1 / 31

The Segmentation Problem

The Segmentation Problem. Segmentation attempts to partition the pixels of an image into groups that strongly correlate with the objects in an image Typically the first step in any automated computer vision application. Image Segmentation.

raine
Télécharger la présentation

The Segmentation Problem

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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. The Segmentation Problem Segmentation attempts to partition the pixels of an image into groups that strongly correlate with the objects in an image Typically the first step in any automated computer vision application

  2. EE 7730 - Image Analysis I Image Segmentation • Group similar components (such as, pixels in an image, image frames in a video) to obtain a compact representation. • Applications: Finding tumors, veins, etc. in medical images, finding targets in satellite/aerial images, finding people in surveillance images, summarizing video, etc. • Methods: Thresholding, region growing, k-means.

  3. EE 7730 - Image Analysis I Image Segmentation • Segmentation algorithms for monochrome images generally are based on one of two basic properties of gray-scale values: • Discontinuity • The approach is to partition an image based on abrupt changes in gray-scale levels. • The principal areas of interest within this category are detection of isolated points, lines, and edges in an image. • Similarity • The principal approaches in this category are based on thresholding, region growing, and region splitting/merging.

  4. Segmentation Examples Images taken from Gonzalez & Woods, Digital Image Processing (2002)

  5. Detection Of Discontinuities There are three basic types of grey level discontinuities that we tend to look for in digital images: • Points • Lines • Edges We typically find discontinuities using masks and correlation

  6. Point Detection Images taken from Gonzalez & Woods, Digital Image Processing (2002) Point detection can be achieved simply using the mask below: Points are detected at those pixels in the subsequent filtered image that are above a set threshold

  7. Point Detection (cont…) Images taken from Gonzalez & Woods, Digital Image Processing (2002) X-ray image of a turbine blade Result of point detection Result of thresholding

  8. Line Detection Images taken from Gonzalez & Woods, Digital Image Processing (2002) The next level of complexity is to try to detect lines The masks below will extract lines that are one pixel thick and running in a particular direction

  9. Line Detection (cont…) Images taken from Gonzalez & Woods, Digital Image Processing (2002) Binary image of a wire bond mask After processing with -45° line detector Result of thresholding filtering result

  10. Edge Detection Images taken from Gonzalez & Woods, Digital Image Processing (2002) An edge is a set of connected pixels that lie on the boundary between two regions

  11. Edges & Derivatives Images taken from Gonzalez & Woods, Digital Image Processing (2002) We have already spokenabout how derivatives are used to find discontinuities 1st derivative tells us where an edge is 2nd derivative canbe used to show edge direction

  12. Derivatives & Noise Images taken from Gonzalez & Woods, Digital Image Processing (2002) Derivative based edge detectors are extremely sensitive to noise We need to keep this in mind

  13. Common Edge Detectors Images taken from Gonzalez & Woods, Digital Image Processing (2002) Given a 3*3 region of an image the following edge detection filters can be used

  14. Edge Detection Example Images taken from Gonzalez & Woods, Digital Image Processing (2002) Original Image Horizontal Gradient Component Vertical Gradient Component Combined Edge Image

  15. Edge Detection Problems Often, problems arise in edge detection in that there are is too much detail For example, the brickwork in the previous example One way to overcome this is to smooth images prior to edge detection

  16. Edge Detection Example With Smoothing Images taken from Gonzalez & Woods, Digital Image Processing (2002) Original Image Horizontal Gradient Component Vertical Gradient Component Combined Edge Image

  17. Laplacian Edge Detection Images taken from Gonzalez & Woods, Digital Image Processing (2002) We encountered the 2nd-order derivative based Laplacian filter already The Laplacian is typically not used by itself as it is too sensitive to noise Usually then used for edge detection the Laplacian is combined with a smoothing Gaussian filter

  18. Laplacian Of Gaussian Images taken from Gonzalez & Woods, Digital Image Processing (2002) The Laplacian of Gaussian (or Mexican hat) filter uses the Gaussian for noise removal and the Laplacian for edge detection

  19. Laplacian Of Gaussian Example Images taken from Gonzalez & Woods, Digital Image Processing (2002)

  20. Edge Linking and Boundary Detection • Local Processing • Global Processing • Graph-Theoretic Techniques

  21. Local Processing • Edge Linking using gradient and gradient direction.

  22. Graph-Theoretic Techniques

More Related