mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-12-23 06:57:50 +08:00
1164 lines
31 KiB
HTML
1164 lines
31 KiB
HTML
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
|
|
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
|
|
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">
|
|
<head>
|
|
<meta http-equiv="Content-Type" content="application/xhtml+xml; charset=UTF-8" />
|
|
<meta name="generator" content="AsciiDoc 8.6.9" />
|
|
<title>TESSERACT(1)</title>
|
|
<style type="text/css">
|
|
/* Shared CSS for AsciiDoc xhtml11 and html5 backends */
|
|
|
|
/* Default font. */
|
|
body {
|
|
font-family: Georgia,serif;
|
|
}
|
|
|
|
/* Title font. */
|
|
h1, h2, h3, h4, h5, h6,
|
|
div.title, caption.title,
|
|
thead, p.table.header,
|
|
#toctitle,
|
|
#author, #revnumber, #revdate, #revremark,
|
|
#footer {
|
|
font-family: Arial,Helvetica,sans-serif;
|
|
}
|
|
|
|
body {
|
|
margin: 1em 5% 1em 5%;
|
|
}
|
|
|
|
a {
|
|
color: blue;
|
|
text-decoration: underline;
|
|
}
|
|
a:visited {
|
|
color: fuchsia;
|
|
}
|
|
|
|
em {
|
|
font-style: italic;
|
|
color: navy;
|
|
}
|
|
|
|
strong {
|
|
font-weight: bold;
|
|
color: #083194;
|
|
}
|
|
|
|
h1, h2, h3, h4, h5, h6 {
|
|
color: #527bbd;
|
|
margin-top: 1.2em;
|
|
margin-bottom: 0.5em;
|
|
line-height: 1.3;
|
|
}
|
|
|
|
h1, h2, h3 {
|
|
border-bottom: 2px solid silver;
|
|
}
|
|
h2 {
|
|
padding-top: 0.5em;
|
|
}
|
|
h3 {
|
|
float: left;
|
|
}
|
|
h3 + * {
|
|
clear: left;
|
|
}
|
|
h5 {
|
|
font-size: 1.0em;
|
|
}
|
|
|
|
div.sectionbody {
|
|
margin-left: 0;
|
|
}
|
|
|
|
hr {
|
|
border: 1px solid silver;
|
|
}
|
|
|
|
p {
|
|
margin-top: 0.5em;
|
|
margin-bottom: 0.5em;
|
|
}
|
|
|
|
ul, ol, li > p {
|
|
margin-top: 0;
|
|
}
|
|
ul > li { color: #aaa; }
|
|
ul > li > * { color: black; }
|
|
|
|
.monospaced, code, pre {
|
|
font-family: "Courier New", Courier, monospace;
|
|
font-size: inherit;
|
|
color: navy;
|
|
padding: 0;
|
|
margin: 0;
|
|
}
|
|
pre {
|
|
white-space: pre-wrap;
|
|
}
|
|
|
|
#author {
|
|
color: #527bbd;
|
|
font-weight: bold;
|
|
font-size: 1.1em;
|
|
}
|
|
#email {
|
|
}
|
|
#revnumber, #revdate, #revremark {
|
|
}
|
|
|
|
#footer {
|
|
font-size: small;
|
|
border-top: 2px solid silver;
|
|
padding-top: 0.5em;
|
|
margin-top: 4.0em;
|
|
}
|
|
#footer-text {
|
|
float: left;
|
|
padding-bottom: 0.5em;
|
|
}
|
|
#footer-badges {
|
|
float: right;
|
|
padding-bottom: 0.5em;
|
|
}
|
|
|
|
#preamble {
|
|
margin-top: 1.5em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
div.imageblock, div.exampleblock, div.verseblock,
|
|
div.quoteblock, div.literalblock, div.listingblock, div.sidebarblock,
|
|
div.admonitionblock {
|
|
margin-top: 1.0em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
div.admonitionblock {
|
|
margin-top: 2.0em;
|
|
margin-bottom: 2.0em;
|
|
margin-right: 10%;
|
|
color: #606060;
|
|
}
|
|
|
|
div.content { /* Block element content. */
|
|
padding: 0;
|
|
}
|
|
|
|
/* Block element titles. */
|
|
div.title, caption.title {
|
|
color: #527bbd;
|
|
font-weight: bold;
|
|
text-align: left;
|
|
margin-top: 1.0em;
|
|
margin-bottom: 0.5em;
|
|
}
|
|
div.title + * {
|
|
margin-top: 0;
|
|
}
|
|
|
|
td div.title:first-child {
|
|
margin-top: 0.0em;
|
|
}
|
|
div.content div.title:first-child {
|
|
margin-top: 0.0em;
|
|
}
|
|
div.content + div.title {
|
|
margin-top: 0.0em;
|
|
}
|
|
|
|
div.sidebarblock > div.content {
|
|
background: #ffffee;
|
|
border: 1px solid #dddddd;
|
|
border-left: 4px solid #f0f0f0;
|
|
padding: 0.5em;
|
|
}
|
|
|
|
div.listingblock > div.content {
|
|
border: 1px solid #dddddd;
|
|
border-left: 5px solid #f0f0f0;
|
|
background: #f8f8f8;
|
|
padding: 0.5em;
|
|
}
|
|
|
|
div.quoteblock, div.verseblock {
|
|
padding-left: 1.0em;
|
|
margin-left: 1.0em;
|
|
margin-right: 10%;
|
|
border-left: 5px solid #f0f0f0;
|
|
color: #888;
|
|
}
|
|
|
|
div.quoteblock > div.attribution {
|
|
padding-top: 0.5em;
|
|
text-align: right;
|
|
}
|
|
|
|
div.verseblock > pre.content {
|
|
font-family: inherit;
|
|
font-size: inherit;
|
|
}
|
|
div.verseblock > div.attribution {
|
|
padding-top: 0.75em;
|
|
text-align: left;
|
|
}
|
|
/* DEPRECATED: Pre version 8.2.7 verse style literal block. */
|
|
div.verseblock + div.attribution {
|
|
text-align: left;
|
|
}
|
|
|
|
div.admonitionblock .icon {
|
|
vertical-align: top;
|
|
font-size: 1.1em;
|
|
font-weight: bold;
|
|
text-decoration: underline;
|
|
color: #527bbd;
|
|
padding-right: 0.5em;
|
|
}
|
|
div.admonitionblock td.content {
|
|
padding-left: 0.5em;
|
|
border-left: 3px solid #dddddd;
|
|
}
|
|
|
|
div.exampleblock > div.content {
|
|
border-left: 3px solid #dddddd;
|
|
padding-left: 0.5em;
|
|
}
|
|
|
|
div.imageblock div.content { padding-left: 0; }
|
|
span.image img { border-style: none; vertical-align: text-bottom; }
|
|
a.image:visited { color: white; }
|
|
|
|
dl {
|
|
margin-top: 0.8em;
|
|
margin-bottom: 0.8em;
|
|
}
|
|
dt {
|
|
margin-top: 0.5em;
|
|
margin-bottom: 0;
|
|
font-style: normal;
|
|
color: navy;
|
|
}
|
|
dd > *:first-child {
|
|
margin-top: 0.1em;
|
|
}
|
|
|
|
ul, ol {
|
|
list-style-position: outside;
|
|
}
|
|
ol.arabic {
|
|
list-style-type: decimal;
|
|
}
|
|
ol.loweralpha {
|
|
list-style-type: lower-alpha;
|
|
}
|
|
ol.upperalpha {
|
|
list-style-type: upper-alpha;
|
|
}
|
|
ol.lowerroman {
|
|
list-style-type: lower-roman;
|
|
}
|
|
ol.upperroman {
|
|
list-style-type: upper-roman;
|
|
}
|
|
|
|
div.compact ul, div.compact ol,
|
|
div.compact p, div.compact p,
|
|
div.compact div, div.compact div {
|
|
margin-top: 0.1em;
|
|
margin-bottom: 0.1em;
|
|
}
|
|
|
|
tfoot {
|
|
font-weight: bold;
|
|
}
|
|
td > div.verse {
|
|
white-space: pre;
|
|
}
|
|
|
|
div.hdlist {
|
|
margin-top: 0.8em;
|
|
margin-bottom: 0.8em;
|
|
}
|
|
div.hdlist tr {
|
|
padding-bottom: 15px;
|
|
}
|
|
dt.hdlist1.strong, td.hdlist1.strong {
|
|
font-weight: bold;
|
|
}
|
|
td.hdlist1 {
|
|
vertical-align: top;
|
|
font-style: normal;
|
|
padding-right: 0.8em;
|
|
color: navy;
|
|
}
|
|
td.hdlist2 {
|
|
vertical-align: top;
|
|
}
|
|
div.hdlist.compact tr {
|
|
margin: 0;
|
|
padding-bottom: 0;
|
|
}
|
|
|
|
.comment {
|
|
background: yellow;
|
|
}
|
|
|
|
.footnote, .footnoteref {
|
|
font-size: 0.8em;
|
|
}
|
|
|
|
span.footnote, span.footnoteref {
|
|
vertical-align: super;
|
|
}
|
|
|
|
#footnotes {
|
|
margin: 20px 0 20px 0;
|
|
padding: 7px 0 0 0;
|
|
}
|
|
|
|
#footnotes div.footnote {
|
|
margin: 0 0 5px 0;
|
|
}
|
|
|
|
#footnotes hr {
|
|
border: none;
|
|
border-top: 1px solid silver;
|
|
height: 1px;
|
|
text-align: left;
|
|
margin-left: 0;
|
|
width: 20%;
|
|
min-width: 100px;
|
|
}
|
|
|
|
div.colist td {
|
|
padding-right: 0.5em;
|
|
padding-bottom: 0.3em;
|
|
vertical-align: top;
|
|
}
|
|
div.colist td img {
|
|
margin-top: 0.3em;
|
|
}
|
|
|
|
@media print {
|
|
#footer-badges { display: none; }
|
|
}
|
|
|
|
#toc {
|
|
margin-bottom: 2.5em;
|
|
}
|
|
|
|
#toctitle {
|
|
color: #527bbd;
|
|
font-size: 1.1em;
|
|
font-weight: bold;
|
|
margin-top: 1.0em;
|
|
margin-bottom: 0.1em;
|
|
}
|
|
|
|
div.toclevel0, div.toclevel1, div.toclevel2, div.toclevel3, div.toclevel4 {
|
|
margin-top: 0;
|
|
margin-bottom: 0;
|
|
}
|
|
div.toclevel2 {
|
|
margin-left: 2em;
|
|
font-size: 0.9em;
|
|
}
|
|
div.toclevel3 {
|
|
margin-left: 4em;
|
|
font-size: 0.9em;
|
|
}
|
|
div.toclevel4 {
|
|
margin-left: 6em;
|
|
font-size: 0.9em;
|
|
}
|
|
|
|
span.aqua { color: aqua; }
|
|
span.black { color: black; }
|
|
span.blue { color: blue; }
|
|
span.fuchsia { color: fuchsia; }
|
|
span.gray { color: gray; }
|
|
span.green { color: green; }
|
|
span.lime { color: lime; }
|
|
span.maroon { color: maroon; }
|
|
span.navy { color: navy; }
|
|
span.olive { color: olive; }
|
|
span.purple { color: purple; }
|
|
span.red { color: red; }
|
|
span.silver { color: silver; }
|
|
span.teal { color: teal; }
|
|
span.white { color: white; }
|
|
span.yellow { color: yellow; }
|
|
|
|
span.aqua-background { background: aqua; }
|
|
span.black-background { background: black; }
|
|
span.blue-background { background: blue; }
|
|
span.fuchsia-background { background: fuchsia; }
|
|
span.gray-background { background: gray; }
|
|
span.green-background { background: green; }
|
|
span.lime-background { background: lime; }
|
|
span.maroon-background { background: maroon; }
|
|
span.navy-background { background: navy; }
|
|
span.olive-background { background: olive; }
|
|
span.purple-background { background: purple; }
|
|
span.red-background { background: red; }
|
|
span.silver-background { background: silver; }
|
|
span.teal-background { background: teal; }
|
|
span.white-background { background: white; }
|
|
span.yellow-background { background: yellow; }
|
|
|
|
span.big { font-size: 2em; }
|
|
span.small { font-size: 0.6em; }
|
|
|
|
span.underline { text-decoration: underline; }
|
|
span.overline { text-decoration: overline; }
|
|
span.line-through { text-decoration: line-through; }
|
|
|
|
div.unbreakable { page-break-inside: avoid; }
|
|
|
|
|
|
/*
|
|
* xhtml11 specific
|
|
*
|
|
* */
|
|
|
|
div.tableblock {
|
|
margin-top: 1.0em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
div.tableblock > table {
|
|
border: 3px solid #527bbd;
|
|
}
|
|
thead, p.table.header {
|
|
font-weight: bold;
|
|
color: #527bbd;
|
|
}
|
|
p.table {
|
|
margin-top: 0;
|
|
}
|
|
/* Because the table frame attribute is overriden by CSS in most browsers. */
|
|
div.tableblock > table[frame="void"] {
|
|
border-style: none;
|
|
}
|
|
div.tableblock > table[frame="hsides"] {
|
|
border-left-style: none;
|
|
border-right-style: none;
|
|
}
|
|
div.tableblock > table[frame="vsides"] {
|
|
border-top-style: none;
|
|
border-bottom-style: none;
|
|
}
|
|
|
|
|
|
/*
|
|
* html5 specific
|
|
*
|
|
* */
|
|
|
|
table.tableblock {
|
|
margin-top: 1.0em;
|
|
margin-bottom: 1.5em;
|
|
}
|
|
thead, p.tableblock.header {
|
|
font-weight: bold;
|
|
color: #527bbd;
|
|
}
|
|
p.tableblock {
|
|
margin-top: 0;
|
|
}
|
|
table.tableblock {
|
|
border-width: 3px;
|
|
border-spacing: 0px;
|
|
border-style: solid;
|
|
border-color: #527bbd;
|
|
border-collapse: collapse;
|
|
}
|
|
th.tableblock, td.tableblock {
|
|
border-width: 1px;
|
|
padding: 4px;
|
|
border-style: solid;
|
|
border-color: #527bbd;
|
|
}
|
|
|
|
table.tableblock.frame-topbot {
|
|
border-left-style: hidden;
|
|
border-right-style: hidden;
|
|
}
|
|
table.tableblock.frame-sides {
|
|
border-top-style: hidden;
|
|
border-bottom-style: hidden;
|
|
}
|
|
table.tableblock.frame-none {
|
|
border-style: hidden;
|
|
}
|
|
|
|
th.tableblock.halign-left, td.tableblock.halign-left {
|
|
text-align: left;
|
|
}
|
|
th.tableblock.halign-center, td.tableblock.halign-center {
|
|
text-align: center;
|
|
}
|
|
th.tableblock.halign-right, td.tableblock.halign-right {
|
|
text-align: right;
|
|
}
|
|
|
|
th.tableblock.valign-top, td.tableblock.valign-top {
|
|
vertical-align: top;
|
|
}
|
|
th.tableblock.valign-middle, td.tableblock.valign-middle {
|
|
vertical-align: middle;
|
|
}
|
|
th.tableblock.valign-bottom, td.tableblock.valign-bottom {
|
|
vertical-align: bottom;
|
|
}
|
|
|
|
|
|
/*
|
|
* manpage specific
|
|
*
|
|
* */
|
|
|
|
body.manpage h1 {
|
|
padding-top: 0.5em;
|
|
padding-bottom: 0.5em;
|
|
border-top: 2px solid silver;
|
|
border-bottom: 2px solid silver;
|
|
}
|
|
body.manpage h2 {
|
|
border-style: none;
|
|
}
|
|
body.manpage div.sectionbody {
|
|
margin-left: 3em;
|
|
}
|
|
|
|
@media print {
|
|
body.manpage div#toc { display: none; }
|
|
}
|
|
|
|
|
|
</style>
|
|
<script type="text/javascript">
|
|
/*<+'])');
|
|
// Function that scans the DOM tree for header elements (the DOM2
|
|
// nodeIterator API would be a better technique but not supported by all
|
|
// browsers).
|
|
var iterate = function (el) {
|
|
for (var i = el.firstChild; i != null; i = i.nextSibling) {
|
|
if (i.nodeType == 1 /* Node.ELEMENT_NODE */) {
|
|
var mo = re.exec(i.tagName);
|
|
if (mo && (i.getAttribute("class") || i.getAttribute("className")) != "float") {
|
|
result[result.length] = new TocEntry(i, getText(i), mo[1]-1);
|
|
}
|
|
iterate(i);
|
|
}
|
|
}
|
|
}
|
|
iterate(el);
|
|
return result;
|
|
}
|
|
|
|
var toc = document.getElementById("toc");
|
|
if (!toc) {
|
|
return;
|
|
}
|
|
|
|
// Delete existing TOC entries in case we're reloading the TOC.
|
|
var tocEntriesToRemove = [];
|
|
var i;
|
|
for (i = 0; i < toc.childNodes.length; i++) {
|
|
var entry = toc.childNodes[i];
|
|
if (entry.nodeName.toLowerCase() == 'div'
|
|
&& entry.getAttribute("class")
|
|
&& entry.getAttribute("class").match(/^toclevel/))
|
|
tocEntriesToRemove.push(entry);
|
|
}
|
|
for (i = 0; i < tocEntriesToRemove.length; i++) {
|
|
toc.removeChild(tocEntriesToRemove[i]);
|
|
}
|
|
|
|
// Rebuild TOC entries.
|
|
var entries = tocEntries(document.getElementById("content"), toclevels);
|
|
for (var i = 0; i < entries.length; ++i) {
|
|
var entry = entries[i];
|
|
if (entry.element.id == "")
|
|
entry.element.id = "_toc_" + i;
|
|
var a = document.createElement("a");
|
|
a.href = "#" + entry.element.id;
|
|
a.appendChild(document.createTextNode(entry.text));
|
|
var div = document.createElement("div");
|
|
div.appendChild(a);
|
|
div.className = "toclevel" + entry.toclevel;
|
|
toc.appendChild(div);
|
|
}
|
|
if (entries.length == 0)
|
|
toc.parentNode.removeChild(toc);
|
|
},
|
|
|
|
|
|
/////////////////////////////////////////////////////////////////////
|
|
// Footnotes generator
|
|
/////////////////////////////////////////////////////////////////////
|
|
|
|
/* Based on footnote generation code from:
|
|
* http://www.brandspankingnew.net/archive/2005/07/format_footnote.html
|
|
*/
|
|
|
|
footnotes: function () {
|
|
// Delete existing footnote entries in case we're reloading the footnodes.
|
|
var i;
|
|
var noteholder = document.getElementById("footnotes");
|
|
if (!noteholder) {
|
|
return;
|
|
}
|
|
var entriesToRemove = [];
|
|
for (i = 0; i < noteholder.childNodes.length; i++) {
|
|
var entry = noteholder.childNodes[i];
|
|
if (entry.nodeName.toLowerCase() == 'div' && entry.getAttribute("class") == "footnote")
|
|
entriesToRemove.push(entry);
|
|
}
|
|
for (i = 0; i < entriesToRemove.length; i++) {
|
|
noteholder.removeChild(entriesToRemove[i]);
|
|
}
|
|
|
|
// Rebuild footnote entries.
|
|
var cont = document.getElementById("content");
|
|
var spans = cont.getElementsByTagName("span");
|
|
var refs = {};
|
|
var n = 0;
|
|
for (i=0; i<spans.length; i++) {
|
|
if (spans[i].className == "footnote") {
|
|
n++;
|
|
var note = spans[i].getAttribute("data-note");
|
|
if (!note) {
|
|
// Use [\s\S] in place of . so multi-line matches work.
|
|
// Because JavaScript has no s (dotall) regex flag.
|
|
note = spans[i].innerHTML.match(/\s*\[([\s\S]*)]\s*/)[1];
|
|
spans[i].innerHTML =
|
|
"[<a id='_footnoteref_" + n + "' href='#_footnote_" + n +
|
|
"' title='View footnote' class='footnote'>" + n + "</a>]";
|
|
spans[i].setAttribute("data-note", note);
|
|
}
|
|
noteholder.innerHTML +=
|
|
"<div class='footnote' id='_footnote_" + n + "'>" +
|
|
"<a href='#_footnoteref_" + n + "' title='Return to text'>" +
|
|
n + "</a>. " + note + "</div>";
|
|
var id =spans[i].getAttribute("id");
|
|
if (id != null) refs["#"+id] = n;
|
|
}
|
|
}
|
|
if (n == 0)
|
|
noteholder.parentNode.removeChild(noteholder);
|
|
else {
|
|
// Process footnoterefs.
|
|
for (i=0; i<spans.length; i++) {
|
|
if (spans[i].className == "footnoteref") {
|
|
var href = spans[i].getElementsByTagName("a")[0].getAttribute("href");
|
|
href = href.match(/#.*/)[0]; // Because IE return full URL.
|
|
n = refs[href];
|
|
spans[i].innerHTML =
|
|
"[<a href='#_footnote_" + n +
|
|
"' title='View footnote' class='footnote'>" + n + "</a>]";
|
|
}
|
|
}
|
|
}
|
|
},
|
|
|
|
install: function(toclevels) {
|
|
var timerId;
|
|
|
|
function reinstall() {
|
|
asciidoc.footnotes();
|
|
if (toclevels) {
|
|
asciidoc.toc(toclevels);
|
|
}
|
|
}
|
|
|
|
function reinstallAndRemoveTimer() {
|
|
clearInterval(timerId);
|
|
reinstall();
|
|
}
|
|
|
|
timerId = setInterval(reinstall, 500);
|
|
if (document.addEventListener)
|
|
document.addEventListener("DOMContentLoaded", reinstallAndRemoveTimer, false);
|
|
else
|
|
window.onload = reinstallAndRemoveTimer;
|
|
}
|
|
|
|
}
|
|
asciidoc.install();
|
|
/*]]>*/
|
|
</script>
|
|
</head>
|
|
<body class="manpage">
|
|
<div id="header">
|
|
<h1>
|
|
TESSERACT(1) Manual Page
|
|
</h1>
|
|
<h2>NAME</h2>
|
|
<div class="sectionbody">
|
|
<p>tesseract -
|
|
command-line OCR engine
|
|
</p>
|
|
</div>
|
|
</div>
|
|
<div id="content">
|
|
<div class="sect1">
|
|
<h2 id="_synopsis">SYNOPSIS</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p><strong>tesseract</strong> <em>imagename</em>|<em>stdin</em> <em>outputbase</em>|<em>stdout</em> [options…] [configfile…]</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_description">DESCRIPTION</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>tesseract(1) is a commercial quality OCR engine originally developed at HP
|
|
between 1985 and 1995. In 1995, this engine was among the top 3 evaluated by
|
|
UNLV. It was open-sourced by HP and UNLV in 2005, and has been developed
|
|
at Google since then.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_in_out_arguments">IN/OUT ARGUMENTS</h2>
|
|
<div class="sectionbody">
|
|
<div class="dlist"><dl>
|
|
<dt class="hdlist1">
|
|
<em>imagename</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
The name of the input image. Most image file formats (anything
|
|
readable by Leptonica) are supported.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>stdin</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
Instruction to read data from standard input
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>outputbase</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
The basename of the output file (to which the appropriate extension
|
|
will be appended). By default the output will be named <em>outbase.txt</em>.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>stdout</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
Instruction to sent output data to standard output
|
|
</p>
|
|
</dd>
|
|
</dl></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_options">OPTIONS</h2>
|
|
<div class="sectionbody">
|
|
<div class="dlist"><dl>
|
|
<dt class="hdlist1">
|
|
<em>--tessdata-dir /path</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
Specify the location of tessdata path
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>--user-words /path/to/file</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
Specify the location of user words file
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>--user-patterns /path/to/file specify</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
The location of user patterns file
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>-c configvar=value</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
Set value for control parameter. Multiple -c arguments are allowed.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>-l lang</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
The language to use. If none is specified, English is assumed.
|
|
Multiple languages may be specified, separated by plus characters.
|
|
Tesseract uses 3-character ISO 639-2 language codes. (See LANGUAGES)
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>-psm N</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
Set Tesseract to only run a subset of layout analysis and assume
|
|
a certain form of image. The options for <strong>N</strong> are:
|
|
</p>
|
|
<div class="literalblock">
|
|
<div class="content">
|
|
<pre><code>0 = Orientation and script detection (OSD) only.
|
|
1 = Automatic page segmentation with OSD.
|
|
2 = Automatic page segmentation, but no OSD, or OCR.
|
|
3 = Fully automatic page segmentation, but no OSD. (Default)
|
|
4 = Assume a single column of text of variable sizes.
|
|
5 = Assume a single uniform block of vertically aligned text.
|
|
6 = Assume a single uniform block of text.
|
|
7 = Treat the image as a single text line.
|
|
8 = Treat the image as a single word.
|
|
9 = Treat the image as a single word in a circle.
|
|
10 = Treat the image as a single character.</code></pre>
|
|
</div></div>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>configfile</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
The name of a config to use. A config is a plaintext file which
|
|
contains a list of variables and their values, one per line, with a
|
|
space separating variable from value. Interesting config files
|
|
include:<br />
|
|
</p>
|
|
<div class="ulist"><ul>
|
|
<li>
|
|
<p>
|
|
hocr - Output in hOCR format instead of as a text file.
|
|
</p>
|
|
</li>
|
|
<li>
|
|
<p>
|
|
pdf - Output in pdf instead of a text file.
|
|
</p>
|
|
</li>
|
|
</ul></div>
|
|
</dd>
|
|
</dl></div>
|
|
<div class="paragraph"><p><strong>Nota Bene:</strong> The options <em>-l lang</em> and <em>-psm N</em> must occur
|
|
before any <em>configfile</em>.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_single_options">SINGLE OPTIONS</h2>
|
|
<div class="sectionbody">
|
|
<div class="dlist"><dl>
|
|
<dt class="hdlist1">
|
|
<em>-v</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
Returns the current version of the tesseract(1) executable.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>--list-langs</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
list available languages for tesseract engine. Can be used with --tessdata-dir.
|
|
</p>
|
|
</dd>
|
|
<dt class="hdlist1">
|
|
<em>--print-parameters</em>
|
|
</dt>
|
|
<dd>
|
|
<p>
|
|
print tesseract parameters to the stdout.
|
|
</p>
|
|
</dd>
|
|
</dl></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_languages">LANGUAGES</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>There are currently language packs available for the following languages
|
|
(in <a href="https://github.com/tesseract-ocr/tessdata">https://github.com/tesseract-ocr/tessdata</a>):</p></div>
|
|
<div class="paragraph"><p><strong>afr</strong> (Afrikaans)
|
|
<strong>amh</strong> (Amharic)
|
|
<strong>ara</strong> (Arabic)
|
|
<strong>asm</strong> (Assamese)
|
|
<strong>aze</strong> (Azerbaijani)
|
|
<strong>aze_cyrl</strong> (Azerbaijani - Cyrilic)
|
|
<strong>bel</strong> (Belarusian)
|
|
<strong>ben</strong> (Bengali)
|
|
<strong>bod</strong> (Tibetan)
|
|
<strong>bos</strong> (Bosnian)
|
|
<strong>bul</strong> (Bulgarian)
|
|
<strong>cat</strong> (Catalan; Valencian)
|
|
<strong>ceb</strong> (Cebuano)
|
|
<strong>ces</strong> (Czech)
|
|
<strong>chi_sim</strong> (Chinese - Simplified)
|
|
<strong>chi_tra</strong> (Chinese - Traditional)
|
|
<strong>chr</strong> (Cherokee)
|
|
<strong>cym</strong> (Welsh)
|
|
<strong>dan</strong> (Danish)
|
|
<strong>dan_frak</strong> (Danish - Fraktur)
|
|
<strong>deu</strong> (German)
|
|
<strong>deu_frak</strong> (German - Fraktur)
|
|
<strong>dzo</strong> (Dzongkha)
|
|
<strong>ell</strong> (Greek, Modern (1453-))
|
|
<strong>eng</strong> (English)
|
|
<strong>enm</strong> (English, Middle (1100-1500))
|
|
<strong>epo</strong> (Esperanto)
|
|
<strong>equ</strong> (Math / equation detection module)
|
|
<strong>est</strong> (Estonian)
|
|
<strong>eus</strong> (Basque)
|
|
<strong>fas</strong> (Persian)
|
|
<strong>fin</strong> (Finnish)
|
|
<strong>fra</strong> (French)
|
|
<strong>frk</strong> (Frankish)
|
|
<strong>frm</strong> (French, Middle (ca.1400-1600))
|
|
<strong>gle</strong> (Irish)
|
|
<strong>glg</strong> (Galician)
|
|
<strong>grc</strong> (Greek, Ancient (to 1453))
|
|
<strong>guj</strong> (Gujarati)
|
|
<strong>hat</strong> (Haitian; Haitian Creole)
|
|
<strong>heb</strong> (Hebrew)
|
|
<strong>hin</strong> (Hindi)
|
|
<strong>hrv</strong> (Croatian)
|
|
<strong>hun</strong> (Hungarian)
|
|
<strong>iku</strong> (Inuktitut)
|
|
<strong>ind</strong> (Indonesian)
|
|
<strong>isl</strong> (Icelandic)
|
|
<strong>ita</strong> (Italian)
|
|
<strong>ita_old</strong> (Italian - Old)
|
|
<strong>jav</strong> (Javanese)
|
|
<strong>jpn</strong> (Japanese)
|
|
<strong>kan</strong> (Kannada)
|
|
<strong>kat</strong> (Georgian)
|
|
<strong>kat_old</strong> (Georgian - Old)
|
|
<strong>kaz</strong> (Kazakh)
|
|
<strong>khm</strong> (Central Khmer)
|
|
<strong>kir</strong> (Kirghiz; Kyrgyz)
|
|
<strong>kor</strong> (Korean)
|
|
<strong>kur</strong> (Kurdish)
|
|
<strong>lao</strong> (Lao)
|
|
<strong>lat</strong> (Latin)
|
|
<strong>lav</strong> (Latvian)
|
|
<strong>lit</strong> (Lithuanian)
|
|
<strong>mal</strong> (Malayalam)
|
|
<strong>mar</strong> (Marathi)
|
|
<strong>mkd</strong> (Macedonian)
|
|
<strong>mlt</strong> (Maltese)
|
|
<strong>msa</strong> (Malay)
|
|
<strong>mya</strong> (Burmese)
|
|
<strong>nep</strong> (Nepali)
|
|
<strong>nld</strong> (Dutch; Flemish)
|
|
<strong>nor</strong> (Norwegian)
|
|
<strong>ori</strong> (Oriya)
|
|
<strong>osd</strong> (Orientation and script detection module)
|
|
<strong>pan</strong> (Panjabi; Punjabi)
|
|
<strong>pol</strong> (Polish)
|
|
<strong>por</strong> (Portuguese)
|
|
<strong>pus</strong> (Pushto; Pashto)
|
|
<strong>ron</strong> (Romanian; Moldavian; Moldovan)
|
|
<strong>rus</strong> (Russian)
|
|
<strong>san</strong> (Sanskrit)
|
|
<strong>sin</strong> (Sinhala; Sinhalese)
|
|
<strong>slk</strong> (Slovak)
|
|
<strong>slk_frak</strong> (Slovak - Fraktur)
|
|
<strong>slv</strong> (Slovenian)
|
|
<strong>spa</strong> (Spanish; Castilian)
|
|
<strong>spa_old</strong> (Spanish; Castilian - Old)
|
|
<strong>sqi</strong> (Albanian)
|
|
<strong>srp</strong> (Serbian)
|
|
<strong>srp_latn</strong> (Serbian - Latin)
|
|
<strong>swa</strong> (Swahili)
|
|
<strong>swe</strong> (Swedish)
|
|
<strong>syr</strong> (Syriac)
|
|
<strong>tam</strong> (Tamil)
|
|
<strong>tel</strong> (Telugu)
|
|
<strong>tgk</strong> (Tajik)
|
|
<strong>tgl</strong> (Tagalog)
|
|
<strong>tha</strong> (Thai)
|
|
<strong>tir</strong> (Tigrinya)
|
|
<strong>tur</strong> (Turkish)
|
|
<strong>uig</strong> (Uighur; Uyghur)
|
|
<strong>ukr</strong> (Ukrainian)
|
|
<strong>urd</strong> (Urdu)
|
|
<strong>uzb</strong> (Uzbek)
|
|
<strong>uzb_cyrl</strong> (Uzbek - Cyrilic)
|
|
<strong>vie</strong> (Vietnamese)
|
|
<strong>yid</strong> (Yiddish)</p></div>
|
|
<div class="paragraph"><p>To use a non-standard language pack named <strong>foo.traineddata</strong>, set the
|
|
<strong>TESSDATA_PREFIX</strong> environment variable so the file can be found at
|
|
<strong>TESSDATA_PREFIX</strong>/tessdata/<strong>foo</strong>.traineddata and give Tesseract the
|
|
argument <em>-l foo</em>.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_config_files_and_augmenting_with_user_data">CONFIG FILES AND AUGMENTING WITH USER DATA</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>Tesseract config files consist of lines with variable-value pairs (space
|
|
separated). The variables are documented as flags in the source code like
|
|
the following one in tesseractclass.h:</p></div>
|
|
<div class="paragraph"><p>STRING_VAR_H(tessedit_char_blacklist, "",
|
|
"Blacklist of chars not to recognize");</p></div>
|
|
<div class="paragraph"><p>These variables may enable or disable various features of the engine, and
|
|
may cause it to load (or not load) various data. For instance, let’s suppose
|
|
you want to OCR in English, but suppress the normal dictionary and load an
|
|
alternative word list and an alternative list of patterns — these two files
|
|
are the most commonly used extra data files.</p></div>
|
|
<div class="paragraph"><p>If your language pack is in /path/to/eng.traineddata and the hocr config
|
|
is in /path/to/configs/hocr then create three new files:</p></div>
|
|
<div class="paragraph"><p>/path/to/eng.user-words:</p></div>
|
|
<div class="verseblock">
|
|
<pre class="content">the
|
|
quick
|
|
brown
|
|
fox
|
|
jumped</pre>
|
|
<div class="attribution">
|
|
</div></div>
|
|
<div class="paragraph"><p>/path/to/eng.user-patterns:</p></div>
|
|
<div class="verseblock">
|
|
<pre class="content">1-\d\d\d-GOOG-411
|
|
www.\n\\\*.com</pre>
|
|
<div class="attribution">
|
|
</div></div>
|
|
<div class="paragraph"><p>/path/to/configs/bazaar:</p></div>
|
|
<div class="verseblock">
|
|
<pre class="content">load_system_dawg F
|
|
load_freq_dawg F
|
|
user_words_suffix user-words
|
|
user_patterns_suffix user-patterns</pre>
|
|
<div class="attribution">
|
|
</div></div>
|
|
<div class="paragraph"><p>Now, if you pass the word <em>bazaar</em> as a trailing command line parameter
|
|
to Tesseract, Tesseract will not bother loading the system dictionary nor
|
|
the dictionary of frequent words and will load and use the eng.user-words
|
|
and eng.user-patterns files you provided. The former is a simple word list,
|
|
one per line. The format of the latter is documented in dict/trie.h
|
|
on read_pattern_list().</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_history">HISTORY</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>The engine was developed at Hewlett Packard Laboratories Bristol and at
|
|
Hewlett Packard Co, Greeley Colorado between 1985 and 1994, with some more
|
|
changes made in 1996 to port to Windows, and some C++izing in 1998. A
|
|
lot of the code was written in C, and then some more was written in C++.
|
|
The C\++ code makes heavy use of a list system using macros. This predates
|
|
stl, was portable before stl, and is more efficient than stl lists, but has
|
|
the big negative that if you do get a segmentation violation, it is hard to
|
|
debug.</p></div>
|
|
<div class="paragraph"><p>Version 2.00 brought Unicode (UTF-8) support, six languages, and the ability
|
|
to train Tesseract.</p></div>
|
|
<div class="paragraph"><p>Tesseract was included in UNLV’s Fourth Annual Test of OCR Accuracy.
|
|
See <a href="https://github.com/tesseract-ocr/docs/blob/master/AT-1995.pdf">https://github.com/tesseract-ocr/docs/blob/master/AT-1995.pdf</a>. With Tesseract 2.00,
|
|
scripts are now included to allow anyone to reproduce some of these tests.
|
|
See <a href="https://github.com/tesseract-ocr/tesseract/wiki/TestingTesseract">https://github.com/tesseract-ocr/tesseract/wiki/TestingTesseract</a> for more
|
|
details.</p></div>
|
|
<div class="paragraph"><p>Tesseract 3.00 adds a number of new languages, including Chinese, Japanese,
|
|
and Korean. It also introduces a new, single-file based system of managing
|
|
language data.</p></div>
|
|
<div class="paragraph"><p>Tesseract 3.02 adds BiDirectional text support, the ability to recognize
|
|
multiple languages in a single image, and improved layout analysis.</p></div>
|
|
<div class="paragraph"><p>For further details, see the file ReleaseNotes included with the distribution.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_resources">RESOURCES</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>Main web site: <a href="https://github.com/tesseract-ocr">https://github.com/tesseract-ocr</a><br />
|
|
Information on training: <a href="https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract">https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract</a></p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_see_also">SEE ALSO</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>ambiguous_words(1), cntraining(1), combine_tessdata(1), dawg2wordlist(1),
|
|
shape_training(1), mftraining(1), unicharambigs(5), unicharset(5),
|
|
unicharset_extractor(1), wordlist2dawg(1)</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_author">AUTHOR</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>Tesseract development was led at Hewlett-Packard and Google by Ray Smith.
|
|
The development team has included:</p></div>
|
|
<div class="paragraph"><p>Ahmad Abdulkader, Chris Newton, Dan Johnson, Dar-Shyang Lee, David Eger,
|
|
Eric Wiseblatt, Faisal Shafait, Hiroshi Takenaka, Joe Liu, Joern Wanke,
|
|
Mark Seaman, Mickey Namiki, Nicholas Beato, Oded Fuhrmann, Phil Cheatle,
|
|
Pingping Xiu, Pong Eksombatchai (Chantat), Ranjith Unnikrishnan, Raquel
|
|
Romano, Ray Smith, Rika Antonova, Robert Moss, Samuel Charron, Sheelagh
|
|
Lloyd, Shobhit Saxena, and Thomas Kielbus.</p></div>
|
|
</div>
|
|
</div>
|
|
<div class="sect1">
|
|
<h2 id="_copying">COPYING</h2>
|
|
<div class="sectionbody">
|
|
<div class="paragraph"><p>Licensed under the Apache License, Version 2.0</p></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div id="footnotes"><hr /></div>
|
|
<div id="footer">
|
|
<div id="footer-text">
|
|
Last updated 2015-06-28 22:23:47 CEST
|
|
</div>
|
|
</div>
|
|
</body>
|
|
</html>
|