swflint
/
bin-files


			
				
					
						
						
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109
							<html>
<head>
    <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
    <title>jTessBoxEditor - Box Editor & Trainer for Tesseract OCR Data</title>
    <style type="text/css">
        .auto-style1
        {
            text-decoration: underline;
        }
    </style>
</head>
<body lang="EN-US">
    <div>
        <h2 style="text-align: center;">
            jTessBoxEditor</h2>
        <h3>
            DESCRIPTION</h3>
        <p>
            <a href="http://vietocr.sourceforge.net/training.html">jTessBoxEditor</a> is a box
            editor and trainer for <a href="https://github.com/tesseract-ocr/">Tesseract OCR</a>,
            providing editing of box data of both Tesseract 2.0x and 3.0x formats and full automation
            of Tesseract training. It can read common image formats, including multi-page TIFF.
        </p>
        <p>
            jTessBoxEditor is released and distributed under the <a href="http://www.apache.org/licenses/LICENSE-2.0.html">Apache License, v2.0</a>.
        </p>
        <h3>
            SYSTEM REQUIREMENTS</h3>
        <p>
            <a href="http://www.oracle.com/technetwork/java/javase/downloads/index.html">Java Runtime
                Environment 7.0</a> or later.
        </p>
        <h3>
            INSTRUCTIONS</h3>
        <p>
            Double-click on the JAR file to launch the program, or execute the following command:
        </p>
        <blockquote>
            <p>
                <code>java -Xms128m -Xmx1024m -jar jTessBoxEditor.jar</code>
            </p>
        </blockquote>
        <p>
            You will need to provide the TIFF/Box files as input to the editor. Images to be
            used in training should be of 300 DPI and 1 bpp (bit per pixel) black&amp;white
            or 8 bpp grayscale, uncompressed TIFF format; box files, encoded in UTF-8 format,
            are generated by Tesseract executables with appropriate command-line options (see
            <a href="https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract">Tesseract Training Wiki</a>). Or
            they both can be created using the built-in <em>TIFF/Box Generator</em>.</p>
        <p>
            The following hotkeys are available in Box View for ease of editing:</p>
        <ul>
            <li><strong>W/S</strong> - move box up/down;<strong> A/D</strong> - move box left/right</li>
            <li><strong>Q/E</strong> - decrease/increase box width;<strong> R/F</strong> - decrease/increase box height</li>
            <li><strong>&lt;/&gt;</strong> - previous/next box</li>
            <li><strong>X</strong> - edit character in box</li>
        </ul>
        <p>
            Holding Shift when using hotkeys multiplies movement speed by 10.
            Pressing Enter or ESC when editing character focuses the box editor.</p>
        <p>
            Note that the coordinate system used in the box file has (0,0) at the bottom-left;
            on computer graphics devices, however, (0,0) is defined as top-left. jTessBoxEditor
            uses and displays in the graphics device coordinates. The edited box files are still
            read and written in proper format.
        </p>
        <p>
            The generator produces, for a given input UTF-8 text file, a TIFF/Box pair of files
            suitable for training with Tesseract. The generated image is, depending on anti-aliasing
            mode enabled, a binary or grayscale, uncompressed multi-page TIFF with 300 DPI resolution.
            Letter tracking, or spacing between characters, can be adjusted to eliminate bounding
            box overlapping issues. Note that the coordinates of some boxes could be slightly
            different (by 1 or 2 pixels) from the ones that would have been generated by Tesseract
            itself; nevertheless, the generated box file can be used to validate the one created
            by Tesseract with the use of a Unicode-compatible file compare tool, such as <a href="http://sourceforge.net/projects/winmerge/">
                WinMerge</a>.
        </p>
        <p>
            <span class="auto-style1">Tips</span>: Experiments indicate that the quality of
            training with images created by <em>TIFF/Box Generator</em> is higher with font
            sizes 24pt or greater and with some noise added.
        </p>
        <p>
            Combining symbols or diacritics, like those found in Devanagari or Indic scripts,
            that need to be combined with the main, base character can be specified by the user
            in a UTF-8 text file, specifically <code>data/combiningsymbols.txt</code>, which is
            read by the generator. This setup gives the users the flexibility in
            defining combining symbols/diacritics for their language scripts.</p>
        <p>
            Automated training is provided in latest version. Tesseract Windows training executables
            are bundled with the program; for other platforms, you will need to <a href="https://github.com/tesseract-ocr/tesseract/wiki/Compiling">
                build</a> them. Place all required source training data files, prefixed with
            an appropriate language code, in a specified directory (check <code>samples</code>
            folder for examples). The training operation can also be automated using the enclosed
            <code>train.ps1</code> Windows PowerShell script.
        </p>
        <p>
            The <em>Merge TIFF</em> function can save multiple images containing text of the
            same font into a single multi-page TIFF file to be used for training.
            A conversion function is included to convert numeric character reference (NCR) and
            escape sequence in the <em>Character</em> text field to Unicode characters.</p>
        <p>
            If there is any question, please post in <a href="http://sourceforge.net/projects/vietocr/forums">
                VietOCR Forums</a>.
        </p>
        <hr />
    </div>
</body>
</html>