Optical Character Recognition
Introducing OCR API!
Efficiently converting printed text from images into machine-readable text.
Key Features
Polygon Area Precision: Polygon detection in OCR offers precise localization of text and complex page layouts, allowing for accurate and structured extraction of information from documents, which enhances the overall quality and reliability of OCR results.
OCR Text Output: The API response includes the extracted OCR text alongside the polygon data. Receive accurate and editable text content from images, streamlining data entry and enhancing text-based analysis.
Use Cases
Document Digitization: Easily convert scanned documents into searchable and editable digital formats, saving time on manual transcription and data entry.
Text Search in Images: OCR is employed in image search engines and content management systems to enable users to search for text within images, such as in digital libraries and archives.
License Plate Recognition: Law enforcement agencies and parking management companies use OCR to automatically recognize license plates, aiding in security and parking enforcement.
Form Data
| Field | Data Type | Description |
|---|---|---|
| file | bytes | Image which is used for OCR |
| language | text | A language needed for recognition, with accepted values being: en for English, jp for Japanese, and vi for Vietnamese. |
Response
| Field | Data Type | Description |
|---|---|---|
| status_code | int | HTTP response code |
| result | object | Text Detection result |
| message_error | string | Message error (if exists) |