OCR Usage Basics Leave feedback
GroupDocs.Parser doesn’t contain OCR functionality as a part of its distributable. Instead of it API for integrating any paid or free OCR solution is provided. See this article for details how to integrate OCR soluton to GroupDocs.Parser.
To use OCR functionality, Parser object must be properly initialized:
- Instantiate ParserSettings object with the instance of class that implements OCR functionality;
- Instantiate Parser object with ParserSettings object.
The following example shows how to create an instance of Parser class with Aspose.OCR on-premise API connector:
// Create an instance of ParserSettings class with OCR Connector
ParserSettings settings = new ParserSettings(new AsposeOcrOnPremise());
// Create an instance of Parser class with settings
Parser parser = new Parser(Constants.SampleScan, settings);
getText and getTextAreas methods from Parser class are used to recognize a text from images.
To extract a text from image files or non-text PDF documents GetText method is used:
- Instantiate ParserSettings object with the instance of class that implements OCR functionality;
- Instantiate Parser object with ParserSettings object;
- Instantiate TextOptions object with useOcr = true;
- Call getText(TextOptions) method with TextOptions parameter and obtain TextReader object;
- Check if the reader isn’t null (text extraction is supported for the document);
- Read a text from the reader.
The following example shows how to extract a text from the image file:
// Create an instance of ParserSettings class with OCR Connector
ParserSettings settings = new ParserSettings(new AsposeOcrOnPremise());
// Create an instance of Parser class with settings
try (Parser parser = new Parser(Constants.SampleScan, settings)) {
// Create an instance of TextOptions to use OCR
TextOptions options = new TextOptions(false, true);
// Extract a text using OCR
try (TextReader reader = parser.getText(options)) {
// Print a text or 'not supported' message
System.out.println(reader == null ? "Text extraction isn't supported" : reader.readToEnd());
}
}
To extract text areas from image files or non-text PDF documents GetTextAreas method is used:
- Instantiate ParserSettings object with the instance of class that implements OCR functionality;
- Instantiate Parser object with ParserSettings object;
- Instantiate PageTextAreaOptions object with useOcr = true;
- Call getTextAreas(PageTextAreaOptions) method and obtain the collection of PageTextArea objects;
- Check if the collection isn’t null (text areas extraction is supported for the document);
- Iterate through the collection and get rectangles and texts.
The following example shows how to extract text areas from the image file:
// Create an instance of ParserSettings class with OCR Connector
ParserSettings settings = new ParserSettings(new AsposeOcrOnPremise());
// Create an instance of Parser class with settings
try (Parser parser = new Parser(Constants.SampleScan, settings)) {
// Create an instance of PageTextAreaOptions to use OCR
PageTextAreaOptions options = new PageTextAreaOptions(true);
// Extract text areas
java.lang.Iterable<PageTextArea> areas = parser.getTextAreas(options);
// Check if text areas extraction is supported
if (areas == null) {
System.out.println("Text areas extraction isn't supported");
return;
}
// Iterate over text areas
for (PageTextArea a : areas) {
// Print a text, position and size for an each text area
System.out.println(a.getText());
System.out.println(String.format("\tPosition: (%d; %d)",
a.getRectangle().getLeft(),
a.getRectangle().getTop()));
System.out.println(String.format("\tSize: (%d; %d)",
a.getRectangle().getSize().getWidth(),
a.getRectangle().getSize().getHeight()));
}
}
TextOptions and PageTextAreaOptions classes accept an OcrOptions object in the constructor (new TextOptions(false, true, ocrOptions), new PageTextAreaOptions(true, ocrOptions)) and return it by the getOcrOptions method. OcrOptions class has the following members:
| Member | Description |
|---|---|
| getRectangle / setRectangle | Is used to pass a rectangular area to restrict the area of the text recognition. |
| getHandler / setHandler | An instance of OcrEventHandler class to handle any warnings which occur while the text recognition. |
| getUseSpellChecker / setUseSpellChecker | A flag that asks the connector to use spell checking (if the OCR engine supports it). |
| getLanguage / setLanguage | The recognition language - a value of the Language enum. Language.Eng by default; passing null resets it to Language.Eng. |
| getPagePreviewOptions / setPagePreviewOptions | PagePreviewOptions object with the resolution (DPI) the connector may use for the page image. |
OcrOptions object is passed to the OCR connector, and the connector is responsible for applying these values: GroupDocs.Parser itself only uses the rectangle (to scale it to the page image) and the handler (to collect warnings).
WarningIn GroupDocs.Parser for Java 26.10 the connector receives your OcrOptions object as is only when the source document is an image file. For PDF and other documents that are rendered to images before the recognition, the connector receives a copy that contains only the rectangle (scaled to the rendered page image) and the handler; language, spell checker flag and page preview options are not passed. The page images are rendered by the parser itself (images are passed in their original size; document pages are rendered at 144 DPI), soPagePreviewOptionsdoesn’t change the image that the connector receives.
The following sections describe how to use these members.
To restrict an area of the image for the text recognition OcrOptions class is used. Set Rectangle property to restrict the rectangular area for the text recognition.
The following example shows how to restrict the text recognition by the rectangular area:
// Create an instance of ParserSettings class with OCR Connector
ParserSettings settings = new ParserSettings(new AsposeOcrOnPremise());
// Create an instance of Parser class with settings
try (Parser parser = new Parser(Constants.SampleScan, settings)) {
// Create an instance of OcrOptions to set a rectangle
OcrOptions ocrOptions = new OcrOptions(new Rectangle(0, 0, 400, 200));
// Create an instance of TextOptions to use OCR
TextOptions options = new TextOptions(false, true, ocrOptions);
// Extract a text using OCR
try (TextReader reader = parser.getText(options)) {
// Print a text or 'not supported' message
System.out.println(reader == null ? "Text extraction isn't supported" : reader.readToEnd());
}
}
To handle warnings which occur while the text recognition OcrOptions class is used. Set Handler property to handle warning messages. hasWarnings property of OcrEventHandler class is used to indicate if any warnings occur. Use Warnings to get all warnings or getWarnings method for warnings for the page. The empty list returns if no warning occurs during the text recognition.
The following example shows how to handle warning messages:
// Create an instance of ParserSettings class with OCR Connector
ParserSettings settings = new ParserSettings(new AsposeOcrOnPremise());
// Create an instance of Parser class with settings
try (Parser parser = new Parser(Constants.SampleScan, settings)) {
// Create an instance of OcrEventHandler to handle warnings
OcrEventHandler handler = new OcrEventHandler();
// Create an instance of OcrOptions to set a handler
OcrOptions ocrOptions = new OcrOptions(null, handler);
// Create an instance of TextOptions to use OCR
TextOptions options = new TextOptions(false, true, ocrOptions);
// Extract a text using OCR
try (TextReader reader = parser.getText(options)) {
// Print a text or 'not supported' message
System.out.println(reader == null ? "Text extraction isn't supported" : reader.readToEnd());
}
if (handler.hasWarnings()) {
System.out.println("The following warnings occur while text recognition:");
for (String w : handler.getWarnings()) {
System.out.println("\\t* " + w);
}
} else {
System.out.println("Text recognition was performed without any warning.");
}
}
To pass the recognition language to the connector, call setLanguage method of OcrOptions class with a Language value. PagePreviewOptions object with the required DPI can be passed to the OcrOptions constructor or set by setPagePreviewOptions method. Which languages are supported and how these values are applied depends on the OCR connector (see the note above).
The following example shows how to set the recognition language and the page preview resolution:
// Create an instance of ParserSettings class with OCR Connector
ParserSettings settings = new ParserSettings(new AsposeOcrOnPremise());
// Create an instance of Parser class with settings
try (Parser parser = new Parser(Constants.SampleScan, settings)) {
// Create an instance of OcrOptions with the page preview resolution
OcrOptions ocrOptions = new OcrOptions(new PagePreviewOptions(144));
// Set the recognition language
ocrOptions.setLanguage(Language.Jpn);
// Create an instance of TextOptions to use OCR
TextOptions options = new TextOptions(false, true, ocrOptions);
// Extract a text using OCR
try (TextReader reader = parser.getText(options)) {
// Print a text or 'not supported' message
System.out.println(reader == null ? "Text extraction isn't supported" : reader.readToEnd());
}
}
Inside the connector, read these values from the options parameter, for example options.getLanguage() and options.getPagePreviewOptions(), and map them to the settings of your OCR engine.
Was this page helpful?
Any additional feedback you'd like to share with us?
Please tell us how we can improve this page.
Thank you for your feedback!
We value your opinion. Your feedback will help us improve our documentation.
