01
Invoices & annexures
Invoice Reader
Read multi-page invoices, freight rows, and shipment annexures while preserving the source structure.
Layout detectionDynamic tablesStructured JSON
Loading website
Loading website
AI-Kalp OCR brings focused readers for invoices, logistics documents, registration plates, fuel displays, container images, and verification workflows into one practical suite.
Document readers
Process invoices, Bills of Entry, container images, fuel displays, vehicle registrations, shipping documents, and verification tasks.
Invoices & annexures
Read multi-page invoices, freight rows, and shipment annexures while preserving the source structure.
Bill of Entry
Parse a BOE page by page and prepare structured fields, raw text, JSON output, and report-ready data.
Container images
Upload a container photograph, keep the source image visible, and read the container information through OCR.
Scanned documents
Handle invoices, letters, declarations, screenshots, and scanned documents with layout-friendly extraction.
Fuel pump display
Read mobile fuel-pump snapshots with priority given to litres or quantity, amount, rate, and the full display.
Number plate
Detect an Indian vehicle registration number across likely regions and repair common OCR character mistakes.
Form 13 / E-Gate Form
Read supported text PDFs page by page and clearly reject scanned, image-only, or unsupported files.
Shipping bill PDFs
Support ICES and US Computers layouts with page preview, source fields, metadata, raw text, and full JSON.
Seal image verification
Find the likely seal region, read the primary seal number, and compare it with an expected value.
From file to workflow
Step 1
Upload a supported PDF or image.
Step 2
Detect the relevant document or visual region.
Step 3
Organise fields, tables, text, and metadata.
Step 4
Export, verify, report, or continue the workflow.
Structured output
Review source pages, work with structured fields and tables, validate supported values, and export results for downstream use.
Page and image previews keep extracted information connected to its source.
Supported readers organise document fields, page data, tables, and metadata.
Available flows include JSON and, where supported, PDF, Word, Excel, and reports.
File-type checks and expected-value comparisons make supported workflows clearer.