Skip this Video
Download Presentation
Allen Y. Yang, John Wright, Shankar Sastry, Yi Ma

Loading in 2 Seconds...

play fullscreen
1 / 15

Allen Y. Yang, John Wright, Shankar Sastry, Yi Ma - PowerPoint PPT Presentation

  • Uploaded on

Compression-based Texture Merging “ Unsupervised Segmentation of Natural Images via Lossy Data Compression ”. Allen Y. Yang, John Wright, Shankar Sastry, Yi Ma. Segmentation cues. Color Edge Contour Texture Filter bank Color value stacks. Filter bank. Response to a 2D-filter bank.

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
Download Presentation

PowerPoint Slideshow about 'Allen Y. Yang, John Wright, Shankar Sastry, Yi Ma' - chavez

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

Compression-based Texture Merging“Unsupervised Segmentation of Natural Images via Lossy Data Compression”

Allen Y. Yang, John Wright, Shankar Sastry, Yi Ma

segmentation cues
Segmentation cues
  • Color
  • Edge
  • Contour
  • Texture
    • Filter bank
    • Color value stacks
filter bank
Filter bank

Response to a 2D-filter bank

color value stacks
Color value stacks
  • A w×w window of each of the three L*a*b channels around each pixel is convoluted with a Gaussian and then all channels are stacked into a single vector v.
two assumptions about natural images
Two assumptions about natural images
  • 1. The distribution of texture features in a natural image is (approximately) a mixture of Gaussians that can be degenerate and of different dimensions, one for each image segment.
  • 2. At any given quantization scale, the optimal segmentation is the one that gives the most compressed representation of the image features, as measured by the number of binary bits needed to encode all the features.
lossy compression
Lossy Compression





rate distortion function
rate-distortion function
  • Memoryless (Independent) Gaussian Source
  • The total number of bits needed to encode the data set V, including bits needed to represent the codebook and mean
  • Upper bound of the total number of bits needed to code V drawn from a mixture of Gaussians
a greedy scheme pairwise steepest descent
A greedy scheme - pairwise steepest descent

As a greedy descent scheme, the algorithm does not guarantee to always find the globally optimal segmentation for any given (V, ε2). In our experience, the main factor affecting the global convergence of the algorithm appears to be the density of the samples relative to the distortion ε2.

image segmentation via lossy compression
Image Segmentation via Lossy Compression
  • Superpixels
  • Region adjacency graph (RAG)

In order to group edge pixels appropriately, we preprocess an image with a low-level segmentation based on local cues such as color and edges. That is, we oversegment the image into (usually several hundred) small, homogeneous regions, known as


Such low-level segmentation can be effectively computed using K-Means or Normalized-Cuts (NCuts)

region adjacency graph rag
Region adjacency graph (RAG)
  • In order to enforce that the resulting segmentation consists of connected segments, we impose an additional spatial constraint that two segments Si and Sj can be merged together only if they are adjacent in the 2D image.
  • We represent the RAG using an adjacency list G{i} for each segment Si.
choosing the distortion
Choosing the Distortion

ε=0.001 ε=0.02 ε=0.05

Heuristically select the scale by stipulating that feature distributions in adjacent regions must be sufficiently dissimilar, i.e.

the distance between the means of the adjacentsegments must be larger than a preselected threshold γ