v43: Improve VIN extraction with Korean transliteration and bbox zone detection

v42: Fix NoneType error when vin is None in summary

v41: Fix owner name extraction for spaced OCR text

v40: Add purchase price (출고가격) field extraction

v39: Add model-spec lookup for dimension fill/correction

v38: Revert to single Korean OCR engine - fix cpu-basic timeout

v37: Fix race condition - thread-safe OCR engine initialization

v36: Move warmup to background thread so Gradio starts immediately

v35: Skip English engine warmup to prevent startup timeout on cpu-basic

v34: Dual OCR engine (Korean + English) for character-type-aware recognition

v33: Improve OCR accuracy - bbox extraction, Korean fuel types, VIN year, date

v32: Disable OCR in PP-Structure to reduce startup time

v31: Fix ssr parameter - use GRADIO_SSR_MODE env var for compatibility

v30: Fix connection timeout - warmup engines at startup, restore ssr=False

v29: Fix PP-Structure lang error - use 'ch' instead of 'korean' for layout

v28: Add PP-Structure layout analysis engine for form-aware OCR

v27: Update version to v32, add system packages for HF Spaces

v26: disable Gradio SSR to fix HF Spaces Starting infinite loop

v25: Remove opencv-python-headless (already bundled with paddleocr)

v24: Port OCR_Vehicle_02 algorithms - preprocessing, bbox extraction, standards

v23: Fix fuel detection - Hydrogen before LPG, add H2/FCEV keywords

v22: Fix owner name cleanup for bracketless OCR variants

v21: Fix owner name - use next-line extraction for table layout

v20: Fix owner name extraction using ⑨ marker and robust label matching

v19: Fix owner name cleanup, model name extraction, weight/capacity parsing

v18: ISO 3779 VIN validation, OCR correction, and owner name cleanup

feat: improve VIN extraction and show OCR debug in summary (v17)

feat: major parser rewrite for robust field extraction (v16)

fix: broaden document type verification and show OCR preview on skip (v15)

fix: pin PaddlePaddle 2.6.2 + PaddleOCR 2.9.1 to fix PIR runtime crash (v14)

fix: add debug diagnostics for PaddleOCR 3.x result format (v13)

feat: add image preview on file selection (v12)

fix: robust PaddleOCR 3.x result parsing with multi-strategy fallback (v11)

ui: show build version next to title

fix: wrap run_ocr in try-except and improve file path handling

fix: show detailed error messages in UI for debugging

fix: auto-detect PaddleOCR version and use correct API

fix: set python_version 3.10 and sdk_version 5.23.0 for HF Spaces

fix: use unpinned deps matching working HF Spaces config

fix: match proven PaddleOCR HF Spaces config

fix: update sdk_version to 5.23.0 and remove gradio from requirements

fix: pin PaddlePaddle 2.6.2 and add missing system deps for HF Spaces

fix: downgrade PaddlePaddle/PaddleOCR to 2.x for HF Spaces compatibility

docs: add design and implementation plan for HF Spaces deployment

Remove dead code and fix issues from code review

Update requirements.txt for HF Spaces and add packages.txt

Add HuggingFace Spaces README with YAML frontmatter

Add Gradio web app for HuggingFace Spaces deployment

feat: add core processing pipeline (processor.py) and tests

feat: add parse_single() method to CarRegistrationParser