VivaKitDocument OCR & Key Field Extraction
Digitize and extract structured business intelligence from Indian GST invoices, medical bills, and university tuition receipts. Powered by EasyOCR with CRAFT character-region text detection and CRNN sequence recognition, coupled with a spatial rule-based Key Information Extraction (KIE) engine. Automatically identifies document types, validates 15-character Indian statutory GSTIN numbers, normalizes dates, computes tax integrity checks, and exports ERP-ready JSON with interactive colored polygon bounding overlays.
Secure checkout by Dodo Payments (UPI, cards). Your personalised download link is e-mailed within 24 hours. One purchase covers one project team of up to 4 students. See terms and refunds.
Our honest results
| Key Field Extraction Macro-F1 (synthetic) | 100.0% (18 field checks on the 3-document synthetic suite) |
| CPU Inference Latency | ~3 s per full-page document (EasyOCR, offline) |
| Statutory GSTIN Format Validation | 100.0% (15-char regex check) |
| Single-Page CPU Processing Latency | 3.51 s (fully local, zero GPU needed) |
Evaluated on photorealistic synthetic Indian commercial and administrative documents rendered with exact word-level ground-truth coordinates. Includes complete synthetic document generator, automated test suite, and 15 viva voce questions for academic project defense.
What's included
- Readable source codeSmall, commented modules you can explain line by line in your viva.
- Demo appA local web app to show your examiners - runs offline on your laptop.
- Trained model + reference resultsSo you can compare your own runs fairly.
- Learning guide with viva Q&ABackground, design choices explained, limitations and extension ideas.
- One-click setup & testsWindows setup script and tests that prove it works on your PC.
- Dataset download scriptFetches the public data from its original source, with the citation.
Dataset credit
EasyOCR by Jaided AI (Apache-2.0 Licence), CRAFT text detection by NAVER Corp. (MIT Licence). Synthetic Indian commercial invoice and billing dataset with exact ground-truth annotations.
Academic integrity
We sell code and teaching, not finished projects. You must understand, extend and write up the work yourself, acknowledge the kit and cite the dataset. No ready-made reports.