๐Ÿ“Š

Japanese Contract OCR Benchmark โ€” API vs Open Source, Which Is Better?

Google Vision, Azure, PaddleOCR, Sarashina2.2 โ€” accuracy, speed, price comparison on Japanese contracts

Test Conditions

Input: Japanese real estate contract with mixed vertical/horizontal text, specialized terms, special characters.

Expected Performance

Tool CER Vertical Speed
Google Vision ~1-2% Yes ~1s
Sarashina2.2 ~1-3% Yes ~5s
PaddleOCR ~3-5% Yes ~2s
EasyOCR ~5-10% Partial ~3s

Cost (10K pages/month)

Method Monthly Cost
Google Vision ~$15
PaddleOCR $0 (server only)
Sarashina2.2 $0 (needs GPU ~$50/mo)

Selection

Situation Recommendation
Confidential docs Sarashina2.2 (local)
Accuracy first Google Vision
No GPU, free PaddleOCR

Key Concepts

1

Google Vision โ€” highest accuracy (CER ~1-2%) but data sent to external servers

2

Sarashina2.2 โ€” Google-level accuracy + local execution possible. GPU required

3

PaddleOCR โ€” free without GPU. CER ~3-5% practical. Weak on special characters

4

Confidential docs (contracts) โ†’ local execution (Sarashina2.2/PaddleOCR) recommended

Use Cases

Japanese real estate contracts โ€” vertical text + specialized terms + special characters OCR tool selection โ€” compare tools by accuracy, cost, security for your document type Security compliance โ€” local for confidential, API for non-confidential, split operation