public static class Ocr.PropertyBuilder extends Properties
defaults
Constructor and Description |
---|
PropertyBuilder() |
Modifier and Type | Method and Description |
---|---|
Ocr.PropertyBuilder |
saveIntermediateImagesToDir(File dir)
Save intermediate images generated for debug purpose - don't specify or empty string to skip saving
|
Ocr.PropertyBuilder |
setCustomImagePreProcessing(String cmds)
set the image pre-processing type to Ocr.ImagePreProcessingType.CUSTOM and the corresponding custom commands.
|
Ocr.PropertyBuilder |
setDictCustomDictFile(File customDictFile)
Path to your custom dictionary (words are separated using line breaks).
|
Ocr.PropertyBuilder |
setDictCustomTemplatesFile(File customTemplatesFile)
Path to your custom templates (templates are separated using line breaks).
|
Ocr.PropertyBuilder |
setDictImportance(int importance)
Percentage measuring the importance of the dictionary (0: not at all; 100: extremely important; default: 10)
|
Ocr.PropertyBuilder |
setDictSkipBuiltInAll(boolean skip)
set to 'true' to skip using all built-in dicts.
|
Ocr.PropertyBuilder |
setDictSkipBuiltInDefault(boolean skip)
set to 'true' to skip using the default built in dict.
|
Ocr.PropertyBuilder |
setImagePreProcessingType(Ocr.ImagePreProcessingType type)
Sets the image pre-processing type
|
Ocr.PropertyBuilder |
setInputPdfDpi(int dpi)
The DPI to be used to render the PDF file; default is 300 if not specified
|
Ocr.PropertyBuilder |
setLimitToCharset(String chars)
recognizes only certain characters
|
Ocr.PropertyBuilder |
setLimitToCharsetDigitsOnly()
only recognizes '0123456789'
|
Ocr.PropertyBuilder |
setOutputSeparateWords(boolean enable)
whether to use word as the base unit for output; set to false to use the default unit: line.
|
Ocr.PropertyBuilder |
setPageType(Ocr.PageType pageType)
hints the page type to the OCR engine
|
Ocr.PropertyBuilder |
setPageType(String pageType)
hints the page type to the OCR engine
|
Ocr.PropertyBuilder |
setPdfImageForceBlackWhite(boolean enable)
true to convert image in PDF to black/white to save space false for keeping as is (default).
|
Ocr.PropertyBuilder |
setPdfOutputFile(File file)
Target pdf output file when output format is set to pdf
|
Ocr.PropertyBuilder |
setPdfOutputFile(String filePath)
Target pdf output file when output format is set to pdf
|
Ocr.PropertyBuilder |
setPdfOutputFontSans(boolean enable)
true to set PDF output font to Sans, false to Serif (default).
|
Ocr.PropertyBuilder |
setPdfOutputReturnNothing()
Return neither plain text nor xml when the output format is set to PDF.
|
Ocr.PropertyBuilder |
setPdfOutputReturnPlainText()
Return plain text when the output format is set to PDF.
|
Ocr.PropertyBuilder |
setPdfOutputReturnXml()
Return xml when the output format is set to PDF.
|
Ocr.PropertyBuilder |
setPdfTextVisible(boolean enable)
true to make text recognized visible on PDF or false for transparent (default).
|
Ocr.PropertyBuilder |
setRtfOutputFile(File file)
Target rtf output file when output format is set to rtf
|
Ocr.PropertyBuilder |
setRtfOutputReturnNothing()
Return neither plain text nor xml when the output format is set to RTF.
|
Ocr.PropertyBuilder |
setRtfOutputReturnPlainText()
Return plain text when the output format is set to RTF.
|
Ocr.PropertyBuilder |
setRtfOutputReturnXml()
Return xml when the output format is set to rtf.
|
Ocr.PropertyBuilder |
setSkipTableDetection(boolean skipTableDetection)
Whether table detection should be skipped.
|
Ocr.PropertyBuilder |
setTableDetectionMinSideLength(int minSideLength)
Sets the min side length of a table cell when table detection is enabled.
|
getProperty, getProperty, list, list, load, load, loadFromXML, propertyNames, save, setProperty, store, store, storeToXML, storeToXML, stringPropertyNames
clear, clone, compute, computeIfAbsent, computeIfPresent, contains, containsKey, containsValue, elements, entrySet, equals, forEach, get, getOrDefault, hashCode, isEmpty, keys, keySet, merge, put, putAll, putIfAbsent, rehash, remove, remove, replace, replace, replaceAll, size, toString, values
public Ocr.PropertyBuilder setDictSkipBuiltInDefault(boolean skip)
public Ocr.PropertyBuilder setDictSkipBuiltInAll(boolean skip)
public Ocr.PropertyBuilder setDictCustomDictFile(File customDictFile)
public Ocr.PropertyBuilder setDictCustomTemplatesFile(File customTemplatesFile)
public Ocr.PropertyBuilder setDictImportance(int importance)
public Ocr.PropertyBuilder setPageType(Ocr.PageType pageType)
public Ocr.PropertyBuilder setPageType(String pageType)
public Ocr.PropertyBuilder setLimitToCharset(String chars)
public Ocr.PropertyBuilder setLimitToCharsetDigitsOnly()
public Ocr.PropertyBuilder setOutputSeparateWords(boolean enable)
public Ocr.PropertyBuilder setInputPdfDpi(int dpi)
public Ocr.PropertyBuilder setImagePreProcessingType(Ocr.ImagePreProcessingType type)
public Ocr.PropertyBuilder setCustomImagePreProcessing(String cmds)
public Ocr.PropertyBuilder setSkipTableDetection(boolean skipTableDetection)
public Ocr.PropertyBuilder setTableDetectionMinSideLength(int minSideLength)
public Ocr.PropertyBuilder saveIntermediateImagesToDir(File dir)
public Ocr.PropertyBuilder setPdfOutputFile(File file)
public Ocr.PropertyBuilder setPdfOutputFile(String filePath)
public Ocr.PropertyBuilder setPdfOutputFontSans(boolean enable)
public Ocr.PropertyBuilder setPdfTextVisible(boolean enable)
public Ocr.PropertyBuilder setPdfImageForceBlackWhite(boolean enable)
public Ocr.PropertyBuilder setPdfOutputReturnPlainText()
public Ocr.PropertyBuilder setPdfOutputReturnXml()
public Ocr.PropertyBuilder setPdfOutputReturnNothing()
public Ocr.PropertyBuilder setRtfOutputFile(File file)
public Ocr.PropertyBuilder setRtfOutputReturnPlainText()
public Ocr.PropertyBuilder setRtfOutputReturnXml()
public Ocr.PropertyBuilder setRtfOutputReturnNothing()
Copyright 2015 (C) Asprise. » Asprise OCR Home · Developer's Guide