Optical character recognition
Optical character recognition makes writing in images machine-processable. Reading an amount is not the same as checking an invoice against business rules.
Obtain text from writing in an image
Optical character recognition, or OCR, recognises writing in images or scanned documents and provides it as processable text. Recognition may return words and their positions. Additional structures recognised by a service depend on the method used.
A fictional scanned invoice states 120 EUR. If OCR reads 1,200 EUR, the capture must be checked against the original. If the invoice actually states 1,200 EUR, this is not merely a reading correction: its difference from the expected order needs a business review.
OCR alone does not reliably connect a read value to a business rule and does not authorise payment. Existing digital text or a structured invoice file may enable different processing steps. The data still needs checking in the correct context.
Sources
Related terms
- Confidence scoreA confidence score assesses a model prediction according to a particular method. It does not grant business approval.
- Model cardA model card documents an AI model’s purpose, foundations, evaluation conditions and known limitations for a particular version.
- AI readinessAI readiness concerns the foundations of an AI project: objectives, usable data, skills, responsibilities and an operating workflow.
- Context engineeringContext engineering prepares information for individual model calls: relevant instructions, messages, sources and current states.
- Anomaly detectionMethods that flag unusual observations relative to a defined reference or a learned pattern.
- Forecasting modelA model that uses available information to estimate a future quantity for a defined period.
Articles on this topic
AI & Automation with ASES
AI assistants and automated workflows