Making it installabel package and switching to segmentation mode

QUICKSTART.md

@@ -38,7 +38,7 @@ This will install:
 - OpenCV and Pillow (image processing)
 - And other dependencies
 
-**Note:** The first run will automatically download the YOLOv8s.pt model (~22MB).
+**Note:** The first run will automatically download the YOLOv8s-seg.pt segmentation model (~23MB).
 
 ### 4. Verify Installation
 
@@ -84,11 +84,11 @@ In the Settings dialog:
 ### Single Image Detection
 
 1. Go to the **Detection** tab
-2. Select a model from the dropdown (default: Base Model yolov8s.pt)
+2. Select a model from the dropdown (default: Base Model yolov8s-seg.pt)
 3. Adjust confidence threshold with the slider
 4. Click "Detect Single Image"
 5. Select an image file
-6. View results in the results panel
+6. View results with segmentation masks overlaid on the image
 
 ### Batch Detection
 
@@ -108,9 +108,18 @@ Detection results include:
 - **Class names**: Types of objects detected (e.g., organelle, membrane_branch)
 - **Confidence scores**: Detection confidence (0-1)
 - **Bounding boxes**: Object locations (stored in database)
+- **Segmentation masks**: Pixel-accurate polygon coordinates for each detected object
 
 All results are stored in the SQLite database at [`data/detections.db`](data/detections.db).
 
+### Segmentation Visualization
+
+The application automatically displays segmentation masks when available:
+- Semi-transparent colored overlay (30% opacity) showing the exact shape of detected objects
+- Polygon contours outlining each segmentation
+- Color-coded by object class
+- Toggle-able in future versions
+
 ## Database
 
 The application uses SQLite to store:
@@ -176,7 +185,7 @@ sudo apt-get install libxcb-xinerama0
 ### Detection Not Working
 
 **No models available**
-- The base YOLOv8s model will be downloaded automatically on first use
+- The base YOLOv8s-seg segmentation model will be downloaded automatically on first use
 - Make sure you have internet connection for the first run
 
 **Images not found**