If so you can download any of the below versions for testing. The product will function as normal except for an evaluation limitation. At the time of purchase we provide a license file via email that will allow the product to work in its full capacity. If you would also like an evaluation license to test without any restrictions for 30 days, please follow the directions provided here.
If you experience errors, when you try to download a file, make sure your network policies (enforced by your company or ISP) allow downloading ZIP and/or MSI files.
Aspose.OCR for Python via C++
Product Page | Docs | Demos | API Reference | Examples | Blog | Search | Free Support | Temporary License | EULA
Extract text from images on any platform with our powerful and developer-friendly API for optical character recognition. You only need a few lines of Python code to add OCR capabilities into your Linux, MacOS, and Windows solutions. Analyze the data, create cloud services and serverless applications focusing on business task rather than complex maths, neural networks, and other technical intricacies.
Aspose.OCR technology
Optical character recognition becomes a trivial and straightforward task with Aspose.OCR, even for developers new to the technology. It can convert virtually any file you can get from a scanner, camera, or download from web: scanned books, contracts, invoices, receipts, street photos, or screenshots. The accuracy and reliability of text recognition is guaranteed by an extensive range of both fully automated and manual image processing filters that enhance an image before it is sent to the OCR engine.
Powerful image processing and customizable content structure detection algorithms enable text extraction from virtually any image, ranging from high-quality scans to street photos. Multiple processing filters can be applied to the same image to get the best recognition quality.
Key features
- Optical character recognition engine with superior recognition speed and accuracy.
- No pre-training or adaptation is necessary - the reliable results are guaranteed by Aspose engineering team.
- Supports 28 languages based on Latin, Cyrillic and Asian scrips.
- Detects and recognizes text in all popular typefaces and font styles.
- Accurately reads rotated, noisy and distorted images with the help of automatic processing filters.
- Supports a large number of image formats as well as bulk recognition of multiple images from an archive or folder.
- Recognizes the whole image or selected areas only.
- Recognition results are returned in the most popular data exchange formats.
- Full compatibility with other Aspose products - build solutions of any complexity using familiar concepts with minimal code.
- JPEG (.JPG or .JPEG)
- PNG (.PNG)
- PDF document (.PDF)
- TIFF (.TIF or .TIFF)
- Bitmap (.BMP)
- Archive (.ZIP)
- Public URL to JPEG, PNG, TIFF and BMP image.
Note: The URL must point directly to the image. The library cannot extract images from HTML pages and does not support authentication.
Supported languages
Aspose.OCR for Python via C++ can recognize a large number of languages and all popular writing scripts, including texts with mixed languages.
Extended Latin alphabets
- Croatian
- Czech
- Danish
- Dutch
- English
- Estonian
- Finnish
- French
- German
- Italian
- Latvian
- Lithuanian
- Norwegian
- Polish
- Portuguese
- Romanian
- Slovak
- Slovenian
- Spanish
- Swedish
Cyrillic alphabets
- Belorussian
- Bulgarian
- Kazakh
- Russian
- Serbian
- Ukrainian
Asian languages
- Chinese (more than 6,000 characters)
- Hindi
System requirements
- Python 3.11 or later
- Microsoft Windows 7 or later, 64-bit
- Microsoft Windows Server 2008 R2 SP1 or later
- macOS Mojave version 10.14 or later. MacOS ARM (Apple Silicon) platform is fully supported.
- Any Linux x64, including Ubuntu, OpenSUSE and CentOS.
Evaluation version limitation
Aspose.OCR for Python via C++ is a commercially licensed product that can be used in trial (evaluation) mode. If the license is not provided, the library extracts the first 300 characters from an image; other text is not processed.
Get started
You only need a few minutes and a basic knowledge of Python to create a basic OCR application:
import sys
sys.path.append('./path/to/lib/asposeocr')
import asposeocr
settings = asposeocr.RecognitionSettings()
recognition_batch = [asposeocr.AsposeOCRInput()]
recognition_batch[0].url = 'scan.png'
recognition_result = AsposeOCRRecognize(recognition_batch, settings)
The functionality has been updated to Aspose.OCR for C++ 24.3.0
Added: 
Downloads:
First release of Aspose.OCR for Python
Added:
Downloads: