Privacy Policy

Last Updated: 24 January 2026

Privacy Policy

Last Updated: 24 January 2026

1. Introduction

Sinhala OCR ("we", "our", "us") operates a Sinhala Optical Character Recognition (OCR) platform that enables users to upload documents containing Sinhala text (including PDFs and images) and convert such content into machine‑readable Unicode text.

We are committed to protecting user privacy and ensuring transparency in how information is handled. This Privacy Policy explains what information we collect, how it is used, stored, and protected, and the rights available to users of our services.

By accessing or using Sinhala OCR, you agree to the practices described in this Privacy Policy.

2. Information We Collect

2.1 Uploaded Content

When using our OCR services, users may upload:

  • PDF documents
  • Image files (including scanned documents)

Uploaded files may contain Sinhala text and may also include personal or sensitive information depending entirely on the content provided by the user.

Sinhala OCR does not intentionally identify, extract, classify, or analyze personal data contained within uploaded documents. The processing is limited strictly to the technical conversion of visual Sinhala text into Unicode format.

2.2 Personal Information

Sinhala OCR does not require users to submit personal information such as names, addresses, identification numbers, or contact details to use the OCR service.

If personal data exists within uploaded documents, such data is user‑provided content and not information actively collected by Sinhala OCR.

3. Purpose of Data Processing

Uploaded documents are processed and used solely for the following purposes:

  1. OCR Processing
    Converting Sinhala text from uploaded documents into Unicode text output.
  2. Model Training and Improvement
    Improving the accuracy, reliability, and performance of Sinhala OCR’s internal OCR and language models. Training activities are conducted internally and within controlled environments.

Uploaded content is not used for advertising, profiling, analytics unrelated to OCR performance, or any secondary commercial purpose.

4. Data Storage and Retention

4.1 Data Storage

  • Uploaded documents are stored using secure and encrypted storage mechanisms.
  • Encryption is applied both at rest and during transmission.
  • Access to stored data is restricted to authorized systems and personnel only.

4.2 Data Retention

  • Uploaded documents may be retained for a limited period for model training, quality assurance, and system improvement purposes.
  • Retention durations are periodically reviewed and limited to what is reasonably necessary.
  • Where feasible, documents may be anonymized or de‑identified before being used for training purposes.

5. Data Sharing and Disclosure

Sinhala OCR does not sell, rent, trade, or otherwise disclose uploaded documents or derived data to third parties.

We may use third‑party infrastructure or service providers (such as cloud hosting or security services) solely to support platform operations. Such providers are contractually bound by confidentiality and security obligations and are not permitted to access or use uploaded data for their own purposes.

6. Data Security

Sinhala OCR implements reasonable and appropriate technical and organizational measures to protect uploaded data, including:

  • Encryption of data at rest and in transit
  • Secure access controls and authentication mechanisms
  • Restricted internal access on a need‑to‑know basis
  • Ongoing monitoring and security reviews

While no method of transmission or storage is completely secure, we continuously work to safeguard data against unauthorized access, alteration, disclosure, or destruction.

7. User Responsibilities

Users are responsible for:

  • Ensuring they have the legal right to upload and process the documents submitted to the platform
  • Ensuring uploaded content complies with applicable laws and does not infringe third‑party rights

Users are advised to avoid uploading highly sensitive or confidential documents unless necessary.

8. Legal and Regulatory Compliance

Sinhala OCR aligns its data handling practices with applicable data protection and privacy principles, including those set out in the Sri Lanka Personal Data Protection Act (PDPA) and internationally recognized privacy standards.

The service is designed strictly for document text extraction and not as a personal data management or profiling system.

9. Children’s Privacy

Sinhala OCR is not intended for use by individuals under the age of 18. We do not knowingly collect or process data belonging to children.

10. Changes to This Privacy Policy

We may update this Privacy Policy from time to time to reflect changes in legal requirements, technology, or service functionality. Any updates will be published on this page with a revised “Last Updated” date.

11. Contact Information

For questions, concerns, or requests related to this Privacy Policy or data handling practices, please contact:

Sinhala OCR
Email: [support@sinhalaocr.com]
Website: https://sinhalaocr.com