{% extends "nopaque.html.j2" %} {% import 'materialize/wtf.html.j2' as wtf %} {% from '_constants.html.j2' import COLORS %} {% set scheme_primary_color = COLORS.ocr_darken %} {% set scheme_secondary_color = COLORS.ocr %} {% block nav_content %} {% include 'services/_nav_content.html.j2' %} {% endblock nav_content %} {% block main_attribs %} class="ocr-color lighten"{% endblock main_attribs %} {% block page_content %}

 

{{ title }}

 

 

layersOCR

In this process, nopaque converts your image data – like photos or scans – into text data. This step enables you to proceed with the computational analysis of your documents.

Submit a job

{{ add_job_form.hidden_tag() }}
{{ wtf.render_field(add_job_form.title, data_length='32', material_icon='title') }}
{{ wtf.render_field(add_job_form.description, data_length='255', material_icon='description') }}
{{ wtf.render_field(add_job_form.files, accept='application/pdf', color=ocr_color_darken, placeholder='Choose your .pdf files') }}
{{ wtf.render_field(add_job_form.language, material_icon='language') }}
{{ wtf.render_field(add_job_form.version, material_icon='apps') }}
Preprocessing

{{ add_job_form.binarization.label.text }}

Based on a brightness threshold pixels are converted into either black or white. It is useful to reduce noise in images. (longer duration)

 

 

Page range

 

 

Page rotation

 

 

Page split

{{ wtf.render_field(add_job_form.submit, color=ocr_color_darken, material_icon='send') }}
{% endblock %}