Convert images and PDFs to text in Java

Recognizes formatted text in scanned images and PDFs

Supports all file formats you can get form a scanner or camera

Reads Latin and Cyrillic scripts

Recognizes more than 6,000 Chinese characters

Detects and recognizes all popular typefaces

Carefully preserves font styles and formatting

Processes the whole image or selected areas only

Supports rotated, skewed and noisy images

Batch recognition of all images in a folder or archive

Recognizes images provided as web links

Finds and automatically corrects misspelled words

100% compatibility with other Aspose products

Easy to Install

You can use Aspose.OCR for Java directly from a Maven based project by following simple installation instructions.

Request a temporary license to start building a fully functional OCR application without any limits and restrictions.

Easy to Use

Image recognition requires a couple of lines of code. Literally. It's really that simple - try yourself:

// Create instance of OCR API
AsposeOCR api = new AsposeOCR();
try {
    // Recognize image
    String result = api.RecognizePage("<file name>");
    // Display the recognition result
    System.out.println(result);
} catch (IOException e) {
    // Error handling
    e.printStackTrace();
}

26 Recognition Languages

OCR API supports a large number of languages and all popular writing scripts, including texts with mixed languages. The built-in spell checker automatically replaces misspelled words and saves you the trouble of manually correcting recognition results.

• Extended Latin alphabet: Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Italian, Latvian, Lithuanian, Norwegian, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, Swedish.
• Cyrillic alphabet: Belorussian, Bulgarian, Kazakh, Russian, Serbian, Ukrainian.
• Chinese: more than 6,000 characters.

You can specify the language to increase the recognition performance and reliability or let the API to detect languages automatically.

Preserve Formatting

The OCR API reads all popular typefaces such as Arial, Times New Roman, Courier New, Tahoma, Calibri and more in regular, bold and italic styles and carefully preserves formatting in OCR results. You can also split recognition results into lines and detect text areas in a page.

Recognize Photos

Scanner not always available on end user workstations, which may become a showstopper for OCR applications. Our OCR API provides a number of pre-processing filters that can handle distorted, rotated, skewed, and noisy images. In combination with support for all image formats, it allows for reliable recognition of even smartphone photos. Most of the pre-processing and image correction is done automatically, but you can always intervene in difficult cases.

// Create instance of OCR API
AsposeOCR api = new AsposeOCR();

// Define pre-processing filters
PreprocessingFilter filters = new PreprocessingFilter();
filters.add(PreprocessingFilter.ToGrayscale());
filters.add(PreprocessingFilter.Rotate(-90));

// Pre-process image before recognition
BufferedImage imageRes = api.PreprocessImage(imagePath, filters);

// Recognize image
RecognitionResult result = api.RecognizePage(imageRes, set);

Performance Optimization

Optical character recognition requires a lot of processing resources, which may become a problem for web services and entry-level devices. The API offers very flexible ways to balance recognition speed, resource requirements, and accuracy:

• Choose between thorough recognition and fast recognition.
• Specify the number of threads allocated for recognition, or allow the library to automatically scale to the number of CPU cores.
• Free up the CPU by offloading the calculations to the GPU.

// Create instance of OCR API
AsposeOCR api = new AsposeOCR();

// Recognize image in the fastest mode
String result = api.RecognizePageFast("sample.jpg");

Batch Processing

The OCR API frees you from having to recognize each image one at a time by offering various batch processing methods that allow you to recognize multiple images in a single call:

• Recognition of multi-page PDF and TIFF files.
• Recognition of all files in an archive.
• Recognition of all files in a folder.