Please read these terms carefully before using Drishti OCR.
1. OCR Technology
Drishti uses Tesseract OCR (open-source) out of the box for optical character
recognition. The accuracy of text extraction depends on:
- Image quality and resolution
- Font clarity and size
- Document language and script
- Presence of noise or distortions
2. Data Collection and Usage
By using this service, you explicitly consent to the following:
- We collect and store the raw text extracted from your uploaded documents
- We may process, analyze, and use this data for service improvement, research,
and development purposes
- Uploaded documents and extracted text may be stored indefinitely
- We reserve the right to use the collected data as we deem necessary, including
but not limited to:
- Training and improving OCR models
- Analytics and research
- Quality assurance and testing
3. User Responsibilities
You agree that:
- You will not upload sensitive, confidential, or personal information that you
do not wish to be stored and processed
- You have the legal right to upload and process the documents you submit
- You understand that this is a research/development tool and not intended for
production use with sensitive data
4. No Warranty
This service is provided "as is" without any warranties. We do not guarantee:
- Accuracy of OCR results
- Availability or uptime of the service
- Data security or privacy beyond AWS standard protections