Loading [a11y]/accessibility-menu.js
Online Robust Image Alignment via Subspace Learning from Gradient Orientations | IEEE Conference Publication | IEEE Xplore

Online Robust Image Alignment via Subspace Learning from Gradient Orientations


Abstract:

Robust and efficient image alignment remains a challenging task, due to the massiveness of images, great illumination variations between images, partial occlusion and cor...Show More

Abstract:

Robust and efficient image alignment remains a challenging task, due to the massiveness of images, great illumination variations between images, partial occlusion and corruption. To address these challenges, we propose an online image alignment method via subspace learning from image gradient orientations (IGO). The proposed method integrates the subspace learning, transformed IGO reconstruction and image alignment into a unified online framework, which is robust for aligning images with severe intensity distortions. Our method is motivated by principal component analysis (PCA) from gradient orientations provides more reliable low-dimensional subspace than that from pixel intensities. Instead of processing in the intensity domain like conventional methods, we seek alignment in the IGO domain such that the aligned IGO of the newly arrived image can be decomposed as the sum of a sparse error and a linear composition of the IGO-PCA basis learned from previously well-aligned ones. The optimization problem is accomplished by an iterative linearization that minimizes the L1-norm of the sparse error. Furthermore, the IGO-PCA basis is adaptively updated based on incremental thin singular value decomposition (SVD) which takes the shift of IGO mean into consideration. The efficacy of the proposed method is validated on extensive challenging datasets through image alignment and face recognition. Experimental results demonstrate that our algorithm provides more illumination- and occlusion-robust image alignment than state-of-the-art methods do.
Date of Conference: 22-29 October 2017
Date Added to IEEE Xplore: 25 December 2017
ISBN Information:
Electronic ISSN: 2380-7504
Conference Location: Venice, Italy

1. Introduction

Image alignment is one of the most widely used image processing techniques in computer vision [24]. The technique seeks the optimal image transformations to establish spatial correspondences between different image acquisitions. Applications in video stabilization [19], medical image registration [23], image recognition [27] and visual tracking [31] all leverage alignment to estimate image correspondences. In recent years, with the increasing popularity of the image and video sharing in social networks, such as Facebook and Instagram, we are seeing a dramatic increasing amount of visual data available online. Such enormous data poses great challenges for existing batch image alignment algorithms, due to great illumination variations between images, partial occlusion, gross pixel corruption, and the dynamically increasing images [2]. Therefore, the robust alignment with both memory and time efficiency deems to be a crucial image processing issue to be resolved for handling large and increasing amount of images.

Contact IEEE to Subscribe

References

References is not available for this document.