954103cdf2
Backend: build_word_grid() intersects column regions with content rows, OCRs each cell with language-specific Tesseract, and returns vocabulary entries with percent-based bounding boxes. New endpoints: POST /words, GET /image/words-overlay, ground-truth save/retrieve for words. Frontend: StepWordRecognition with overview + step-through labeling modes, goToStep callback for row correction feedback loop. MkDocs: OCR Pipeline documentation added. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
5 lines
234 B
SQL
5 lines
234 B
SQL
-- Migration 004: Add word_result column for OCR Pipeline Step 5
|
|
-- Stores the word recognition grid result (entries with english/german/example + bboxes)
|
|
|
|
ALTER TABLE ocr_pipeline_sessions ADD COLUMN IF NOT EXISTS word_result JSONB;
|