Deformed Lattice Detection in Real-World Images Using Mean-Shift Belief Propagation

Authors:
Minwoo Park;Kyle Brocklehurst;Robert T. Collins;Yanxi Liu
Affiliations:
Pennsylvania State University, University Park;Pennsylvania State University, University Park;Pennsylvania State University, University Park;Pennsylvania State University, University Park
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2009

Citing 0
Cited 15

Non-local scan consolidation for 3D urban scenes

ACM SIGGRAPH 2010 papers
Resizing by symmetry-summarization

ACM SIGGRAPH Asia 2010 papers
Translation-symmetry-based perceptual grouping with applications to urban scenes

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
Geo-localization of street views with aerial image databases

MM '11 Proceedings of the 19th ACM international conference on Multimedia
Symmetry-guided texture synthesis and manipulation

ACM Transactions on Graphics (TOG)
Visual pattern discovery for architecture image classification and product image search

Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
Digital reconstruction of halftoned color comics

ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH Asia 2012
Dynamics of a mean-shift-like algorithm and its applications on clustering

Information Processing Letters
Discrimination and description of repetitive patterns for enhancing the performance of feature-based recognition

Image and Vision Computing
Ultra-wide baseline facade matching for geo-localization

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Dynamic markov random field model for visual tracking

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Online Detection of Repeated Structures in Point Clouds of Urban Scenes for Compression and Registration

International Journal of Computer Vision
Scale detection via keypoint density maps in regular or near-regular textures

Pattern Recognition Letters
Unified detection of skewed rotation, reflection and translation symmetries from affine invariant contour features

Pattern Recognition
Lattice estimation from images of patterns that exhibit translational symmetry

Image and Vision Computing

Quantified Score

Hi-index	0.15

Visualization

Abstract

We propose a novel and robust computational framework for automatic detection of deformed 2D wallpaper patterns in real-world images. The theory of 2D crystallographic groups provides a sound and natural correspondence between the underlying lattice of a deformed wallpaper pattern and a degree-4 graphical model. We start the discovery process with unsupervised clustering of interest points and voting for consistent lattice unit proposals. The proposed lattice basis vectors and pattern element contribute to the pairwise compatibility and joint compatibility (observation model) functions in a Markov Random Field (MRF). Thus, we formulate the 2D lattice detection as a spatial, multitarget tracking problem, solved within an MRF framework using a novel and efficient Mean-Shift Belief Propagation (MSBP) method. Iterative detection and growth of the deformed lattice are interleaved with regularized thin-plate spline (TPS) warping, which rectifies the current deformed lattice into a regular one to ensure stability of the MRF model in the next round of lattice recovery. We provide quantitative comparisons of our proposed method with existing algorithms on a diverse set of 261 real-world photos to demonstrate significant advances in accuracy and speed over the state of the art in automatic discovery of regularity in real images.