TurboLens logo
TurboLens
KhmerReceiptCambodia

Khmer Receipt
OCR Extraction

Extract data from Cambodian receipts with AI trained on Khmer script consonant clusters, dual-currency formats, and mixed-language content.

Sample Extraction Demo

See how TurboLens extracts structured data from Khmer receipt documents.

Input Document

Sample Cambodian receipt with Khmer script

Extracted JSON Output

{
  "merchant_name": "ហាងកាហ្វេ ភ្នំពេញ",  "merchant_name_en": "Phnom Penh Coffee Shop",  "receipt_date": "2025-05-18",  "items": [
  {
  "name": "កាហ្វេទឹកដោះគោ",  "price_usd": 3.5},  {
  "name": "នំបុ័ង",  "price_usd": 2}],  "total_usd": 5.5,  "total_khr": 22000,  "exchange_rate": 4000}
1300ms
Processing Time
Handles Khmer subscript consonant clusters and dual-currency parsing

Extracted Fields

Key data fields extracted from receipt documents.

Merchant Name (Khmer)

merchant_name

Business name in Khmer script

Sample

ហាងកាហ្វេ ភ្នំពេញ

Total (USD)

total_usd

Total amount in US Dollars

Sample

$5.50

Total (KHR)

total_khr

Total amount in Cambodian Riel

Sample

22,000 KHR

Exchange Rate

exchange_rate

USD to KHR exchange rate used

Sample

4,000 KHR/USD

Language & Region Details

Language
Khmer
Code: km
Region
Cambodia
Code: KH
Script Type
Khmer
Direction
Left to Right

Special Handling

  • Khmer consonant clusters and subscript forms (coeng)
  • Dual-currency amounts (KHR and USD) on same receipt
  • Mixed Khmer-English receipt content

Key Features

Purpose-built capabilities for Khmer receipt processing.

Khmer Script Engine

Purpose-built OCR for Khmer script including complex consonant clusters, subscript forms (coeng), and dependent vowels.

Dual-Currency Parsing

Automatically detects and extracts both USD and KHR amounts commonly found on Cambodian receipts, including the exchange rate.

Mixed Script Recognition

Handles receipts with Khmer, English, and numeric content seamlessly for complete data extraction.

ROI & Business Impact

High

Field Accuracy

Extraction accuracy for Khmer receipt fields

<1.3s

Processing Speed

Per-receipt processing time

5,000/hr

Batch Throughput

Khmer receipts processed per hour

Related Capabilities

Thai Receipt OCR Processing
Vietnamese Receipt Extraction

Related Solutions

Banking & Financial Services

Frequently Asked Questions

Khmer script features complex consonant clusters with subscript forms (coeng). TurboLens uses a Khmer-specific OCR model trained on these patterns to accurately recognize stacked and combined characters.

Yes. Cambodia commonly uses both USD and KHR on the same receipt. TurboLens extracts both currency amounts and the exchange rate when present.

Get Started Today

Try DocumentLens for free or contact us for an enterprise solution with dedicated support and custom integrations.

Need Enterprise Support?

Submit an inquiry below or email us at support@turbolens.io