Text extraction on image

Inga Ulusoy, SSC, July 2022

# if running on google colab
# flake8-noqa-cell
import os

if "google.colab" in str(get_ipython()):
    # update python version
    # install setuptools
    !pip install setuptools==61 -qqq
    # install ammico
    !pip install git+https://github.com/ssciwr/ammico.git -qqq
    # mount google drive for data and API key
    from google.colab import drive

    drive.mount("/content/drive")

import ammico
from ammico import utils as mutils
from ammico import display as mdisplay

# download the models if they are not there yet
!python -m spacy download en_core_web_md
!python -m textblob.download_corpora

Collecting en-core-web-md==3.5.0
  Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.5.0/en_core_web_md-3.5.0-py3-none-any.whl (42.8 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 42.8/42.8 MB 45.5 MB/s eta 0:00:00
Requirement already satisfied: spacy<3.6.0,>=3.5.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from en-core-web-md==3.5.0) (3.5.3)
Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (3.0.12)
Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (1.0.4)
Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (1.0.9)
Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (2.0.7)
Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (3.0.8)
Requirement already satisfied: thinc<8.2.0,>=8.1.8 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (8.1.10)
Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (1.1.1)
Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (2.4.6)
Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (2.0.8)
Requirement already satisfied: typer<0.8.0,>=0.3.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (0.7.0)
Requirement already satisfied: pathy>=0.10.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (0.10.1)
Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (6.3.0)
Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (4.65.0)
Requirement already satisfied: numpy>=1.15.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (1.23.4)
Requirement already satisfied: requests<3.0.0,>=2.13.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (2.30.0)
Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (1.10.7)
Requirement already satisfied: jinja2 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (3.1.2)
Requirement already satisfied: setuptools in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (58.1.0)
Requirement already satisfied: packaging>=20.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (23.1)
Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (3.3.0)
Requirement already satisfied: typing-extensions>=4.2.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4->spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (4.5.0)
Requirement already satisfied: charset-normalizer<4,>=2 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (3.1.0)
Requirement already satisfied: idna<4,>=2.5 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (2.10)
Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (1.26.15)
Requirement already satisfied: certifi>=2017.4.17 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (2023.5.7)
Requirement already satisfied: blis<0.8.0,>=0.7.8 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from thinc<8.2.0,>=8.1.8->spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (0.7.9)
Requirement already satisfied: confection<1.0.0,>=0.0.1 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from thinc<8.2.0,>=8.1.8->spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (0.0.4)
Requirement already satisfied: click<9.0.0,>=7.1.1 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from typer<0.8.0,>=0.3.0->spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (8.1.3)
Requirement already satisfied: MarkupSafe>=2.0 in /opt/hostedtoolcache/Python/3.9.16/x64/lib/python3.9/site-packages (from jinja2->spacy<3.6.0,>=3.5.0->en-core-web-md==3.5.0) (2.1.2)
Installing collected packages: en-core-web-md
Successfully installed en-core-web-md-3.5.0

[notice] A new release of pip is available: 22.0.4 -> 23.1.2
[notice] To update, run: pip install --upgrade pip
✔ Download and installation successful
You can now load the package via spacy.load('en_core_web_md')
[nltk_data] Downloading package brown to /home/runner/nltk_data...
[nltk_data]   Unzipping corpora/brown.zip.
[nltk_data] Downloading package punkt to /home/runner/nltk_data...
[nltk_data]   Unzipping tokenizers/punkt.zip.
[nltk_data] Downloading package wordnet to /home/runner/nltk_data...
[nltk_data] Downloading package averaged_perceptron_tagger to
[nltk_data]     /home/runner/nltk_data...
[nltk_data]   Unzipping taggers/averaged_perceptron_tagger.zip.
[nltk_data] Downloading package conll2000 to /home/runner/nltk_data...
[nltk_data]   Unzipping corpora/conll2000.zip.
[nltk_data] Downloading package movie_reviews to
[nltk_data]     /home/runner/nltk_data...
[nltk_data]   Unzipping corpora/movie_reviews.zip.
Finished.

images = mutils.find_files(path="data", limit=10)

mydict = mutils.initialize_dict(images)

google cloud vision API

First 1000 images per month are free.

Inspect the elements per image

mdisplay.explore_analysis(mydict, identify="text-on-image")

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[6], line 1
----> 1 mdisplay.explore_analysis(mydict, identify="text-on-image")

AttributeError: module 'ammico.display' has no attribute 'explore_analysis'

Or directly analyze for further processing

for key in mydict:
    mydict[key] = ammico.text.TextDetector(
        mydict[key], analyse_text=True
    ).analyse_image()

Convert to dataframe and write csv

outdict = mutils.append_data_to_dict(mydict)
df = mutils.dump_df(outdict)

# check the dataframe
df.head(10)

	filename	text	text_language	text_english	text_clean	text_english_correct	polarity	subjectivity	text_summary	sentiment	sentiment_score	entity	entity_type
0	data/102730_eng.png	400 DEATHS GET E-BOOK X AN Corporation ncy Ser...	en	400 DEATHS GET E-BOOK X AN Corporation ncy Ser...	DEATHS GET E - BOOK X AN Corporation Services ...	400 DEATHS GET E-BOOK X of Corporation ney Ser...	-0.125000	0.375000	A municipal worker sprays disinfectant on his...	NEGATIVE	0.991692	[AN Corporation ncy Services, Ahmedabad, RE, #...	[ORG, LOC, PER, ORG]
1	data/102141_2_eng.png	CORONAVIRUS QUARANTINE CORONAVIRUS OUTBREAK BE...	en	CORONAVIRUS QUARANTINE CORONAVIRUS OUTBREAK BE...	CORONAVIRUS QUARANTINE CORONAVIRUS OUTBREAK BE...	CORONAVIRUS QUARANTINE CORONAVIRUS OUTBREAK BE...	0.000000	0.000000	Coronavirus QUARANTINE CORONAVIRUS OUTBREAK	NEGATIVE	0.976247	[CORONAVIRUS, ##AR, ##TI, ##RONAVIR, ##C, Co]	[ORG, MISC, MISC, ORG, MISC, MISC]
2	data/106349S_por.png	NEWS URGENTE SAMSUNG AO VIVO Rio de Janeiro NO...	pt	NEWS URGENT SAMSUNG LIVE Rio de Janeiro NEW CO...	NEWS URGENT SAMSUNG LIVE Rio de Janeiro NEW CO...	NEWS URGENT SAMSUNG LIVE Rio de Janeiro NEW CO...	-0.106818	0.588636	NEW COUNTING METHOD RJ City HALL EXCLUDES 1,1...	NEGATIVE	0.990659	[Rio de Janeiro, C, ##IT, P, ##NA, ##LTO]	[LOC, ORG, LOC, LOC, ORG, LOC]

# Write the csv
df.to_csv("./data_out.csv")