209-handwritten-ocr: Handwritten Chinese and Japanese OCR

PHOTO

Fri Jun 17 2022 05:10:39 GMT+0000 (Coordinated Universal Time)

Saved by @OpenVINOtoolkit #python #openvino #openvino-notebooks #deeplearning #accelerated-inference ##nlp #ocr #chinese #japanese #handwritten

# Imports
from collections import namedtuple
from itertools import groupby
from pathlib import Path

import cv2
import matplotlib.pyplot as plt
import numpy as np
from openvino.runtime import Core

# Settings
# Directories where data will be placed
model_folder = "model"
data_folder = "data"
charlist_folder = f"{data_folder}/charlists"

# Precision used by model
precision = "FP16"

Language = namedtuple(
    typename="Language", field_names=["model_name", "charlist_name", "demo_image_name"]
)
chinese_files = Language(
    model_name="handwritten-simplified-chinese-recognition-0001",
    charlist_name="chinese_charlist.txt",
    demo_image_name="handwritten_chinese_test.jpg",
)
japanese_files = Language(
    model_name="handwritten-japanese-recognition-0001",
    charlist_name="japanese_charlist.txt",
    demo_image_name="handwritten_japanese_test.png",
)

# Select Language
# Select language by using either language='chinese' or language='japanese'
language = "chinese"

languages = {"chinese": chinese_files, "japanese": japanese_files}

selected_language = languages.get(language)

# Download Model
path_to_model_weights = Path(f'{model_folder}/intel/{selected_language.model_name}/{precision}/{selected_language.model_name}.bin')
if not path_to_model_weights.is_file():
    download_command = f'omz_downloader --name {selected_language.model_name} --output_dir {model_folder} --precision {precision}'
    print(download_command)
    ! $download_command

# Load Network and Execute
ie = Core()
path_to_model = path_to_model_weights.with_suffix(".xml")
model = ie.read_model(model=path_to_model)

# Select Device Name
# To check available device names run the line below
# print(ie.available_devices)

compiled_model = ie.compile_model(model=model, device_name="CPU")

# Fetch Information About Input and Output Layers
recognition_output_layer = compiled_model.output(0)
recognition_input_layer = compiled_model.input(0)

# Load an Image
# Read file name of demo file based on the selected model

file_name = selected_language.demo_image_name

# Text detection models expects an image in grayscale format
# IMPORTANT!!! This model allows to read only one line at time

# Read image
image = cv2.imread(filename=f"{data_folder}/{file_name}", flags=cv2.IMREAD_GRAYSCALE)

# Fetch shape
image_height, _ = image.shape

# B,C,H,W = batch size, number of channels, height, width
_, _, H, W = recognition_input_layer.shape

# Calculate scale ratio between input shape height and image height to resize image
scale_ratio = H / image_height

# Resize image to expected input sizes
resized_image = cv2.resize(
    image, None, fx=scale_ratio, fy=scale_ratio, interpolation=cv2.INTER_AREA
)

# Pad image to match input size, without changing aspect ratio
resized_image = np.pad(
    resized_image, ((0, 0), (0, W - resized_image.shape[1])), mode="edge"
)

# Reshape to network the input shape
input_image = resized_image[None, None, :, :]

# Visualise Input Image
plt.figure(figsize=(20, 1))
plt.axis("off")
plt.imshow(resized_image, cmap="gray", vmin=0, vmax=255);

# Prepare Charlist
# Get dictionary to encode output, based on model documentation
used_charlist = selected_language.charlist_name

# With both models, there should be blank symbol added at index 0 of each charlist
blank_char = "~"

with open(f"{charlist_folder}/{used_charlist}", "r", encoding="utf-8") as charlist:
    letters = blank_char + "".join(line.strip() for line in charlist)

# Run Inference
# Run inference on the model
predictions = compiled_model([input_image])[recognition_output_layer]

# Process Output Data
# Remove batch dimension
predictions = np.squeeze(predictions)

# Run argmax to pick the symbols with the highest probability
predictions_indexes = np.argmax(predictions, axis=1)

# Use groupby to remove concurrent letters, as required by CTC greedy decoding
output_text_indexes = list(groupby(predictions_indexes))

# Remove grouper objects
output_text_indexes, _ = np.transpose(output_text_indexes, (1, 0))

# Remove blank symbols
output_text_indexes = output_text_indexes[output_text_indexes != 0]

# Assign letters to indexes from output array
output_text = [letters[letter_index] for letter_index in output_text_indexes]

# Print Output
plt.figure(figsize=(20, 1))
plt.axis("off")
plt.imshow(resized_image, cmap="gray", vmin=0, vmax=255)

print("".join(output_text))

COPY

In this tutorial, we perform optical character recognition (OCR) for handwritten Chinese (simplified) and Japanese. An OCR tutorial using the Latin alphabet is available in notebook 208. This model is capable of processing only one line of symbols at a time. The models used in this notebook are handwritten-japanese-recognition and handwritten-simplified-chinese. To decode model outputs as readable text kondate_nakayosi and scut_ept charlists are used. Both models are available on Open Model Zoo. If you have not yet installed OpenVINO™, please follow the Installation Guide to install all required dependencies. https://github.com/openvinotoolkit/openvino_notebooks/blob/main/README.md#-installation-guide Link to .bin and .xml files: https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/intel/handwritten-japanese-recognition-0001/model.yml https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/intel/handwritten-simplified-chinese-recognition-0001/model.yml

https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/209-handwritten-ocr/209-handwritten-ocr.ipynb

Save snippets that work from anywhere online with our extensions

Comments

OpenVINO™ notebooks

@OpenVINOtoolkit

001-hello-world: Hello Image Classification using OpenVINO™ toolkit 002-openvino-api: OpenVINO API tutorial 003-hello-segmentation: Introduction to Segmentation in OpenVINO 004-hello-detection: Introduction to Detection in OpenVINO 101-tensorflow-to-openvino: TensorFlow to OpenVINO Model Conversion Tutorial 102-pytorch-onnx-to-openvino: PyTorch to ONNX and OpenVINO IR Tutorial 103-paddle-onnx-to-openvino: Convert a PaddlePaddle Model to ONNX and OpenVINO IR 104-model-tools: Working with Open Model Zoo Models 210-ct-scan-live-inference: Live Inference and Benchmark CT-scan Data with OpenVINO 201-vision-monodepth: Monodepth Estimation with OpenVINO 210-ct-scan-live-inference: Live Inference and Benchmark CT-scan Data with OpenVINO 401-object-detection-webcam: Live Object Detection with OpenVINO 402-pose-estimation-webcam: Live Human Pose Estimation with OpenVINO 403-action-recognition-webcam: Human Action Recognition with OpenVINO 211-speech-to-text: Speech to Text with OpenVINO 213-question-answering: Interactive Question Answering with OpenVINO 208-optical-character-recognition: Optical Character Recognition (OCR) with OpenVINO 209-handwritten-ocr: Handwritten Chinese and Japanese OCR 405-paddle-ocr-webcam: PaddleOCR with OpenVINO 305-tensorflow-quantization-aware-training: Optimizing TensorFlow models with Neural Network Compression Framework of OpenVINO by 8-bit quantization 302-pytorch-quantization-aware-training: Optimizing PyTorch models with Neural Network Compression Framework of OpenVINO by 8-bit quantization 301-tensorflow-training-openvino: Post-Training Quantization with TensorFlow Classification Model 301-tensorflow-training-openvino: From Training to Deployment with TensorFlow and OpenVINO 204-named-entity-recognition: Named Entity Recognition with OpenVINO

#python

Importing images from a directory (Python) to list or dictionary

from PIL import Image
import glob
image_list = []
for filename in glob.glob('yourpath/*.gif'): #assuming gif
    im=Image.open(filename)
    image_list.append(im)

#python

python - Find out the percentage of missing values in each column in the given dataset - Stack Overflow

percent_missing = df.isnull().sum() * 100 / len(df)
missing_value_df = pd.DataFrame({'column_name': df.columns,
                                 'percent_missing': percent_missing})

#python #python #loops #whileloop

Print the name of 7 days in a week - by using while loop

days = 0
week = [‘Monday’, ‘Tuesday’, ‘Wednesday’, ‘Thursday’, ‘Friday’, ‘Saturday’, 3.‘Sunday’]
while day < 7:
print(“Today is” + week[days])
days += 1

#python

Getting the index of an item in a list containing it in Python

>>> ["foo", "bar", "baz"].index("bar")
1

#python #python #strings #vowels #function

Get vowels in strings

This method gets vowels (‘a’, ‘e’, ‘i’, ‘o’, ‘u’) found in a string.
   
#make a function:
def get_vowels(string):

#return is the keyword which means function have to return value: 
 return [each for each in string if each in 'aeiou']


#assign the words and function will return vowels words.
get_vowels('foobar') # ['o', 'o', 'a']


get_vowels('gym') # []

#python

Could not build wheels for tokenizers which use PEP 517 and cannot be installed directly

https://github.com/pydata/bottleneck/issues/281

#python

How To Bypass Cloudflare Bot Protection In Selenium - CodingTutz

options = webdriver.ChromeOptions()
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_experimental_option('useAutomationExtension', False)
options.add_argument("--disable-blink-features=AutomationControlled")
driver = webdriver.Chrome(options=options)

#javascript #python #search #historicalcode #google #algorithms

Google’s PageRank Algorithm from 1996 - the origin of internet search

import numpy as np

def pagerank(M, num_iterations=100, d=0.85):
    N = M.shape[1]
    v = np.random.rand(N, 1)
    v = v / np.linalg.norm(v, 1)
    iteration = 0
    while iteration < num_iterations:
        iteration += 1
        v = d * np.matmul(M, v) + (1 - d) / N
    return v

#python

Python Loop through Excel sheets, place into one df - Stack Overflow

import pandas as pd

sheets_dict = pd.read_excel('Book1.xlsx', sheetname=None)

full_table = pd.DataFrame()
for name, sheet in sheets_dict.items():
    sheet['sheet'] = name
    sheet = sheet.rename(columns=lambda x: x.split('\n')[-1])
    full_table = full_table.append(sheet)

full_table.reset_index(inplace=True, drop=True)

print full_table

#python #dates #functions #python3.8

How to parse a String into Datetime in Python

from datetime import datetime

datetime_object = datetime.strptime('Jun 1 2005  1:33PM', '%b %d %Y %I:%M%p')

#python

python - Way to change Google Chrome user agent in Selenium? - Stack Overflow

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from fake_useragent import UserAgent

options = Options()
ua = UserAgent()
userAgent = ua.random
print(userAgent)
options.add_argument(f'user-agent={userAgent}')
driver = webdriver.Chrome(chrome_options=options, executable_path=r'C:\WebDrivers\ChromeDriver\chromedriver_win32\chromedriver.exe')
driver.get("https://www.google.co.in")
driver.quit()

#python

python - How to see the progress bar of read_csv - Stack Overflow

def read_csv_pgbar(csv_path, chunksize, usecols, dtype=object):


    # print('Getting row count of csv file')

    rows = sum(1 for _ in open(csv_path, 'r')) - 1 # minus the header
    # chunks = rows//chunksize + 1
    # print('Reading csv file')
    chunk_list = []

    with tqdm(total=rows, desc='Rows read: ') as bar:
        for chunk in pd.read_csv(csv_path, chunksize=chunksize, usecols=usecols, dtype=dtype):
            chunk_list.append(chunk)
            bar.update(len(chunk))

    df = pd.concat((f for f in chunk_list), axis=0)
    print('Finish reading csv file')

    return df

#python #python #lists #dictionary

Convert two lists into a dictionary

keys, values)) # {'a': 2, 'c': 4, 'b': 3}
 
 
#make a function: def is the keyword for the function:
def to_dictionary(keys, values):
 
 
#return is the keyword that tells program that function has to return value   
return dict(zip(keys, values))
 
  
 
# keys and values are the lists:
 
keys = ["a", "b", "c"]   
 
values = [2, 3, 4]

#python

Convert string to Enum in Python - Stack Overflow

>>> from enum import Enum
>>> class Build(Enum):
...   debug = 200
...   build = 400
... 

Build['debug']

#python

Raising errors in Python

my_list = [27, 5, 9, 6, 8]

def RemoveValue(myVal):
    if myVal not in my_list:
        raise ValueError("Value must be in the given list")
    else:
        my_list.remove(myVal)
    return my_list

print(RemoveValue(27))
print(RemoveValue(27))

209-handwritten-ocr: Handwritten Chinese and Japanese OCR

Save snippets that work from anywhere online with our extensions

Comments

More like this

OpenVINO™ notebooks

Browse more snippets >>

209-handwritten-ocr: Handwritten Chinese and Japanese OCR

Save snippets that work from anywhere online with our extensions

Comments

More like this

OpenVINO™ notebooks

Browse more snippets >>

Embed code snippet