Antony Wu antonywu

Using Python 3 + Google Cloud Vision API's OCR to extract text from photos and scanned documents

Just a quickie test in Python 3 (using Requests) to see if Google Cloud Vision can be used to effectively OCR a scanned data table and preserve its structure, in the way that products such as ABBYY FineReader can OCR an image and provide Excel-ready output.

The short answer: No. While Cloud Vision provides bounding polygon coordinates in its output, it doesn't provide it at the word or region level, which would be needed to then calculate the data delimiters.

On the other hand, the OCR quality is pretty good, if you just need to identify text anywhere in an image, without regards to its physical coordinates. I've included two examples:

####### 1. A low-resolution photo of road signs

Operational PGP

This is a guide on how to email securely.

There are many guides on how to install and use PGP to encrypt email. This is not one of them. This is a guide on secure communication using email with PGP encryption. If you are not familiar with PGP, please read another guide first. If you are comfortable using PGP to encrypt and decrypt emails, this guide will raise your security to the next level.

	<!doctype html>
	<html lang="en">
	<body>
	<article class="gallery" role="main">
	<section class="photos">
	{% for image in page.image %} <!-- Loop through the photos from the YAML frontmatter from an empty Jekyll post -->
	<figure>
	<img src="{{ page.image[forloop.index0] }}" alt="{{ page.image-alt[forloop.index0] }}"> <!-- Insert the src, the alt text for each image, using the forloop.index0 liquid helper -->
	</figure>
	<figcaption>{{ page.image-caption[forloop.index0] }}</figcaption> <!-- and the figcaption too -->

	if [ -f ${HOME}/.ssh-agent ]; then
	. ${HOME}/.ssh-agent > /dev/null
	fi
	if [ -z "$SSH_AGENT_PID" -o -z "`/usr/bin/ps -a\|/usr/bin/egrep \"^[ ]+$SSH_AGENT_PID\"`" ]; then
	/usr/bin/ssh-agent > ${HOME}/.ssh-agent
	. ${HOME}/.ssh-agent > /dev/null
	fi
	ssh-add ~/.ssh/id_rsa

	<!-- using the truncate filter -->
	{% for post in site.posts limit:10 %}
	<h2><a href="{{ post.url }}">{{ post.title }}</a></h2>
	<span class="post-date">{{ post.date \| date: "%B %d, %Y" }}</span>
	{% if post.content.size > 2000 %}
	{{ post.content \| truncatewords: 300 }} <!-- bad! content gives you rendered html and you will truncate in the middle of a node -->
	<a href="{{ post.url }}">read more</a>
	{% else %}
	{{ post.content }}
	{% endif %}