ID-Doc OCR 🇮🇩
ID-Doc OCR adalah framework Python open-source local-first untuk mengekstraksi data terstruktur dari berbagai dokumen identitas Indonesia (KTP, SIM, Paspor, STNK) menjadi model data Pydantic V2 (Type-Safe) dan JSON terformat.
🚀 Fitur Utama (v0.2.0)
- Multi-Dokumen Identitas: Ekstraksi KTP, SIM (Surat Izin Mengemudi), Paspor Indonesia, dan STNK.
- Auto-Detection (
doc_type="auto"): Otomatis mengenali jenis dokumen berbasis analisis kata kunci OCR mentah. - Auto-Cropping & Perspective Transform: Deteksi 4 sudut fisik kartu (
cv2.approxPolyDP) & perataan posisi miring (cv2.warpPerspective) dengan graceful fallback. - Validasi Matematika NIK KTP: Validasi struktur 16-digit NIK (Provinsi, Kabupaten, tanggal lahir DDMMYY dengan offset wanita $+40$) & koreksi otomatis typo OCR (
O->0,I->1,B->8). - Pydantic V2 Schemas: Output data tervalidasi tipe datanya (
KTPSchema,SIMSchema,PasporSchema,STNKSchema). - Zero-Dependency ONNX Fallback Engine: Pilihan engine ringan on-device via ONNX Runtime tanpa perlu menginstal binary C++ Tesseract di OS.
- Built-in REST API Microservice: Server FastAPI siap pakai via CLI (
akshara-ocr serve --port 8000) dengan OpenAPI Swagger docs.
🛡️ Privacy-by-Design & Kepatuhan Hukum (UU PDP)
[!IMPORTANT] Pernyataan Privasi & Kepatuhan UU PDP (UU No. 27 Tahun 2022):
- 100% Local-First & In-Memory: Seluruh pemrosesan gambar dan ekstraksi data berjalan secara lokal di perangkat/server pengguna. TIDAK ADA data atau foto yang diunggah ke server cloud pihak ketiga.
- No Logging by Default: Gambar input dan hasil ekstraksi JSON tidak pernah ditulis ke disk atau disimpan dalam log file secara otomatis.
- BUKAN Alat Verifikasi Identitas Resmi: Library ini adalah alat bantu ekstraksi teks (text extraction helper), BUKAN alat verifikasi identitas resmi/legal atau deteksi keaslian dokumen (liveness/fraud detection). Pengembang dan pengguna library bertanggung jawab penuh atas kepatuhan terhadap UU Pelindungan Data Pribadi (UU PDP) saat mengimplementasikan library ini pada aplikasi produksi.
- Penggunaan Data Uji Sintetis: Seluruh pengujian dan pengembangan WAJIB menggunakan data dummy/sintetis fiktif. Dilarang menggunakan foto KTP/SIM/Paspor asli siapa pun untuk testing.
🎯 Panduan Confidence Score & Manual Review
[!TIP] Rekomendasi Verifikasi Produksi: Library ini menyediakan metadata tingkat keyakinan OCR per field pada
meta.confidence_per_field. Aturan Praktis: Field dengan confidence score di bawah 70% disarankan untuk diverifikasi secara manual oleh operator/pengguna (human-in-the-loop) sebelum disimpan ke database produksi aplikasi Anda.
📦 Instalasi
1. Install Package Python
# Instalasi standar (Tesseract engine)
pip install akshara-ocr
# Instalasi lengkap (termasuk ONNX engine & REST API server)
pip install "akshara-ocr[all]"
2. Prasyarat Binary Tesseract OCR (Default Engine)
Jika menggunakan default Tesseract engine:
- Windows:
winget install --id UB-Mannheim.TesseractOCR -e - Linux (Ubuntu/Debian):
sudo apt-get install -y tesseract-ocr tesseract-ocr-ind - macOS:
brew install tesseract
(Catatan: Jika menginstal versi pip install akshara-ocr[onnx], Anda tidak perlu menginstal binary Tesseract di OS!)
💻 Contoh Penggunaan Python SDK
from akshara_ocr import IDDocOCR, KTPSchema
# Inisialisasi SDK dengan auto-detection tipe dokumen
sdk = IDDocOCR(doc_type="auto", auto_crop=True)
# Ekstraksi dari path gambar (bisa juga dari bytes atau numpy ndarray)
result: KTPSchema = sdk.extract("path/to/ktp_photo.jpg")
# Output Pydantic V2 Schema & JSON
print(result.nik) # "3573012304950001"
print(result.nik_valid) # True
print(result.provinsi_code) # "35"
# Convert ke formatted JSON string
print(result.model_dump_json(indent=2, by_alias=True))
🌐 CLI & REST API Microservice
Ekstraksi Langsung via Terminal (CLI)
# Ekstraksi KTP
akshara-ocr path/to/ktp_photo.png
# Simpan ke file JSON
akshara-ocr path/to/ktp_photo.png -o result.json
Menjalankan REST Microservice Server
# Jalankan FastAPI REST Server pada port 8000
akshara-ocr serve --port 8000
Akses Interactive OpenAPI Swagger Documentation di browser pada: http://127.0.0.1:8000/docs
📜 Lisensi
Lisensi open-source MIT License.
Metadata
Release files for akshara-ocr 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| akshara_ocr-0.3.0.tar.gz | 33.1 kB | With provenance | Details for akshara_ocr-0.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| akshara_ocr-0.3.0-py3-none-any.whl | Python 3 | none | any | Details for akshara_ocr-0.3.0-py3-none-any.whl |
Total release size: 71.8 kB
Release files / akshara_ocr-0.3.0.tar.gz
| Download URL | akshara_ocr-0.3.0.tar.gz |
|---|---|
| Size | 33.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
91c6d13d91bd241cd0a102101d01a11d12f28a2b9b437abfa78c6d8c6ce853df
|
|
BLAKE2b-256 checksum How to use checksums |
9c576d62a9ebbd8f52495a2284127b712b8d8469307ff70743d4329877cc87a6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 31, 2026.
Transparency logRelease files / akshara_ocr-0.3.0-py3-none-any.whl
| Download URL | akshara_ocr-0.3.0-py3-none-any.whl |
|---|---|
| Size | 38.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b10fbd36c3b2d78b01dfe84cac49fffe3f8db2b0148a0ef98ce97348e91a937d
|
|
BLAKE2b-256 checksum How to use checksums |
4bb029d4a7cbe5b35902993c5637b25147dbf54ae119752ab6d82f22611b42f0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 31, 2026.
Transparency logSecurity for akshara-ocr 0.3.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for akshara_ocr-0.3.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 31, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.