Subject
3 entries
Ocr
Bookmarks
Tearing Down the Rewind App
Kevin Chen's technical teardown of the Rewind app — which records your entire screen continuously while claiming not to tax system resources. The teardown reveals clever use of on-device Apple ML frameworks, differential compression, and local OCR to make this technically feasible.
"Hey Machine, What's My Invoice Total?" (Impira Blog)
Impira's explainer on document understanding ML — how to extract structured data like invoice totals from unstructured documents using layout-aware models. Covers why document AI is harder than it looks and how layout-aware transformers like LayoutLM changed the problem.
Document Processing in Multiple Languages
Nanonets' overview of multilingual document processing — extracting structured data from invoices, forms, and documents in non-English languages. Covers the ML challenges of multilingual OCR and key-value extraction at scale.
