Reading Documents
OCR, parsing, layout, tables, images, and document structure.
Watch the playlist on YouTube →
Posts
Loading posts…
Examples
Short examples of OCR, parsing, layout, tables, and images.
OCR Gets the $202 Total Right but the Inputs Wrong
2026-09-17
OCR Misses the Meaning of Color in an Immunization Table
2026-09-16
OCR Misses 7 Fields on a Census Form
2026-09-15
Count Fixtures on a Floor Plan with OpenCV
2026-09-14
Floor Plan OCR: Calculate Room Area with Code
2026-09-12
Bank Balance Sheet OCR: Check the Digits
2026-09-10
Apple 10-K: OCR on Merged Table Cells
2026-09-09
OCR on Tables with Merged Cells: Markdown vs HTML
2026-09-08
OCR on Clinical Notes: Gemini Rewrites a Lab Entry
2026-09-07
OCR a Wide Table Without Losing Its Formulas
2026-09-02
OCR a Rotated Patent Flowchart Without Losing the Edges
2026-09-01
Accurate Bus Timetable OCR for Less Time and Cost
2026-08-31
OCR Can Miss Draft Watermarks in Legal Documents
2026-08-28
OCR on Graphs: Extracting Data from an FDIC Chart
2026-08-27
Nested Table Extraction Assigns Chris Evans to the Wrong Film
2026-08-26
AWS Textract Extracts a 33-Row Federal Reserve Table
2026-08-25
OCR Cannot Reliably Detect Signatures
2026-08-24
OCR Models Fail on Handwritten Bank Forms
2026-08-14
OCR on Redlined Documents: Testing the Edit Boundary
2026-08-10
OCR Models Fail on Census Grid Forms
2026-08-08
OCR Misses Topographic Map Labels
2026-08-07
OCR Procurement Forms: Blank Fields vs Missed Values
2026-08-06
How to OCR a Diagram
2026-08-05
Extract Financial Tables as Tables or JSON
2026-08-04
When OCR Completes Text It Cannot See
2026-08-01
Transcribe Scanned Equations Into LaTeX With a VLM
2026-07-31
Turn a Map Label Into Normalized Coordinates With a VLM
2026-07-30
Turn a Grouped Bar Chart Into CSV With a VLM
2026-07-29
When PDF Table Extraction Changes 2 Months to 23
2026-07-27
Make a Static PDF Fillable with commonforms
2026-07-26
When OCR Moves a Cell Into the Header
2026-07-23
Extract Handwritten Tables With Structure Intact
2026-07-22
Check OCR Labels and Values Together
2026-07-21
How to Preserve Grouped Headers in a Scanned Table
2026-07-20
How to Extract a Scanned Table Without a Text Layer
2026-07-19
Why Datasheet OCR Needs Product-Specific Evals
2026-07-18
How to Extract IRS Tax Tables Without Losing the Formula
2026-07-17
Plain Text Loses the Structure in Tesla’s Revenue Table
2026-07-16
Why Plain Text Breaks Financial Tables
2026-07-15