot be directly applied due to intrinsic differences between the models, e.g., sampling, scale, noise. In this paper we present a method for the automatic registration of multi-modal geometric data, i.e., acquired by devices with different properties (e.g., resolution, noise, data scaling). The method uses a descriptor based on Growing Least Squares, and is robust to noise, variation in sampling density, details, and enables scale-invariant matching. It allows not only the measurement of the similarity between the geometry surrounding two points, but also the estimation of their relative scale. As it is computed locally, it can be used to analyze large point clouds composed of millions of points. We implemented our approach in two registration procedures (assisted and automatic) and applied them successfully on a number of synthetic and real cases. We show that using our method, multi-modal models can be automatically registered, regardless of their differences in noise, detail, scale, and unknown relative coverage.

show abstract

Section: Multi-scale Geometry Analysismentioning

confidence: 99%

Section: Multi-scale Geometry Analysismentioning

confidence: 99%

Relative Scale Estimation and 3D Registration of Multi-Modal Geometry Using Growing Least Squares

Mellado

Dellepiane

Scopigno

2016

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…Many applications exploit the benefits of feature extraction and matching, such as registration of medical images [3], co-registration of very high resolution aerial / satellite images [4], [5], landing of an Unmanned Aerial Vehicle [6], [7], ship extraction [8], object recognition (e.g. face) [9], extraction of image correspondences or bundle adjustment [10], [11].…”

Section: Introductionmentioning

confidence: 99%

GPU acceleration of feature extraction and matching algorithms

Marinelli

Mancini

Zingaretti

2014

2014 IEEE/ASME 10th International Conference on Mechatronic and Embedded Systems and Applications (MESA)

View full text Add to dashboard Cite

show abstract

“…Stereo matching has always been a focus in the field of stereo vision research [4,5] . The stereo matching algorithms can be categorized into three types: area-based matching algorithm [6,7] , phase-based matching algorithm [8,9] and feature-based matching algorithm [10][11][12][13] . The algorithm of area matching has the following drawbacks: it is sensitive to the affine distortion and radiation distortion; it is lack of robustness against the impact of image noise and gray value differences or contrast differences; it is difficult to choose the size of matching window.…”

mentioning

confidence: 99%