Na linha de comando, você pode executar algo assim:
tesseract $imageFile $hocr hocr com a versão 3+ do tesseract.
$imageFile é a entrada, $hocr = arquivo HTML do OCR.
Você pode analisar o arquivo (por exemplo, com PHP) e obter uma caixa para cada palavra. Isso ajudará você a obter as coordenadas de cada palavra.
Usamos esse método para criar um PDF personalizado para pesquisa ... Colocamos o texto em uma página e sobrepomos a imagem original. Esse processo também pode ser simplificado com: man hocr2pdf
Em seguida, usamos o clássico e leve R & amp; SO PDF para criar o PDF rapidamente com um script personalizado para girar a imagem. Eu estou anexando a função atualizada (com a função de "fluxo" atualizada para suporte de "currículo" ... Intervalos de aceitação
class Mpdf extends Cezpdf
{
function addPngFromFile($file,$x,$y,$w=0,$h=0,$angle=0)
{
// read in a png file, interpret it, then add to the system
$error=0;
$tmp = get_magic_quotes_runtime();
set_magic_quotes_runtime(0);
$fp = @fopen($file,'rb');
if ($fp){
$data='';
while(!feof($fp)){
$data .= fread($fp,1024);
}
fclose($fp);
} else {
$error = 1;
$errormsg = 'trouble opening file: '.$file;
}
set_magic_quotes_runtime($tmp);
if (!$error){
$header = chr(137).chr(80).chr(78).chr(71).chr(13).chr(10).chr(26).chr(10);
if (substr($data,0,8)!=$header){
$error=1;
$errormsg = 'this file does not have a valid header';
}
}
if (!$error){
// set pointer
$p = 8;
$len = strlen($data);
// cycle through the file, identifying chunks
$haveHeader=0;
$info=array();
$idata='';
$pdata='';
while ($p<$len){
$chunkLen = $this->PRVT_getBytes($data,$p,4);
$chunkType = substr($data,$p+4,4);
switch($chunkType){
case 'IHDR':
// this is where all the file information comes from
$info['width']=$this->PRVT_getBytes($data,$p+8,4);
$info['height']=$this->PRVT_getBytes($data,$p+12,4);
$info['bitDepth']=ord($data[$p+16]);
$info['colorType']=ord($data[$p+17]);
$info['compressionMethod']=ord($data[$p+18]);
$info['filterMethod']=ord($data[$p+19]);
$info['interlaceMethod']=ord($data[$p+20]);
$haveHeader=1;
if ($info['compressionMethod']!=0){
$error=1;
$errormsg = 'unsupported compression method';
}
if ($info['filterMethod']!=0){
$error=1;
$errormsg = 'unsupported filter method';
}
break;
case 'PLTE':
$pdata.=substr($data,$p+8,$chunkLen);
break;
case 'IDAT':
$idata.=substr($data,$p+8,$chunkLen);
break;
case 'tRNS':
//this chunk can only occur once and it must occur after the PLTE chunk and before IDAT chunk
//print "tRNS found, color type = ".$info['colorType']."<BR>";
$transparency = array();
if ($info['colorType'] == 3) { // indexed color, rbg
/* corresponding to entries in the plte chunk
Alpha for palette index 0: 1 byte
Alpha for palette index 1: 1 byte
...etc...
*/
// there will be one entry for each palette entry. up until the last non-opaque entry.
// set up an array, stretching over all palette entries which will be o (opaque) or 1 (transparent)
$transparency['type']='indexed';
$numPalette = strlen($pdata)/3;
$trans=0;
for ($i=$chunkLen;$i>=0;$i--){
if (ord($data[$p+8+$i])==0){
$trans=$i;
}
}
$transparency['data'] = $trans;
} elseif($info['colorType'] == 0) { // grayscale
/* corresponding to entries in the plte chunk
Gray: 2 bytes, range 0 .. (2^bitdepth)-1
*/
$transparency['type']='indexed';
$transparency['data'] = ord($data[$p+8+1]);
} elseif($info['colorType'] == 2) { // truecolor
/* corresponding to entries in the plte chunk
Red: 2 bytes, range 0 .. (2^bitdepth)-1
Green: 2 bytes, range 0 .. (2^bitdepth)-1
Blue: 2 bytes, range 0 .. (2^bitdepth)-1
*/
$transparency['r']=$this->PRVT_getBytes($data,$p+8,2); // r from truecolor
$transparency['g']=$this->PRVT_getBytes($data,$p+10,2); // g from truecolor
$transparency['b']=$this->PRVT_getBytes($data,$p+12,2); // b from truecolor
} else {
//unsupported transparency type
}
// KS End new code
break;
default:
break;
}
$p += $chunkLen+12;
}
if(!$haveHeader){
$error = 1;
$errormsg = 'information header is missing';
}
if (isset($info['interlaceMethod']) && $info['interlaceMethod']){
$error = 1;
$errormsg = 'There appears to be no support for interlaced images in pdf.';
}
}
if (!$error && $info['bitDepth'] > 8){
$error = 1;
$errormsg = 'only bit depth of 8 or less is supported';
}
if (!$error){
if ($info['colorType']!=2 && $info['colorType']!=0 && $info['colorType']!=3){
$error = 1;
$errormsg = 'transparancey alpha channel not supported, transparency only supported for palette images.';
} else {
switch ($info['colorType']){
case 3:
$color = 'DeviceRGB';
$ncolor=1;
break;
case 2:
$color = 'DeviceRGB';
$ncolor=3;
break;
case 0:
$color = 'DeviceGray';
$ncolor=1;
break;
}
}
}
if ($error){
$this->addMessage('PNG error - ('.$file.') '.$errormsg);
return;
}
if ($w==0){
$w=$h/$info['height']*$info['width'];
}
if ($h==0){
$h=$w*$info['height']/$info['width'];
}
// so this image is ok... add it in.
$this->numImages++;
$im=$this->numImages;
$label='I'.$im;
$this->numObj++;
$options = array('label'=>$label,'data'=>$idata,'bitsPerComponent'=>$info['bitDepth'],'pdata'=>$pdata
,'iw'=>$info['width'],'ih'=>$info['height'],'type'=>'png','color'=>$color,'ncolor'=>$ncolor);
if (isset($transparency)){
$options['transparency']=$transparency;
}
$this->o_image($this->numObj,'new',$options);
# $angle in degrees
$this->objects[$this->currentContents]['c'].="\nq";
$this->objects[$this->currentContents]['c'].="\n".sprintf('%.3f',$w)." 0 0 ".sprintf('%.3f',$h)." ".sprintf('%.3f',$x)." ".sprintf('%.3f',$y)." cm";
{
$this->objects[$this->currentContents]['c'].="\n"."%%angle $angle ";
$a = deg2rad((float)$angle);
$this->objects[$this->currentContents]['c'].="\n".sprintf('%.6f',cos($a))." ".sprintf('%.6f',sin($a))." ".sprintf('%.6f',-1*sin($a))." ".sprintf('%.6f',cos($a))." 0 0 cm";
}
$this->objects[$this->currentContents]['c'].="\n/".$label.' Do';
$this->objects[$this->currentContents]['c'].="\nQ";
}
function stream($options=''){
// setting the options allows the adjustment of the headers
// values at the moment are:
// 'Content-Disposition'=>'filename' - sets the filename, though not too sure how well this will
// work as in my trial the browser seems to use the filename of the php file with .pdf on the end
// 'Accept-Ranges'=>1 or 0 - if this is not set to 1, then this header is not included, off by default
// this header seems to have caused some problems despite tha fact that it is supposed to solve
// them, so I am leaving it off by default.
// 'compress'=> 1 or 0 - apply content stream compression, this is on (1) by default
if (!is_array($options)){
$options=array();
}
if ( isset($options['compress']) && $options['compress']==0){
$tmp = $this->output(1);
} else {
$tmp = $this->output();
}
header("Content-type: application/pdf");
header("Content-Length: ".strlen(ltrim($tmp)));
$fileName = (isset($options['Content-Disposition'])?$options['Content-Disposition']:'file.pdf');
header("Content-Disposition: inline; filename=".$fileName);
if (isset($options['Accept-Ranges']) && $options['Accept-Ranges']==1){
header("Accept-Ranges: ".strlen(ltrim($tmp)));
}
echo ltrim($tmp);
}
}