All Downloads are FREE. Search and download functionalities are using the official Maven repository.

net.sourceforge.tess4j.ITesseract Maven / Gradle / Ivy

Go to download

# Tess4J ## Description: A Java JNA wrapper for Tesseract OCR API. Tess4J is released and distributed under the Apache License, v2.0. ## Features: The library provides optical character recognition (OCR) support for: TIFF, JPEG, GIF, PNG, and BMP image formats Multi-page TIFF images PDF document format

There is a newer version: 5.13.0
Show newest version
/**
 * Copyright @ 2014 Quan Nguyen
 *
 * Licensed under the Apache License, Version 2.0 (the "License"); you may not
 * use this file except in compliance with the License. You may obtain a copy of
 * the License at
 *
 * http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
 * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
 * License for the specific language governing permissions and limitations under
 * the License.
 */
package net.sourceforge.tess4j;

import java.awt.Rectangle;
import java.awt.image.BufferedImage;
import java.io.File;
import java.nio.ByteBuffer;
import java.util.List;
import javax.imageio.IIOImage;

/**
 * An interface represents common OCR methods.
 */
public interface ITesseract {

    String htmlBeginTag = "\n"
            + "\n\n\n"
            + "\n\n"
            + "\n\n";
    String htmlEndTag = "\n\n";

    /**
     * Rendered formats supported by Tesseract.
     */
    public enum RenderedFormat {

        TEXT, HOCR, PDF, UNLV, BOX
    }

    /**
     * Performs OCR operation.
     *
     * @param imageFile an image file
     * @return the recognized text
     * @throws TesseractException
     */
    String doOCR(File imageFile) throws TesseractException;

    /**
     * Performs OCR operation.
     *
     * @param imageFile an image file
     * @param rect the bounding rectangle defines the region of the image to be
     * recognized. A rectangle of zero dimension or null indicates
     * the whole image.
     * @return the recognized text
     * @throws TesseractException
     */
    String doOCR(File imageFile, Rectangle rect) throws TesseractException;

    /**
     * Performs OCR operation.
     *
     * @param bi a buffered image
     * @return the recognized text
     * @throws TesseractException
     */
    String doOCR(BufferedImage bi) throws TesseractException;

    /**
     * Performs OCR operation.
     *
     * @param bi a buffered image
     * @param rect the bounding rectangle defines the region of the image to be
     * recognized. A rectangle of zero dimension or null indicates
     * the whole image.
     * @return the recognized text
     * @throws TesseractException
     */
    String doOCR(BufferedImage bi, Rectangle rect) throws TesseractException;

    /**
     * Performs OCR operation.
     *
     * @param imageList a list of IIOImage objects
     * @param rect the bounding rectangle defines the region of the image to be
     * recognized. A rectangle of zero dimension or null indicates
     * the whole image.
     * @return the recognized text
     * @throws TesseractException
     */
    String doOCR(List imageList, Rectangle rect) throws TesseractException;

    /**
     * Performs OCR operation.
     *
     * @param imageList a list of IIOImage objects
     * @param filename input file name. Needed only for training and reading a
     * UNLV zone file.
     * @param rect the bounding rectangle defines the region of the image to be
     * recognized. A rectangle of zero dimension or null indicates
     * the whole image.
     * @return the recognized text
     * @throws TesseractException
     */
    String doOCR(List imageList, String filename, Rectangle rect) throws TesseractException;

    /**
     * Performs OCR operation. Use SetImage, (optionally)
     * SetRectangle, and one or more of the Get*Text
     * functions.
     *
     * @param xsize width of image
     * @param ysize height of image
     * @param buf pixel data
     * @param rect the bounding rectangle defines the region of the image to be
     * recognized. A rectangle of zero dimension or null indicates
     * the whole image.
     * @param bpp bits per pixel, represents the bit depth of the image, with 1
     * for binary bitmap, 8 for gray, and 24 for color RGB.
     * @return the recognized text
     * @throws TesseractException
     */
    String doOCR(int xsize, int ysize, ByteBuffer buf, Rectangle rect, int bpp) throws TesseractException;

    /**
     * Performs OCR operation. Use SetImage, (optionally)
     * SetRectangle, and one or more of the Get*Text
     * functions.
     *
     * @param xsize width of image
     * @param ysize height of image
     * @param buf pixel data
     * @param filename input file name. Needed only for training and reading a
     * UNLV zone file.
     * @param rect the bounding rectangle defines the region of the image to be
     * recognized. A rectangle of zero dimension or null indicates
     * the whole image.
     * @param bpp bits per pixel, represents the bit depth of the image, with 1
     * for binary bitmap, 8 for gray, and 24 for color RGB.
     * @return the recognized text
     * @throws TesseractException
     */
    String doOCR(int xsize, int ysize, ByteBuffer buf, String filename, Rectangle rect, int bpp) throws TesseractException;

    /**
     * Sets tessdata path.
     *
     * @param datapath the tessdata path to set
     */
    void setDatapath(String datapath);

    /**
     * Sets language for OCR.
     *
     * @param language the language code, which follows ISO 639-3 standard.
     */
    void setLanguage(String language);

    /**
     * Sets OCR engine mode.
     *
     * @param ocrEngineMode the OcrEngineMode to set
     */
    void setOcrEngineMode(int ocrEngineMode);

    /**
     * Sets page segmentation mode.
     *
     * @param mode the page segmentation mode to set
     */
    void setPageSegMode(int mode);

    /**
     * Sets the value of Tesseract's internal parameter.
     *
     * @param key variable name, e.g., tessedit_create_hocr,
     * tessedit_char_whitelist, etc.
     * @param value value for corresponding variable, e.g., "1", "0",
     * "0123456789", etc.
     */
    void setTessVariable(String key, String value);

    /**
     * Sets configs to be passed to Tesseract's Init method.
     *
     * @param configs list of config filenames, e.g., "digits", "bazaar",
     * "quiet"
     */
    void setConfigs(List configs);

    /**
     * Creates documents for given renderers.
     *
     * @param filename input image
     * @param outputbase output filename without extension
     * @param formats types of renderers
     * @throws TesseractException
     */
    void createDocuments(String filename, String outputbase, List formats) throws TesseractException;

    /**
     * Creates documents for given renderers.
     *
     * @param filenames array of input files
     * @param outputbases array of output filenames without extension
     * @param formats types of renderers
     * @throws TesseractException
     */
    void createDocuments(String[] filenames, String[] outputbases, List formats) throws TesseractException;

    /**
     * Creates documents with OCR results for given renderers at specified page
     * iterator level.
     *
     * @param filenames array of input files
     * @param outputbases array of output filenames without extension
     * @param formats types of renderer
     * @param pageIteratorLevel TessPageIteratorLevel enum
     * @return OCR results
     * @throws TesseractException
     */
    List createDocumentsWithResults(String[] filenames, String[] outputbases, List formats, int pageIteratorLevel) throws TesseractException;

    /**
     * Gets segmented regions at specified page iterator level.
     *
     * @param bi input image
     * @param pageIteratorLevel TessPageIteratorLevel enum
     * @return list of Rectangle
     * @throws TesseractException
     */
    List getSegmentedRegions(BufferedImage bi, int pageIteratorLevel) throws TesseractException;

    /**
     * Gets recognized words at specified page iterator level.
     *
     * @param bi input image
     * @param pageIteratorLevel TessPageIteratorLevel enum
     * @return list of Word
     */
    List getWords(BufferedImage bi, int pageIteratorLevel);
}




© 2015 - 2024 Weber Informatics LLC | Privacy Policy