How esraa-alii/image-segmentation works
This is a Streamlit image-segmentation application. A user uploads an image, chooses a segmentation or color-conversion method and its available parameters, and views the resulting image. The main branches are clustering, thresholding, region growing, spectral segmentation, and RGB-to-LUV conversion. The graph reflects calls visible in the app excerpt and capabilities documented in the README; it does not infer links for unsampled files or distinguish unshown internal steps.
Main entry points: app.py Streamlit app · KMean.py K-means · meanShift_optimal.py Mean shift · agglomerative.py Agglomerative
Components 10
User interface
- Streamlit app
app.py
Segmentation methods
- K-means
KMean.py - Mean shift
meanShift_optimal.py - Agglomerative
agglomerative.py - Region growing
Region_Growing.py - Spectral threshold
spectral_threshold.py
Image processing
- Optimized threshold
meanShift_optimal.py - Manual and Otsu
Thresholding.py - RGB to LUV
rgb2luv.py
Other components
- User
Connections 11
- User → Streamlit app: uploads image
app.py - User → Streamlit app: selects method
app.py - Streamlit app → K-means: calls clustering
app.py - Streamlit app → Mean shift: calls mean shift
app.py - Streamlit app → Optimized threshold: calls thresholding
app.py - Streamlit app → Spectral threshold: calls thresholding
app.py - Streamlit app → Region growing: calls region growing
app.py - Streamlit app → Agglomerative: calls clustering
app.py - Streamlit app → Manual and Otsu: calls thresholding
app.py - Streamlit app → RGB to LUV: calls conversion
app.py - Streamlit app → User: displays result
app.py