Segmentation techniques: Region growing and split and merge

Mumbai University > Computer Engineering > Sem 7 > Image Processing

Marks: 5 Marks

Year: Dec 2015

  • The objective of segmentation is to partition an image into regions. In this section, segmentation is done by finding the regions directly.
  • Let R represent the entire image region segmentation as a process that partitions R into n sub-regions R_1,R_2,…,R_N such that,

    $R_1∪R_2∪…∪R_(N=) R$

    $R_i$ is connected region where i=1,2,…,N

    $R_i∩R_j=∅ for i≠j$

    Predicate $(R_i )$ =True for all i=1,2,..,N

    There are two different approaches for region oriented segmentation.

    1. Region Growing by Pixel Aggregation:
    2. Region growing is a procedure that groups pixels or sub-regions into larger regions.
    3. Pixel aggregation procedure starts with a set of seed point and from these grows region by appending for each seed point those neighboring pixels that have similar proportion.

    4. Region Splitting & Merging:

    5. In this method an image is first subdivided into a set of arbitrary disjointed region and then merges and/or splits the regions.
    6. Let R represent the entire image region and then select a predicate P.
    7. For image one approach for segmenting R is to subdivide it successively into smaller and smaller quadrant region so that for any region Ri, Predicate(Ri) = True.
    8. If Predicate(Region) = False then divide the image into quadrants.
    9. If Predicate(Region) = False for any quadrant then subdivide that quadrant into sub-quadrants and so on.
Please log in to add an answer.

Next up

Read More Questions

If you are looking for answer to specific questions, you can search them here. We'll find the best answer for you.


Study Full Subject

If you are looking for good study material, you can checkout our subjects. Hundreds of important topics are covered in them.

Know More