Colin M. Ford colinmford

Business Models

Advertising

Models	Examples
Display ads	Yahoo!
Search ads	Google

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

	#!/bin/sh

	###
	# SOME COMMANDS WILL NOT WORK ON macOS (Sierra or newer)
	# For Sierra or newer, see https://github.com/mathiasbynens/dotfiles/blob/master/.macos
	###

	# Alot of these configs have been taken from the various places
	# on the web, most from here
	# https://github.com/mathiasbynens/dotfiles/blob/5b3c8418ed42d93af2e647dc9d122f25cc034871/.osx

	# [email protected]
	### requires an icon file toolGoMetrics.pdf in the same folder
	# download it from www.theharrietseries.com/crypt/robofont/toolGoMetrics.pdf
	### updated 2013/03/10 — linked to didfontopen observers, just set as a startup script
	### updated 2013/07/16 — fixed lame selection traceback and broken spacecenter adjustments
	# to do: adjust by percent, uniform adjust, remember last setting

	import os
	from vanilla import *
	from mojo.UI import CurrentFontWindow, CurrentSpaceCenter

	# Ventriloquist - Build 0.1
	# insert a dummy dsig table with unique numbers into .otf fonts
	# the idea is to kill two birds with one stone
	# this idea needs lots of testing
	# to do: add SerialDump[] to a txt file for record keeping
	#
	# [email protected]

	from fontTools.ttLib import TTFont
	from mojo.compile import *

	# jackson @ okaytype.com
	# simpler big glyph preview window v3

	from vanilla import Window
	from defconAppKit.windows.baseWindow import BaseWindowController
	from mojo import events
	from mojo.events import addObserver, removeObserver
	from mojo.glyphPreview import GlyphPreview

	class BigGlyphPreview(BaseWindowController):

	"""
	Ported from Paper.js - The Swiss Army Knife of Vector Graphics Scripting.
	http://paperjs.org/

	Copyright (c) 2011 - 2014, Juerg Lehni & Jonathan Puckey
	http://scratchdisk.com/ & http://jonathanpuckey.com/

	Distributed under the MIT license. See LICENSE file for details.
	All rights reserved.

	# Robofont script to remove broken image paths, keeping good ones intact.
	import os
	f = CurrentFont()

	layerOrder = ['foreground']
	layerOrder.extend(f.layerOrder)

	for g in f:
	for layerName in layerOrder:
	layeredGlyph = g.getLayer(layerName)

	#Step 1
	import cv2 # working with, mainly resizing, images
	import numpy as np # dealing with arrays
	import os # dealing with directories
	from random import shuffle # mixing up or currently ordered data that might lead our network astray in training.
	from tqdm import tqdm # a nice pretty percentage bar for tasks. Thanks to viewer Daniel BA1/4hler for this suggestion
	import tensorflow as tf #Import Tensorflow
	import glob #This will extract all files from the folder
	import keras
	from keras.preprocessing.image import ImageDataGenerator

	#MenuTitle: HT LetterKerner

	# Put this in your HTLetterSpacer script directory so it can find
	# the library.

	# Todo:
	# Does not handle whole-font yet.
	# Does not know or care about kerning groups.
	# The reference glyph should be adjusted based on the letter pair
	# - "n" works well for lowercase-lowercase