Image Segmentation

The experiment is designed to understand and learn two classes of Image Segmentation methods. This experiment consists of two different segmentation methods:

a. Histogram-based Segmentation methods
b. Region-growing-based Segmentation method

Steps to run the experiments

  1. Select an image from the mosaic using the 'select image' option.
  2. Select a region of the image to load it into the input image panel.
  3. Select one option from Histogram-based Segmentation or Region-growing.
    • For Histogram-based Segmentation:
      1. Select one of the options: Manual Threshold or Automatic Threshold.
        • Manual Thresholding:
          a. Select Single threshold or Double threshold and press Run.
          b. Adjust the threshold on the image histogram space and press Proceed.
        • Automatic Threshold:
          a. Press Run.
    • For Region-growing:
      1. Select a seed point on the image panel and choose one of the following options:
        • Mean-based:
          a. Select the range for different underlying parameters.
        • Variance-based:
          a. Select the range for different underlying parameters.
      2. Press the Run option to perform the operations.
  4. The output result will be displayed in the output panel.

Interesting Observations

  1. Try using different seed point locations for the region-growing method.
  2. Compare results obtained from two different thresholding methods, particularly on the tiger image.