arXiv
Open Access
2019
One-Shot Template Matching for Automatic Document Data Capture
Pranjal Dhakal
Manish Munikar
Bikram Dahal
Abstrak
In this paper, we propose a novel one-shot template-matching algorithm to automatically capture data from business documents with an aim to minimize manual data entry. Given one annotated document, our algorithm can automatically extract similar data from other documents having the same format. Based on a set of engineered visual and textual features, our method is invariant to changes in position and value. Experiments on a dataset of 595 real invoices demonstrate 86.4% accuracy.
Penulis (3)
P
Pranjal Dhakal
M
Manish Munikar
B
Bikram Dahal
Akses Cepat
Informasi Jurnal
- Tahun Terbit
- 2019
- Bahasa
- en
- Sumber Database
- arXiv
- Akses
- Open Access ✓