Tesseract Node.js - 使用" lang"选项会导致崩溃

时间:2017-07-17 15:41:46

标签: javascript node.js ocr tesseract

使用与英语不同的语言的Tesseract.js的基本用法会导致整个系统崩溃:

var options = {
    lang: 'deu',
};

var image = require("path").join(__dirname, 'lib/images/ocr-test-text.png');

var Tesseract = require('tesseract.js')

Tesseract.recognize(image, options)
.progress(function (info) {
    console.log(info);
})
.then(function (data) {
    console.log('done', data);
    process.exit();
})

触发以下错误:

> node index.js
{ status: 'loading tesseract core' }
{ status: 'loaded tesseract core' }
{ status: 'initializing tesseract', progress: 0 }
pre-main prep time: 68 ms
{ status: 'initializing tesseract', progress: 1 }
{ status: 'downloading deu.traineddata.gz',
  loaded: 116,
  progress: 0.00011697604814572795 }
events.js:182
      throw er; // Unhandled 'error' event
      ^

Error: incorrect header check
    at Gunzip.zlibOnError (zlib.js:146:15)

Github问题:https://github.com/naptha/tesseract.js/issues/129

知道发生了什么?

更新: 按照第一个答案的说明,然后下载" deu" trainingdata,出现以下错误:

export TESSDATA_PREFIX=/opt/TESSDATA && node get-text-from-image.js /opt/app/out/image.png
params [ '/opt/app/out/image.png' ]
progress { status: 'loading tesseract core' }
progress { status: 'loaded tesseract core' }
progress { status: 'initializing tesseract', progress: 0 }
pre-main prep time: 62 ms
progress { status: 'initializing tesseract', progress: 1 }
progress { status: 'loading deu.traineddata', progress: 0 }
progress { status: 'loading deu.traineddata', progress: 1 }
progress { status: 'initializing api', progress: 0 }
Failed loading language 'deu'
Tesseract couldn't load any languages!
progress { status: 'initializing api', progress: 0.3 }
progress { status: 'initializing api', progress: 0.6 }
progress { status: 'initializing api', progress: 1 }
progress { status: 'recognizing text', progress: 0 }
AdaptedTemplates != NULL:Error:Assert failed:in file ../classify/adaptmatch.cpp, line 190

/opt/app/node_modules/tesseract.js-core/index.js:4
function f(a){throw a;}var h=void 0,i=!0,j=null,k=!1;function aa(){return function(){}}function ba(a){return function(){return a}}var n,Module;Module||(Module=eval("(function() { try { return TesseractCore || {} } catch(e) { return {} } })()"));var ca={},da;for(da in Module)Module.hasOwnProperty(da)&&(ca[da]=Module[da]);var ea=i,fa=!ea&&i;
              ^
abort() at Error
    at Na (/opt/app/node_modules/tesseract.js-core/index.js:32:26)
    at Object.ka [as abort] (/opt/app/node_modules/tesseract.js-core/index.js:507:108)
    at _abort (/opt/app/node_modules/tesseract.js-core/index.js:373:173)
    at $L (/opt/app/node_modules/tesseract.js-core/index.js:383:55709)
    at jpa (/opt/app/node_modules/tesseract.js-core/index.js:388:22274)
    at lT (/opt/app/node_modules/tesseract.js-core/index.js:387:80568)
    at mT (/opt/app/node_modules/tesseract.js-core/index.js:387:80700)
    at Array.BS (/opt/app/node_modules/tesseract.js-core/index.js:387:69011)
    at bP (/opt/app/node_modules/tesseract.js-core/index.js:383:110121)
    at jT (/opt/app/node_modules/tesseract.js-core/index.js:387:80280)
If this abort() is unexpected, build with -s ASSERTIONS=1 which can give more information.

1 个答案:

答案 0 :(得分:1)

未能解压deu.traineddata.gz - 不明白为什么。您可能想要自己下载文件并尝试手动压缩它。这不是module creator建议的方式;这是你可以试试的其他东西。

在运行node.js的计算机上下载语言文件并将它们放在某处。

https://github.com/tesseract-ocr/tessdata

在环境中,确保变量TESSDATA_PREFIX指向该位置。例如,您可以将它们放在/opt/tessdata中。如果您这样做,可以像这样设置TESSDATA_PREFIX

export TESSDATA_PREFIX=/opt/tessdata

再试一次;这次它不应该尝试下载并解压缩它们。