/kmeans-slic-implementation

Superpixel clustering using SLIC algorithm

Primary LanguageJupyter Notebook

Superpixel Clustering using SLIC (Simple Linear Iterative Clustering)

A superpixel can be defined as a group of pixels that share common characteristics. Simple Linear Iterative Clustering (SLIC) generates superpixels by clustering pixels based on their color similarity and proximity in the image plane. The purpose of this project is to understand and implement SLIC Superpixels.

  • This project attempts to:
    • Implement a simple K-Means clustering algorithm in:
      1. RGB (3D) space
      2. RGB + XY (5D) space
      3. Weighted K-Means - different weights for RGB color space and XY space.
    • Implement superpixel clustering using SLIC algorithm (paper).
    • Enforcing connectivity between generated superpixels as a part of the SLIC implementation.