Python API¶
For a gentle introduction to the python API, please refer to the Introduction to the Python API in the user guide.
The API is built around a few core concepts, primarily the data containers
that are used to pass information between different processing steps. These
containers are defined in the kraken.containers module.
The three primary containers are:
Segmentation: Represents the segmentation of a page, including baselines, bounding boxes, and regions.BaselineLine: Represents the positional and typology information of a line in a segmentation.BaselineOCRRecord: Represents a line of text that has been recognized, including the transcription and confidence scores.
