react-native-glyph-ocr: Cyrillic on-device OCR for React Native
New library: Apple Vision on iOS, PaddleOCR on Android. On Russian labels 77–83% ingredients vs 13–28% with ML Kit; already on npm.
Stuzhuk Lab — Chemistry of Code
Chemistry of Code
← All posts
Tag
ocr
All blog posts with this tag.
Lesson 3. Alphabet, labels, format — Train CNN and CRNN from scratch
Train CNN and CRNN from scratch: the blank=0 index contract, label encoding, normalization, and format validation — before the first dataset.
WebGPU + Transformers.js: neural nets straight in the browser
Run ML in React without a mandatory server GPU: WebGPU, Transformers.js, ONNX Runtime, OCR and computer vision, WASM fallback, and model-size budgets.
YOLO: how a network learns to find objects in an image
Object detection in plain engineering language: how YOLO differs from classification and segmentation, what a box, confidence, and duplicate suppression actually mean, why pretrained weights and your own dataset matter, and how to connect a detector with OCR, lines, a graph, and a language model on process diagrams.
Cropping a UT thickness form: projections, gated perspective, and other sheet-splitting methods
Field notes: how the pilot cuts a UT form photo into cells — morphology, projections, gated perspective — and which other sheet-splitting methods show up in industry practice.
Neural network quality metrics: how to know the model actually works
How to choose neural network quality metrics: classification, computer vision, OCR, LLM and RAG, calibration and production indicators — what to measure so the model truly works in the product.
A compact CRNN for UT measurements: 640k parameters and empty cells
Field notes: a local CRNN on thickness crops, CTC, 640k parameters, the empty-cell conflict, and why a Transformer is not the first step.
A compact CRNN does not get better because you hit train: the experiment loop
Third UT-pilot note: error diagnosis, one lever at a time, epochs, the dataset, and when the model should stop being squeezed for points.
Empty cells, dittos, and strike-through: OCR should not decide if a measurement exists
UT pilot sequel: five cell kinds, ink, ditto-up-the-column, strike-through, and why heuristics still do not replace a tiny classifier.
Handwritten UT forms: why one model is not enough
Field notes from a pilot: computer vision, OCR, vision LLMs, confidence, and operator review before ERP — not a finished production guide.
Teaching a Neural Network to Read Handwritten Digits: From CNN to TrOCR
A practical path from single-digit classification to sequence recognition on real paper forms: CNN, CTC, CRNN, TrOCR, labels from your database, experiments, and a production pipeline without the wrong model.
How to Turn a Diagram Image into an Editable Diagram: Full Technology Survey from OCR to AI
Flowcharts, UML, BPMN, network topologies, and CAD drawings: why PNG ≠ diagram, what OCR, vectorization, CAD, computer vision, and VLMs deliver in 2025–2026, and which pipeline actually works.