mirror of
https://github.com/qurator-spk/eynollah.git
synced 2025-10-27 07:44:12 +01:00
147 lines
6.1 KiB
JSON
147 lines
6.1 KiB
JSON
{
|
|
"version": "0.6.0",
|
|
"git_url": "https://github.com/qurator-spk/eynollah",
|
|
"dockerhub": "ocrd/eynollah",
|
|
"tools": {
|
|
"ocrd-eynollah-segment": {
|
|
"executable": "ocrd-eynollah-segment",
|
|
"categories": ["Layout analysis"],
|
|
"description": "Segment page into regions and lines and do reading order detection with eynollah",
|
|
"input_file_grp_cardinality": 1,
|
|
"output_file_grp_cardinality": 1,
|
|
"steps": ["layout/segmentation/region", "layout/segmentation/line"],
|
|
"parameters": {
|
|
"models": {
|
|
"type": "string",
|
|
"format": "uri",
|
|
"content-type": "text/directory",
|
|
"cacheable": true,
|
|
"description": "Directory containing models to be used (See https://qurator-data.de/eynollah)",
|
|
"required": true
|
|
},
|
|
"dpi": {
|
|
"type": "number",
|
|
"format": "float",
|
|
"description": "pixel density in dots per inch (overrides any meta-data in the images); ignored if <= 0 (with fall-back 230)",
|
|
"default": 0
|
|
},
|
|
"full_layout": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Try to detect all element subtypes, including drop-caps and headings"
|
|
},
|
|
"light_version": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Try to detect all element subtypes in light version (faster+simpler method for main region detection and deskewing)"
|
|
},
|
|
"textline_light": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Light version need textline light. If this parameter set to true, this tool will try to return contoure of textlines instead of rectangle bounding box of textline with a faster method."
|
|
},
|
|
"tables": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "Try to detect table regions"
|
|
},
|
|
"curved_line": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "try to return contour of textlines instead of just rectangle bounding box. Needs more processing time"
|
|
},
|
|
"ignore_page_extraction": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "if this parameter set to true, this tool would ignore page extraction"
|
|
},
|
|
"allow_scaling": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "check the resolution against the number of detected columns and if needed, scale the image up or down during layout detection (heuristic to improve quality and performance)"
|
|
},
|
|
"allow_enhancement": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "if this parameter set to true, this tool would check that input image need resizing and enhancement or not."
|
|
},
|
|
"right_to_left": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "if this parameter set to true, this tool will extract right-to-left reading order."
|
|
},
|
|
"headers_off": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "ignore the special role of headings during reading order detection"
|
|
},
|
|
"reading_order_machine_based": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "use data-driven (rather than rule-based) reading order detection"
|
|
}
|
|
},
|
|
"resources": [
|
|
{
|
|
"url": "https://zenodo.org/records/17194824/files/models_layout_v0_5_0.tar.gz?download=1",
|
|
"name": "models_layout_v0_5_0",
|
|
"type": "archive",
|
|
"path_in_archive": "models_layout_v0_5_0",
|
|
"size": 3525684179,
|
|
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization, image enhancement",
|
|
"version_range": ">= v0.5.0"
|
|
},
|
|
{
|
|
"description": "models for eynollah (TensorFlow SavedModel format)",
|
|
"url": "https://github.com/qurator-spk/eynollah/releases/download/v0.3.1/models_eynollah.tar.gz",
|
|
"name": "default",
|
|
"size": 1894627041,
|
|
"type": "archive",
|
|
"path_in_archive": "models_eynollah",
|
|
"version_range": ">= v0.3.0, < v0.5.0"
|
|
}
|
|
]
|
|
},
|
|
"ocrd-sbb-binarize": {
|
|
"executable": "ocrd-sbb-binarize",
|
|
"description": "Pixelwise binarization with selectional auto-encoders in Keras",
|
|
"categories": ["Image preprocessing"],
|
|
"steps": ["preprocessing/optimization/binarization"],
|
|
"input_file_grp_cardinality": 1,
|
|
"output_file_grp_cardinality": 1,
|
|
"parameters": {
|
|
"operation_level": {
|
|
"type": "string",
|
|
"enum": ["page", "region"],
|
|
"default": "page",
|
|
"description": "PAGE XML hierarchy level to operate on"
|
|
},
|
|
"model": {
|
|
"description": "Directory containing HDF5 or SavedModel/ProtoBuf models. Can be an absolute path or a path relative to the OCR-D resource location, the current working directory or the $SBB_BINARIZE_DATA environment variable (if set)",
|
|
"type": "string",
|
|
"format": "uri",
|
|
"content-type": "text/directory",
|
|
"required": true
|
|
}
|
|
},
|
|
"resources": [
|
|
{
|
|
"url": "https://github.com/qurator-spk/sbb_binarization/releases/download/v0.0.11/saved_model_2020_01_16.zip",
|
|
"name": "default",
|
|
"type": "archive",
|
|
"path_in_archive": "saved_model_2020_01_16",
|
|
"size": 563147331,
|
|
"description": "default models provided by github.com/qurator-spk (SavedModel format)"
|
|
},
|
|
{
|
|
"url": "https://github.com/qurator-spk/sbb_binarization/releases/download/v0.0.11/saved_model_2021_03_09.zip",
|
|
"name": "default-2021-03-09",
|
|
"type": "archive",
|
|
"path_in_archive": ".",
|
|
"size": 133230419,
|
|
"description": "updated default models provided by github.com/qurator-spk (SavedModel format)"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|