Package com.itextpdf.pdfocr.onnxtr.recognition

Class CrnnPostProcessor

java.lang.Object

com.itextpdf.pdfocr.onnxtr.recognition.CrnnPostProcessor

All Implemented Interfaces:

IRecognitionPostProcessor

       public class CrnnPostProcessor extends Object implements IRecognitionPostProcessor
      

Implementation of a text recognition predictor post-processor, used for OnnxTR CRNN model outputs.

Notably it does not have end-of-string tokens. Only token, besides the vocabulary one, is blank, which is just skipped or used as a char separator. Multiple of the same label in a row is aggregated into one.

Constructor Summary

Constructors

Constructor	Description
CrnnPostProcessor()	Creates a new post-processor with the default vocabulary.
CrnnPostProcessor(Vocabulary vocabulary)	Creates a new post-processor.

Method Summary

Modifier and Type	Method	Description
int	labelDimension()	Returns the size of the output character label vector.
String	process(FloatBufferMdArray output)	Process ML model output and return recognized characters as string.

Methods inherited from class java.lang.Object

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

Constructor Details

CrnnPostProcessor

             public CrnnPostProcessor
             (Vocabulary vocabulary)
            

Creates a new post-processor.

Parameters:

vocabulary - vocabulary used for the model output (without special tokens)

CrnnPostProcessor

             public CrnnPostProcessor()
            

Creates a new post-processor with the default vocabulary.

Method Details

process

             public String process
             (FloatBufferMdArray output)
            

Process ML model output and return recognized characters as string.

Specified by:

process in interface IRecognitionPostProcessor

Parameters:

output - raw output of the ML model

Returns:

recognized characters as string

labelDimension

             public int labelDimension()
            

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

Specified by:

labelDimension in interface IRecognitionPostProcessor

Returns:

the size of the output character label vector