Package com.itextpdf.pdfocr.onnx.recognition

Class CtcLabelPostProcessor

java.lang.Object

com.itextpdf.pdfocr.onnx.recognition.BasicLabelPostProcessor

com.itextpdf.pdfocr.onnx.recognition.CtcLabelPostProcessor

All Implemented Interfaces:

IRecognitionPostProcessor

       public class CtcLabelPostProcessor extends BasicLabelPostProcessor
      

Implementation of a text recognition predictor post-processor, used for EasyOCR and PaddleOCR model outputs.

It has a single blank token, which is the first one just before the vocabulary. Multiple of the same label in a row is aggregated into one.

Constructor Summary

Constructors

Constructor	Description
CtcLabelPostProcessor(IOutputLabelMapper<String> labelMapper)	Creates a new post-processor.

Method Summary

Modifier and Type	Method	Description
protected void	appendLabel(StringBuilder output, int labelIndex)	Adds label to the string output, based on the label's index.
int	labelDimension()	Returns the size of the output character label vector.

Methods inherited from class com.itextpdf.pdfocr.onnx.recognition.BasicLabelPostProcessor

process

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

CtcLabelPostProcessor

             public CtcLabelPostProcessor
             (IOutputLabelMapper<String> labelMapper)
            

Creates a new post-processor.

Parameters:

labelMapper - label mapper used for the model output (without special tokens)

Method Details

appendLabel

             protected void appendLabel
             (StringBuilder output, int labelIndex)
            

Adds label to the string output, based on the label's index. Can be a noop, if label index should be ignored.

Specified by:

appendLabel in class BasicLabelPostProcessor

Parameters:

output - string builder to append the label to

labelIndex - index of the label to append, guaranteed to be in the [0; labelDimension()) range.

labelDimension

             public int labelDimension()
            

Returns the size of the output character label vector. I.e. how many distinct tokens/characters the model recognizes.

Returns:

the size of the output character label vector