Retain authentic PDF formatting to view translated paperwork with Amazon Textract, Amazon Translate, and PDFBox

Many companies have numerous international customers and have to translate textual content to allow cross-lingual communication between them. It is a guide, gradual, and costly human effort. There’s a have to discover a scalable, dependable, and cost-effective answer to translate paperwork whereas retaining the unique doc formatting.

For verticals comparable to healthcare, as a consequence of regulatory necessities, the translated paperwork require an extra human within the loop to confirm the validity of the machine-translated doc.

If the translated doc doesn’t retain the unique formatting and construction, it loses its context. This could make it tough for a human reviewer to validate and make corrections.

On this publish, we reveal find out how to create a brand new translated PDF from a scanned PDF whereas retaining the unique doc construction and formatting utilizing a geometry-based strategy with Amazon Textract, Amazon Translate, and Apache PDFBox.

Answer overview

The answer offered on this publish makes use of the next parts:

• Amazon Textract – A totally managed machine studying (ML) service that mechanically extracts printed textual content, handwriting, and different information from scanned paperwork that goes past easy optical character recognition (OCR) to establish, perceive, and extract information from kinds and tables. Amazon Textract can detect textual content in a wide range of paperwork, together with monetary stories, medical information, and tax kinds.
• Amazon Translate – A neural machine translation service that delivers quick, high-quality, and reasonably priced language translation. Amazon Translate supplies high-quality on-demand and batch translation capabilities throughout greater than 2,970 language pairs, whereas reducing your translation prices.
• PDF Translate – An open-source library written in Java and printed on AWS Samples in GitHub. This library incorporates logic to generate translated PDF paperwork in your required language with Amazon Textract and Amazon Translate. It additionally makes use of the open-source Java library Apache PDFBox to create PDF paperwork. There are related PDF processing libraries accessible in different programming languages, for instance Node PDFBox.

Whereas performing machine translations, you could have conditions the place you want to protect particular sections of textual content from being translated, comparable to names or distinctive identifiers. Amazon Translate permits tag modifications, which lets you specify what textual content shouldn’t be translated. Amazon Translate additionally helps formality customization, which lets you customise the extent of ritual in your translation output.

For particulars on Amazon Textract limits, consult with Quotas in Amazon Textract.

The answer is restricted to the languages that may be extracted by Amazon Textract, which at present helps English, Spanish, Italian, Portuguese, French, and German. These languages are additionally supported by Amazon Translate. For the total record of languages supported by Amazon Translate, consult with Supported languages and language codes.

We use the next PDF to reveal translating the textual content from English to Spanish. The answer additionally helps producing the translated doc with none formatting. The place of the translated textual content is maintained. The supply and translated PDF paperwork can be discovered within the AWS Samples GitHub repo.

Within the following sections, we reveal find out how to run the interpretation code on a neighborhood machine and take a look at the interpretation code in additional element.

Stipulations

Earlier than you get began, arrange your AWS account and the AWS Command Line Interface (AWS CLI). For entry to any AWS Companies comparable to Textract and Translate, applicable IAM permissions are wanted. We suggest using least privilege permissions. To be taught extra about IAM permissions see Insurance policies and permissions in IAM in addition to How Amazon Textract works with IAM and How Amazon Translate works with IAM.

Run the interpretation code on a neighborhood machine

This answer focuses on the standalone Java code to extract and translate a PDF doc. That is for simpler testing and customizations to get the best-rendered translated PDF doc. The code can then be built-in into an automatic answer to deploy and run in AWS. See Translating PDF paperwork utilizing Amazon Translate and Amazon Textract for a pattern structure that makes use of Amazon Easy Storage Service (Amazon S3) to retailer the paperwork and AWS Lambda to run the code.

To run the code on a neighborhood machine, full the next steps. The code examples can be found on the GitHub repo.

1. Clone the GitHub repo:

   git clone https://github.com/aws-samples/amazon-translate-pdf

2. Run the next command:
3. Run the next command to translate from English to Spanish:

   java -jar goal/translate-pdf-1.0.jar --source en --translated es

Two translated PDF paperwork are created within the paperwork folder, with and with out the unique formatting (SampleOutput-es.pdf and SampleOutput-min-es.pdf).

Code to generate the translated PDF

The next code snippets present find out how to take a PDF doc and generate a corresponding translated PDF doc. It extracts the textual content utilizing Amazon Textract and creates the translated PDF by including the translated textual content as a layer to the picture. It builds on the answer proven within the publish Producing searchable PDFs from scanned paperwork mechanically with Amazon Textract.

The code first will get every line of textual content with Amazon Textract. Amazon Translate is used to get translated textual content and save the geometry of the translated textual content.

Area area = Area.US_EAST_1;
TextractClient textractClient = TextractClient.builder()
        .area(area)
        .construct();

// Get the enter Doc object as bytes
Doc pdfDoc = Doc.builder()
        .bytes(SdkBytes.fromByteBuffer(imageBytes))
        .construct();

TranslateClient translateClient = TranslateClient.builder()
        .area(area)
        .construct();

DetectDocumentTextRequest detectDocumentTextRequest = DetectDocumentTextRequest.builder()
        .doc(pdfDoc)
        .construct();

// Invoke the Detect operation
DetectDocumentTextResponse textResponse = textractClient.detectDocumentText(detectDocumentTextRequest);

Checklist<Block> blocks = textResponse.blocks();
Checklist<TextLine> traces = new ArrayList<>();
BoundingBox boundingBox;

for (Block block : blocks) {
    if ((block.blockType()).equals(BlockType.LINE)) {
        String supply = block.textual content();

        TranslateTextRequest requestTranslate = TranslateTextRequest.builder()
                .sourceLanguageCode(sourceLanguage)
                .targetLanguageCode(destinationLanguage)
                .textual content(supply)
                .construct();

        TranslateTextResponse resultTranslate = translateClient.translateText(requestTranslate);

        boundingBox = block.geometry().boundingBox();
        traces.add(new TextLine(boundingBox.left(),
                boundingBox.prime(),
                boundingBox.width(),
                boundingBox.peak(),
                resultTranslate.translatedText(),
                supply));
    }
}
return traces;

The font dimension is calculated as follows and might simply be configured:

int fontSize = 20;
float textWidth = font.getStringWidth(textual content) / 1000 * fontSize;
float textHeight = font.getFontDescriptor().getFontBoundingBox().getHeight() / 1000 * fontSize;
 
if (textWidth > bbWidth) {
    whereas (textWidth > bbWidth) {
        fontSize -= 1;
        textWidth = font.getStringWidth(textual content) / 1000 * fontSize;
        textHeight = font.getFontDescriptor().getFontBoundingBox().getHeight() / 1000 * fontSize;
     }
} else if (textWidth < bbWidth) {
     whereas (textWidth < bbWidth) {
         fontSize += 1;
         textWidth = font.getStringWidth(textual content) / 1000 * fontSize;
         textHeight = font.getFontDescriptor().getFontBoundingBox().getHeight() / 1000 * fontSize;
      }
}

The translated PDF is created from the saved geometry and translated textual content. Modifications to the colour of the translated textual content can simply be configured.

float width = picture.getWidth();
float peak = picture.getHeight();
 
PDRectangle field = new PDRectangle(width, peak);
PDPage web page = new PDPage(field);
web page.setMediaBox(field);
this.doc.addPage(web page); //org.apache.pdfbox.pdmodel.PDDocument
 
PDImageXObject pdImage;
 
if(imageType == ImageType.JPEG){
    pdImage = JPEGFactory.createFromImage(this.doc, picture);
} else {
    pdImage = LosslessFactory.createFromImage(this.doc, picture);
}
 
PDPageContentStream contentStream = new PDPageContentStream(doc, web page, PDPageContentStream.AppendMode.OVERWRITE, false);
 
contentStream.drawImage(pdImage, 0, 0);
contentStream.setRenderingMode(RenderingMode.FILL);
 
for (TextLine cline : traces){
    String clinetext = cline.textual content;
    String clinetextOriginal = cline.originalText;
                       
    FontInfo fontInfo = calculateFontSize(clinetextOriginal, (float) cline.width * width, (float) cline.peak * peak, font);
    //config to incorporate authentic doc construction - overlay with authentic
    contentStream.setNonStrokingColor(Shade.WHITE);
    contentStream.addRect((float) cline.left * width, (float) (peak - peak * cline.prime - fontInfo.textHeight), (float) cline.width * width, (float) cline.peak * peak);
    contentStream.fill();
 
    fontInfo = calculateFontSize(clinetext, (float) cline.width * width, (float) cline.peak * peak, font);
    //config to incorporate authentic doc construction - overlay with translated
    contentStream.setNonStrokingColor(Shade.WHITE);
    contentStream.addRect((float) cline.left * width, (float) (peak - peak * cline.prime - fontInfo.textHeight), (float) cline.width * width, (float) cline.peak * peak);
    contentStream.fill();
    //change the output textual content colour right here
    fontInfo = calculateFontSize(clinetext.size() <= clinetextOriginal.size() ? clinetextOriginal : clinetext, (float) cline.width * width, (float) cline.peak * peak, font);
    contentStream.setNonStrokingColor(Shade.BLACK);
    contentStream.beginText();
    contentStream.setFont(font, fontInfo.fontSize);
    contentStream.newLineAtOffset((float) cline.left * width, (float) (peak - peak * cline.prime - fontInfo.textHeight));
    contentStream.showText(clinetext);
    contentStream.endText();
}
contentStream.shut()

The next picture exhibits the doc translated into Spanish with the unique formatting (SampleOutput-es.pdf).

The next picture exhibits the translated PDF in Spanish with none formatting (SampleOutput-min-es.pdf).

Processing time

The employment software pdf took about 10 seconds to extract, course of and render the translated pdf. The processing time for textual content heavy doc such because the Declaration of Independence PDF took lower than a minute.

Value

With Amazon Textract, you pay as you go primarily based on the variety of pages and pictures processed. With Amazon Translate, you pay as you go primarily based on the variety of textual content characters which might be processed. Discuss with Amazon Textract pricing and Amazon Translate pricing for precise prices.

Conclusion

This publish confirmed find out how to use Amazon Textract and Amazon Translate to generate translated PDF paperwork whereas retaining the unique doc construction. You possibly can optionally postprocess Amazon Textract outcomes to enhance the standard of the interpretation, for instance extracted phrases might be handed via ML-based spellchecks comparable to SymSpell for information validation, or clustering algorithms can be utilized to protect studying order. You too can use Amazon Augmented AI (Amazon A2I) to construct human evaluate workflows the place you should use your individual personal workforce to evaluate the unique and translated PDF paperwork to supply extra accuracy and context. See Designing human evaluate workflows with Amazon Translate and Amazon Augmented AI and Constructing a multi-lingual doc translation workflow with domain-specific and language-specific customization to get began.

Concerning the Authors

Anubha Singhal is a Senior Cloud Architect at Amazon Net Companies within the AWS Skilled Companies group.

Sean Lawrence was previously a Entrance Finish Engineer at AWS. He specialised in entrance finish improvement within the AWS Skilled Companies group and the Amazon Privateness group.