Module layout_utils 

Layout parsing utilities.

This module provides utilities for layout analysis, including sorting layout boxes and associating OCR results with layout regions. The implementation follows established approaches.

Structs

LayoutBox

Layout box with bounding box and label for sorting/processing purposes.

LayoutOCRAssociation

Result of associating OCR boxes with layout regions.

OverlapRemovalResult

Result of overlap removal.

Functions

associate_ocr_with_layout

Associate OCR results with layout regions.

combine_rectangles_kmeans

Combines rectangles into at most target_n rectangles using KMeans-style clustering on box centers.

get_overlap_boxes_idx

Get indices of OCR boxes that overlap with layout regions.

get_overlap_removal_indices

Removes overlapping layout blocks, returning only indices to remove.

reconcile_table_cells

Reconciles structure recognition cells with detected cells.

remove_overlap_blocks

Removes overlapping layout blocks based on overlap ratio threshold.

reprocess_table_cells_with_ocr

Reprocesses detected table cell boxes using OCR boxes to better match the structure model’s expected cell count.

sort_layout_boxes

Sort layout boxes in reading order with column detection.