{"name": "Raster Vectorizer", "package_name": "raster_vectorizer", "description": "Vectorize scanned topographic maps using interactive HSV colour-range classification", "about": "Converts scanned raster maps (JPEG/PNG/GeoTIFF) into polygon vector layers.\n\nWorkflow:\n1. Draw a rectangle on the map to sample colours\n2. K-means auto-clustering splits the region into colour groups\n3. Adjust HSV ranges and tolerance per class\n4. Run: median pre-filter \u2192 HSV classification \u2192 morphological clean-up \u2192 GDAL Polygonize\n5. Result: a polygon vector layer with class_id and class_name attributes\n\nKey features:\n- HSV colour space matching (perceptually uniform, easy to tune)\n- K-means auto-classification (2\u201325 clusters)\n- Median filter preprocessing (removes JPEG noise without blurring edges)\n- Morphological opening/closing (removes specks, fills gaps)\n- Handles non-standard GeoTransform (rotated/flipped rasters via GDAL Warp)\n- Live preview overlay while editing HSV ranges\n- Export/import colour classes as JSON\n- SciPy optional (NumPy fallback for all operations)\n\nDeveloped as part of a research project under the supervision of\nPavel P. Lepekhin (\u041b\u0435\u043f\u0435\u0445\u0438\u043d \u041f\u0430\u0432\u0435\u043b \u041f\u0430\u0432\u043b\u043e\u0432\u0438\u0447).", "homepage": "https://github.com/terEtiy/qgis-raster-vectorizer", "repository": "https://github.com/terEtiy/qgis-raster-vectorizer", "tracker": "https://github.com/terEtiy/qgis-raster-vectorizer/issues", "author": "\u041a\u0438\u043d\u043e\u0432\u0430\u0440\u044c", "tags": ["raster", "classification", "color", "hsv", "digitize", "morphology", "topographic", "polygonize", "vectorize"], "downloads": 77, "latest_version": "0.1.0", "versions": [{"version": "0.1.0", "experimental": true, "qgis_min": "3.16.0", "qgis_max": "3.99.0", "downloads": 77, "uploaded_by": "terEtiy", "upload_datetime": "2026-05-31T14:02:46.021762"}]}