使用 GroupDocs for Java 和 Aspose 的文档管理 OCR

<repositories>
    <repository>
        <id>repository.groupdocs.com</id>
        <name>GroupDocs Repository</name>
        <url>https://releases.groupdocs.com/search/java/</url>
    </repository>
</repositories>
<dependencies>
    <dependency>
        <groupId>com.groupdocs</groupId>
        <artifactId>groupdocs-search</artifactId>
        <version>25.4</version>
    </dependency>
</dependencies>

import com.groupdocs.search.Index;
// Specify the directory where the index will be stored.
String indexFolder = "YOUR_OUTPUT_DIRECTORY/OcrSupport";
// Create an instance of Index class at the specified location.
Index index = new Index(indexFolder);

String indexFolder = "YOUR_OUTPUT_DIRECTORY/OcrSupport";
Index index = new Index(indexFolder);

import com.groupdocs.search.options.IndexingOptions;
IndexingOptions options = new IndexingOptions();
options.getOcrIndexingOptions().setEnabledForSeparateImages(true);
options.getOcrIndexingOptions().setEnabledForEmbeddedImages(true);
// Set a custom OCR connector.
options.getOcrIndexingOptions().setOcrConnector(new OcrConnector());

String documentsFolder = "YOUR_DOCUMENT_DIRECTORY";
index.add(documentsFolder, options);

import com.groupdocs.search.results.SearchResult;
String query = "water";
SearchResult result = index.search(query);

import com.groupdocs.search.options.IOcrConnector;
import com.groupdocs.search.options.OcrContext;
import java.awt.image.BufferedImage;
import javax.imageio.ImageIO;
import com.aspose.ocr.AsposeOCR;

public class OcrConnector implements IOcrConnector {
    @Override
    public final String recognize(OcrContext context) {
        if (null == context.getImageLocation()) {
            throw new RuntimeException("The image type is not supported: " + context.getImageLocation());
        }
        
        BufferedImage image = ImageIO.read(context.getImageLocation().toFile());
        AsposeOCR api = new AsposeOCR();
        String text = api.RecognizePage(image);
        return text;
    }
}