• Corpus ID: 239616064

Adaptive Fusion Affinity Graph with Noise-free Online Low-rank Representation for Natural Image Segmentation

  title={Adaptive Fusion Affinity Graph with Noise-free Online Low-rank Representation for Natural Image Segmentation},
  author={Yang Zhang and Moyun Liu and Huiming Zhang and Guodong Sun and Jingwu He},
Affinity graph-based segmentation methods have become a major trend in computer vision. The performance of these methods rely on the constructed affinity graph, with particular emphasis on the neighborhood topology and pairwise affinities among superpixels. Due to the advantages of assimilating different graphs, a multi-scale fusion graph has a better performance than a single graph with single-scale. However, these methods ignore the noise from images which influence the accuracy of pairwise… 
1 Citations

Particle Swarm Optimization Embedded in UAV as a Method of Territory-Monitoring Efficiency Improvement

A methodology for terrain classification based on particle swarm optimization was developed and validated, which can provide high quality territory monitoring and plan to establish a self-positioning system based on computer vision.



An Adaptive Affinity Graph with Subspace Pursuit for Natural Image Segmentation

An adaptive affinity graph with subspace pursuit (AASP-graph) for natural image segmentation with improved affinity propagation clustering method to select global nodes of these superpixels adaptively.

A Global/Local Affinity Graph for Image Segmentation

A novel sparse global/local affinity graph over superpixels of an input image is proposed to capture both short- and long-range grouping cues, and thereby enabling perceptual grouping laws, including proximity, similarity, continuity, and to enter in action through a suitable graph-cut algorithm.

A graph-cut approach to image segmentation using an affinity graph based on ℓ0-sparse representation of features

Experimental results on the BSD database demonstrate that the proposed graph-cut based image segmentation method provides perfectly semantic regions even with a constant segmentation number, but also that very competitive quantitative results are achieved.

Learning full pairwise affinities for spectral segmentation

This paper studies the problem of learning a full range of pairwise affinities gained by integrating local grouping cues for spectral segmentation by employing a semi-supervised learning technique and provides high-quality segmentations with object details by directly incorporating the full range connections in the spectral framework.

Segmentation using superpixels: A bipartite graph partitioning approach

A novel segmentation framework based on bipartite graph partitioning is proposed, which is able to aggregate multi-layer superpixels in a principled and very effective manner and leads to a highly efficient, linear-time spectral algorithm.

Image Segmentation UsingHigher-Order Correlation Clustering

The proposed higher-order correlation clustering (HO-CC) framework is formulated in a supervised manner for many high-level computer vision tasks to consider short- and long-range dependency among various regions of an image and also to incorporate wider selection of features.

Image Segmentation Using Linked Mean-Shift Vectors and Global/Local Attributes

The proposed novel noniterative mean-shift-based image segmentation that uses global and local attributes improved segmentation accuracy and improved the speed of the merging process 42 times by applying the RAG.

Segmentation by Fusion of Histogram-Based $K$-Means Clusters in Different Color Spaces

  • M. Mignotte
  • Computer Science
    IEEE Transactions on Image Processing
  • 2008
This paper presents a new, simple, and efficient segmentation approach, based on a fusion procedure which aims at combining several segmentation maps associated to simpler partition models in order

Spectral segmentation with multiscale graph decomposition

The segmentation algorithm works simultaneously across the graph scales, with an inter-scale constraint to ensure communication and consistency between the segmentations at each scale, and incorporates long-range connections with linear-time complexity, providing high-quality segmentations efficiently.

Robust Self-Sparse Fuzzy Clustering for Image Segmentation

The proposed RSSFCA addresses two problems in current fuzzy clustering algorithms, i.e., the outlier sensitivity and the over-segmentation, and it provides better image segmentation results than state-of-the-art algorithms.