mirror of
https://github.com/qurator-spk/eynollah.git
synced 2026-07-26 05:29:16 +02:00
277 lines
12 KiB
JSON
277 lines
12 KiB
JSON
{
|
|
"version": "0.9.0",
|
|
"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 detect reading order with Eynollah",
|
|
"input_file_grp_cardinality": 1,
|
|
"output_file_grp_cardinality": 1,
|
|
"steps": ["layout/segmentation/region", "layout/segmentation/line"],
|
|
"parameters": {
|
|
"device": {
|
|
"type": "string",
|
|
"default": "",
|
|
"description": "Allocate models to computation device; can be a single device name for all models, or a comma-delimited, colon-tagged mapping from model category to device name (where model categories are binarization, col_classifier, page, textline, region_1_2, region_fl_np, table, reading_order, but can be abbreviated by glob expressions), e.g. col*:CPU,page:GPU0,*:GPU1. If empty, selects the first available GPU for all models."
|
|
},
|
|
"models": {
|
|
"type": "string",
|
|
"format": "uri",
|
|
"content-type": "text/directory",
|
|
"cacheable": true,
|
|
"description": "Directory containing models to be used (See https://huggingface.co/collections/SBB/eynollah-models)",
|
|
"required": true
|
|
},
|
|
"model_overrides": {
|
|
"type": "object",
|
|
"properties": {
|
|
"binarization": {
|
|
"type": "object"
|
|
},
|
|
"enhancement": {
|
|
"type": "object"
|
|
},
|
|
"col_classifier": {
|
|
"type": "object"
|
|
},
|
|
"page": {
|
|
"type": "object"
|
|
},
|
|
"textline": {
|
|
"type": "object"
|
|
},
|
|
"region_1_2": {
|
|
"type": "object"
|
|
},
|
|
"region_fl_np": {
|
|
"type": "object"
|
|
},
|
|
"table": {
|
|
"type": "object"
|
|
},
|
|
"reading_order": {
|
|
"type": "object"
|
|
}
|
|
},
|
|
"description": "Map model categories to mappings from model variant to model path, e.g. {'ocr': {'tr': 'path/to/my/trocr-model'}}."
|
|
},
|
|
"dpi": {
|
|
"type": "number",
|
|
"format": "float",
|
|
"description": "ignored (only for backwards-compatibility)",
|
|
"default": 0
|
|
},
|
|
"full_layout": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Try to detect all region subtypes, including drop-capital and heading"
|
|
},
|
|
"light_version": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"enum": [true],
|
|
"description": "ignored (only for backwards-compatibility)"
|
|
},
|
|
"textline_light": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"enum": [true],
|
|
"description": "ignored (only for backwards-compatibility)"
|
|
},
|
|
"tables": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "Try to detect table regions"
|
|
},
|
|
"curved_line": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "retrieve textline polygons independent of each other (needs more processing time)"
|
|
},
|
|
"ignore_page_extraction": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "if true, do not attempt page frame detection (cropping)"
|
|
},
|
|
"skip_layout_and_reading_order": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "skip regions, only run textlines, stuffing them in a single text region for the entire page"
|
|
},
|
|
"binarize": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "run adaptive thresholding on input image with dedicated model before analysis (may be useful for degraded input)."
|
|
},
|
|
"allow_scaling": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "ignored (only for backwards-compatibility)"
|
|
},
|
|
"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 true, return reading order in right-to-left reading direction."
|
|
},
|
|
"num_col_upper": {
|
|
"type": "number",
|
|
"format": "integer",
|
|
"minimum": 0,
|
|
"default": 0,
|
|
"description": "Constrain detection of number of columns by this upper boundary (ignored when zero)."
|
|
},
|
|
"num_col_lower": {
|
|
"type": "number",
|
|
"format": "integer",
|
|
"minimum": 0,
|
|
"default": 0,
|
|
"description": "Constrain detection of number of columns by this lower boundary (ignored when zero)."
|
|
},
|
|
"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/21381102/files/models_inference_layout_v0_9_1.zip",
|
|
"name": "models_inference_layout_v0_9_1",
|
|
"type": "archive",
|
|
"size": 1847700967,
|
|
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization and image enhancement",
|
|
"version_range": ">= v0.9.0"
|
|
},
|
|
{
|
|
"url": "https://zenodo.org/records/21362927/files/models_inference_layout_v0_9_0.zip",
|
|
"name": "models_inference_layout_v0_9_0",
|
|
"type": "archive",
|
|
"size": 1572255489,
|
|
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization and image enhancement",
|
|
"version_range": ">= v0.9.0"
|
|
},
|
|
{
|
|
"url": "https://zenodo.org/records/17727267/files/models_all_v0_8_0.zip",
|
|
"name": "models_all_v0_8_0",
|
|
"type": "archive",
|
|
"size": 5636009377,
|
|
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization and image enhancement",
|
|
"version_range": ">= v0.8.0"
|
|
},
|
|
{
|
|
"url": "https://zenodo.org/records/17580627/files/models_all_v0_7_0.zip?download=1",
|
|
"name": "models_layout_v0_7_0",
|
|
"type": "archive",
|
|
"size": 6119874002,
|
|
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization, image enhancement and OCR",
|
|
"version_range": ">= v0.7.0"
|
|
},
|
|
{
|
|
"url": "https://zenodo.org/records/17295988/files/models_layout_v0_6_0.tar.gz?download=1",
|
|
"name": "models_layout_v0_6_0",
|
|
"type": "archive",
|
|
"path_in_archive": "models_layout_v0_6_0",
|
|
"size": 3525684179,
|
|
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization, image enhancement and OCR",
|
|
"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://zenodo.org/records/21381102/files/models_inference_layout_v0_9_1.zip",
|
|
"name": "models_inference_layout_v0_9_1",
|
|
"type": "archive",
|
|
"size": 1847700967,
|
|
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization and image enhancement",
|
|
"version_range": ">= v0.9.0"
|
|
},
|
|
{
|
|
"url": "https://zenodo.org/records/21381102/files/models_inference_all_v0_9_1.zip",
|
|
"name": "models_inference_all_v0_9_1",
|
|
"type": "archive",
|
|
"size": 3761011909,
|
|
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization and image enhancement",
|
|
"version_range": ">= v0.9.0"
|
|
},
|
|
{
|
|
"url": "https://zenodo.org/records/17727267/files/models_all_v0_8_0.zip",
|
|
"name": "models_all_v0_8_0",
|
|
"type": "archive",
|
|
"size": 5636009377,
|
|
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization and image enhancement",
|
|
"version_range": ">= v0.8.0"
|
|
},
|
|
{
|
|
"url": "https://zenodo.org/records/17580627/files/models_all_v0_7_0.zip?download=1",
|
|
"name": "models_layout_v0_7_0",
|
|
"type": "archive",
|
|
"size": 6119874002,
|
|
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization, image enhancement and OCR",
|
|
"version_range": ">= v0.7.0"
|
|
},
|
|
{
|
|
"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)",
|
|
"version_range": "< v0.7.0"
|
|
},
|
|
{
|
|
"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)",
|
|
"version_range": "< v0.7.0"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|