Piecewise Flat Embedding for Image Segmentation

@article{Yu2015PiecewiseFE,
  title={Piecewise Flat Embedding for Image Segmentation},
  author={Yizhou Yu and Chaowei Fang and Zicheng Liao},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={1368-1376}
}
Image segmentation is a critical step in many computer vision tasks, including high-level visual recognition and scene understanding as well as low-level photo and video processing. In this paper, we propose a new nonlinear embedding, called piecewise flat embedding, for image segmentation. Based on the theory of sparse signal recovery, piecewise flat embedding attempts to identify segment boundaries while significantly suppressing variations within segments. We adopt an L1-regularized energy… 

Piecewise Flat Embedding for Image Segmentation

A new multi-dimensional nonlinear embedding—Piecewise Flat Embedding (PFE)—for image segmentation based on the theory of sparse signal recovery, which offers an image representation with higher region identifiability which is desirable for image segmentsation or high-level semantic analysis tasks.

Efficiently computing piecewise flat embeddings for data clustering and image segmentation

Two improvements to the algorithm for computing piecewise flat embeddings are proposed, reformulate portions of the algorithm to enable various linear algebra operations to be performed in parallel and propose utilizing an iterative linear solver to quickly solve a linear least-squares problem that occurs in the inner loop of a nested iteration.

Image Segmentation Using Sparse Subset Selection

This paper proposes a numerical algorithm based on the alternating direction method of multipliers (ADMM), whose iterations consist of two highly parallelizable sub-problems, and shows each sub-problem enjoys closed-form solution which makes the ADMM iterations computationally very efficient.

Hierarchical Region Merging for Multi-scale Image Segmentation

The results have shown that the proposed method can solve the error caused by manual threshold setting and achieve the optimal selection of individual goals to a certain extent.

Image Segmentation Using Hierarchical Merge Tree

This paper uses a tree structure to represent the hierarchy of region merging to reduce the problem of segmenting image regions to finding a set of label assignment to tree nodes, and forms a constrained conditional model to associate region merging with likelihoods predicted using an ensemble boundary classifier.

Revisiting graph construction for fast image segmentation

Scale-Aware Alignment of Hierarchical Image Segmentation

The method, as a post-processing step, can significantly improve the quality of the hierarchical segmentation representations, and ease the usage of hierarchical image segmentation to high-level vision tasks such as object segmentation.

Optimization for Image Segmentation

This work proposes regularized losses for weakly-supervised CNN segmentation, in which it can integrate MRF energy or KC criteria as part of the losses.

Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation

This paper proposes a fast image segmentation method based on a novel super boundary-to-pixel direction (super-BPD) and a customized segmentation algorithm with super-B PD, which are novel informative superpixels with robust direction similarity for fast grouping into segmentation regions.

References

SHOWING 1-10 OF 78 REFERENCES

An L1 image transform for edge-preserving smoothing and scene-level intrinsic decomposition

An image transform based on the L1 norm for piecewise image flattening that can effectively preserve and sharpen salient edges and contours while eliminating insignificant details, producing a nearly piecewise constant image with sparse structures is introduced.

Contour Detection and Hierarchical Image Segmentation

This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector

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.

Efficient Graph-Based Image Segmentation

An efficient segmentation algorithm is developed based on a predicate for measuring the evidence for a boundary between two regions using a graph-based representation of the image and it is shown that although this algorithm makes greedy decisions it produces segmentations that satisfy global properties.

Image Segmentation by Cascaded Region Agglomeration

We propose a hierarchical segmentation algorithm that starts with a very fine over segmentation and gradually merges regions using a cascade of boundary classifiers. This approach allows the weights

Recovering Occlusion Boundaries from an Image

This paper proposes a hierarchical segmentation process, based on agglomerative merging, that re-estimates boundary strength as the segmentation progresses, and applies Gestalt grouping principles using a conditional random field (CRF) model.

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first

Automatic image segmentation by integrating color-edge extraction and seeded region growing

We propose a new automatic image segmentation method. Color edges in an image are first obtained automatically by combining an improved isotropic edge detector and a fast entropic thresholding

Normalized cuts and image segmentation

  • Jianbo ShiJ. Malik
  • Computer Science
    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
This work treats image segmentation as a graph partitioning problem and proposes a novel global criterion, the normalized cut, for segmenting the graph, which measures both the total dissimilarity between the different groups as well as the total similarity within the groups.

Contour and Texture Analysis for Image Segmentation

This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture, and introduces a gating operator based on the texturedness of the neighborhood at a pixel to facilitate cue combination.
...