Supported File Types
Rekognita supports a wide range of document formats. Each format is processed by the appropriate parser to ensure maximum accuracy.
Documents
| Format | Extensions | Notes |
|---|---|---|
.pdf | Digital and scanned (OCR). Support for protected PDFs | |
| Microsoft Word | .docx, .doc | Full support for tables, images, and styles |
| Microsoft Excel | .xlsx, .xls | Table conversion preserving structure |
| Microsoft PowerPoint | .pptx, .ppt | Text and image extraction from slides |
| OpenDocument | .odt, .ods | LibreOffice / OpenOffice documents |
| Rich Text | .rtf | Basic formatting support |
| Plain Text | .txt | UTF-8, various encodings |
Images
| Format | Extensions | Max Size |
|---|---|---|
| JPEG | .jpg, .jpeg | 50 MB |
| PNG | .png | 50 MB |
| TIFF | .tiff, .tif | 100 MB (multi-page) |
| WebP | .webp | 50 MB |
| BMP | .bmp | 50 MB |
| HEIC | .heic | 50 MB |
Supported OCR Languages
Rekognita supports OCR for 25+ languages, including:
- Latin: English, Deutsch, Français, Español, Italiano, Português, Nederlands, Polski
- Cyrillic: Ukrainian, Russian, Belarusian, Bulgarian, Serbian
- CJK: 中文 (Chinese), 日本語 (Japanese), 한국어 (Korean)
- Arabic: العربية (Arabic), فارسی (Persian)
- Other: हिन्दी (Hindi), ภาษาไทย (Thai), Tiếng Việt (Vietnamese)
Recommendations
- For scanned documents, a resolution of ≥ 300 DPI is recommended
- PDFs with embedded text are processed faster than scans
- For Excel/PowerPoint, we recommend converting to PDF before uploading for the best results