Pipeline

The main high-level interface for OCR processing.

class manuscript._pipeline.Pipeline(detector=<object object>, layout=<object object>, recognizer=<object object>, corrector=None, layout_after='detector')

Bases: object

High-level OCR pipeline with configurable stage ordering.

Default pipeline: detector -> layout -> recognizer. corrector is optional and disabled by default.

Attributes:

last_correction_page

last_detection_page

last_layout_page

last_recognition_page

Parameters:

• detector (DetectorProtocol)

• layout (LayoutProtocol | None)

• recognizer (RecognizerProtocol | None)

• corrector (CorrectorProtocol | None)

• layout_after (str)

Methods

get_text(page)	Extract plain text from Page object.
predict(image[, vis, profile])	Run pipeline on a single image.

__init__(detector=<object object>, layout=<object object>, recognizer=<object object>, corrector=None, layout_after='detector')

Initialize OCR pipeline.

Parameters:

• detector (object, optional) – Detector instance with predict(image) -> Page. If omitted, default YOLO(weights="yolo26x_obb_text_g1") is used. Detector cannot be disabled.

• layout (object or None, optional) – Layout model instance with predict(page, image=None) -> Page. If omitted, default SimpleSorting() is used. Pass None to disable layout stage.

• recognizer (object or None, optional) – Recognizer instance with predict(page, image=None, ...) -> Page. If omitted, default TRBA(weights="trba_lite_g2") is used. Pass None to disable recognition stage.

• corrector (object or None, optional) – Corrector instance with predict(page, image=None) -> Page. Default is None (disabled).

• layout_after ({"detector", "recognizer", "corrector"}, optional) – Slot where layout stage is executed. Default is "detector".

predict(image, vis=False, profile=False)

Run pipeline on a single image.

Parameters:

• image (str, Path, numpy.ndarray, or PIL.Image) – Input image.

• vis (bool, optional) – If True, returns visualization image together with result.

• profile (bool, optional) – If True, prints timing per stage.

Return type:

Union[Dict[str, Page], tuple]

get_text(page)

Extract plain text from Page object.

Return type:

str

Parameters:

page (Page)

property last_detection_page: Page | None

property last_layout_page: Page | None

property last_recognition_page: Page | None

property last_correction_page: Page | None