Unsupervised Iterative Manifold Alignment via Local Feature Histograms

We propose a new unsupervised algorithm for the automatic alignment of two manifolds of different datasets with possibly different dimensionalities. Alignment is performed automatically without any assumptions on the correspondences between the two manifolds. The proposed algorithm automatically est...

Full description

Bibliographic Details
Main Authors: Fan, Ke, Mian, A., Liu, Wan-Quan, Li, Ling
Other Authors: NO editor
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers 2014
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/6837
_version_ 1848745192146862080
author Fan, Ke
Mian, A.
Liu, Wan-Quan
Li, Ling
author2 NO editor
author_facet NO editor
Fan, Ke
Mian, A.
Liu, Wan-Quan
Li, Ling
author_sort Fan, Ke
building Curtin Institutional Repository
collection Online Access
description We propose a new unsupervised algorithm for the automatic alignment of two manifolds of different datasets with possibly different dimensionalities. Alignment is performed automatically without any assumptions on the correspondences between the two manifolds. The proposed algorithm automatically establishes an initial set of sparse correspondences between the two datasets by matching their underlying manifold structures. Local feature histograms are extracted at each point of the manifolds and matched using a robust algorithm to find the initial correspondences. Based on these sparse correspondences, an embedding space is estimated where the distance between the two manifolds is minimized while maximally retaining the original structure of the manifolds. The problem is formulated as a generalized eigenvalue problem and solved efficiently. Dense correspondences are then established between the two manifolds and the process is iteratively implemented until the two manifolds are correctly aligned consequently revealing their joint structure. We demonstrate the effectiveness of our algorithm on aligning protein structures, facial images of different subjects under pose variations and RGB and Depth data from Kinect. Comparison with an state-of-the-art algorithm shows the superiority of the proposed manifold alignment algorithm in terms of accuracy and computational time.
first_indexed 2025-11-14T06:13:27Z
format Conference Paper
id curtin-20.500.11937-6837
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:13:27Z
publishDate 2014
publisher Institute of Electrical and Electronics Engineers
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-68372017-09-13T14:35:05Z Unsupervised Iterative Manifold Alignment via Local Feature Histograms Fan, Ke Mian, A. Liu, Wan-Quan Li, Ling NO editor learning (artificial intelligence) data analysis feature extraction face recognition iterative methods eigenvalues and eigenfunctions proteins pattern matching image colour analysis We propose a new unsupervised algorithm for the automatic alignment of two manifolds of different datasets with possibly different dimensionalities. Alignment is performed automatically without any assumptions on the correspondences between the two manifolds. The proposed algorithm automatically establishes an initial set of sparse correspondences between the two datasets by matching their underlying manifold structures. Local feature histograms are extracted at each point of the manifolds and matched using a robust algorithm to find the initial correspondences. Based on these sparse correspondences, an embedding space is estimated where the distance between the two manifolds is minimized while maximally retaining the original structure of the manifolds. The problem is formulated as a generalized eigenvalue problem and solved efficiently. Dense correspondences are then established between the two manifolds and the process is iteratively implemented until the two manifolds are correctly aligned consequently revealing their joint structure. We demonstrate the effectiveness of our algorithm on aligning protein structures, facial images of different subjects under pose variations and RGB and Depth data from Kinect. Comparison with an state-of-the-art algorithm shows the superiority of the proposed manifold alignment algorithm in terms of accuracy and computational time. 2014 Conference Paper http://hdl.handle.net/20.500.11937/6837 10.1109/WACV.2014.6836051 Institute of Electrical and Electronics Engineers restricted
spellingShingle learning (artificial intelligence)
data analysis
feature extraction
face recognition
iterative methods
eigenvalues and eigenfunctions
proteins
pattern matching
image colour analysis
Fan, Ke
Mian, A.
Liu, Wan-Quan
Li, Ling
Unsupervised Iterative Manifold Alignment via Local Feature Histograms
title Unsupervised Iterative Manifold Alignment via Local Feature Histograms
title_full Unsupervised Iterative Manifold Alignment via Local Feature Histograms
title_fullStr Unsupervised Iterative Manifold Alignment via Local Feature Histograms
title_full_unstemmed Unsupervised Iterative Manifold Alignment via Local Feature Histograms
title_short Unsupervised Iterative Manifold Alignment via Local Feature Histograms
title_sort unsupervised iterative manifold alignment via local feature histograms
topic learning (artificial intelligence)
data analysis
feature extraction
face recognition
iterative methods
eigenvalues and eigenfunctions
proteins
pattern matching
image colour analysis
url http://hdl.handle.net/20.500.11937/6837