OCR (Optical Character Recognition)
Extract Dhivehi text from images and PDFs with AI-powered OCR. Supports both handwritten and printed Thaana script.
Overview
The OCR feature allows you to extract Dhivehi text from images and PDF documents. It's organized into three main tabs:
Scan Tab
Upload images or PDFs, select OCR mode, and process files to extract text.
Results Tab
View, edit, and export extracted text with highlighting and PDF viewer.
History Tab
Access and manage all your previous OCR operations.
OCR Modes
Handwritten Mode
Optimized for hand-written Dhivehi text with various handwriting styles.
Accurate/Standard Mode
1 CreditGeneral-purpose text recognition for printed Dhivehi text.
Quick Mode
1 CreditFast processing option for quick text extraction from clear images.
How to Use OCR
Upload Your File
Go to the OCR page and the Scan tab. Choose your upload method:
- Drag & Drop: Drop image or PDF files into the upload area
- File Browser: Click to browse and select files
- Camera: Use camera button for direct handwritten text capture
Supported formats: JPG, PNG, GIF, WebP, PDF (up to 50MB)
Select OCR Mode
Choose the appropriate mode based on your content:
- Handwritten Mode for handwritten text (3-4 credits)
- Accurate/Standard Mode for printed text (1 credit)
- Quick Mode for fast processing of clear images (1 credit)
Process the File
Click "Process" to start OCR. You'll see:
- Real-time processing progress with percentage
- Estimated time remaining
- Job status tracking
Note: Multi-page PDFs charge only for the first page in handwritten mode.
View Results
Switch to the Results tab to see extracted text:
- Beautiful PDF viewer for processed documents
- Text display with formatting options
- Highlighting toggle to show OCR regions
- Fullscreen mode for detailed work
Edit and Export
Refine and export your extracted text:
- Edit: Modify text in rich text editor
- Magic Edit: AI enhancement of extracted text (magic wand icon)
- Copy: Copy text to clipboard
- Download: Save as file
- History: Automatically saved for future access
Advanced Features
Multi-page PDF Support
Process entire PDF documents with multiple pages. Smart credit management charges only the first page for multi-page PDFs in handwritten mode.
• Cost-effective for long documents
• Page-by-page progress tracking
Camera Integration
Direct camera capture for handwritten text scanning. Perfect for quick scans of physical documents.
• Optimized for handwritten content
• Instant processing after capture
Magic Edit
AI-powered enhancement of extracted text. Automatically corrects OCR errors and improves readability.
• Format standardization
• Context-aware improvements
History Management
All OCR operations are saved to your history for easy access and reference.
• Delete unnecessary records
• Re-access processed documents
Common Use Cases
Digitizing Handwritten Documents
Convert handwritten letters, notes, manuscripts, and historical documents to editable digital text.
Extracting Text from Books
Extract Dhivehi text from printed books, magazines, and newspapers for digital archiving or translation.
Student Work Processing
Teachers can digitize handwritten student assignments for easier grading and record-keeping.
Government Document Processing
Convert scanned official documents and forms to searchable, editable digital text.
Tips for Best Results
Use High-Quality Images
Clear, well-lit images with high resolution produce the best OCR results. Avoid blurry or low-quality scans.
Choose the Right Mode
Use Handwritten Mode for handwritten text and Standard Mode for printed text for optimal accuracy.
Review Extracted Text
Always review OCR output for accuracy, especially with handwritten content or poor-quality source material.
Use Magic Edit for Corrections
The Magic Edit feature can automatically correct common OCR errors and improve text quality.
Pricing
For printed text and fast processing
For single-page handwritten content
For multi-page handwritten PDFs
Ready to Extract Dhivehi Text?
Access the OCR feature in your Dhavana dashboard