akash-ch2812

from pdf2image import convert_from_path

pdfs = r"provide path to pdf file"
pages = convert_from_path(pdfs, 350)

i = 1
for page in pages:
    image_name = "Page_" + str(i) + ".jpg"  
    page.save(image_name, "JPEG")
    i = i+1        

akash-ch2812

# use this command to install open cv2
# pip install opencv-python

# use this command to install PIL
# pip install Pillow

import cv2
from PIL import Image

def mark_region(imagE_path):

akash-ch2812

import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Users\Akash.Chauhan1\AppData\Local\Tesseract-OCR\tesseract.exe'

# load the original image
image = cv2.imread('Original_Image.jpg')

# get co-ordinates to crop the image
c = line_items_coordinates[1]

# cropping image img = image[y0:y1, x0:x1]

akash-ch2812

import tensorflow as tf
from keras.preprocessing.image import ImageDataGenerator

# creating a sequential model
cnn = tf.keras.models.Sequential()

# adding convolution layer to network
cnn.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, activation='relu', input_shape=[64, 64, 3]))

# adding pooling layer to network

akash-ch2812

# adding a flatten layer to CNN
cnn.add(tf.keras.layers.Flatten())

# adding fully connected layers
cnn.add(tf.keras.layers.Dense(128, activation='relu'))
cnn.add(tf.keras.layers.Dense(64, activation='relu'))

# output layer -> 6 Neurons for 6 different classes
# activation function used for multiclass classification is softmax, for binary use sigmoid as activation fxn
cnn.add(tf.keras.layers.Dense(6, activation='softmax'))

akash-ch2812

# import statements
import tensorflow as tf
from keras.preprocessing.image import ImageDataGenerator
import numpy as np

# loading training data
train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,

akash-ch2812

import tensorflow as tf
from keras.preprocessing import image

import numpy as np

# function to extract features from image
def extract_image_features():
    
    model = tf.keras.models.Sequential()
    

akash-ch2812

import tensorflow as tf
from keras.preprocessing import image
from keras.applications.resnet50 import ResNet50
from keras.applications.resnet50 import preprocess_input
from keras.models import Model

# load the ResNet50 Model
feature_extractor = ResNet50(weights='imagenet', include_top=False)
feature_extractor_new = Model(feature_extractor.input, feature_extractor.layers[-2].output)
feature_extractor_new.summary()

akash-ch2812

# loading captions from captions file
import pandas as pd

# loading captions.txt
captions = pd.read_csv('/kaggle/input/flickr8k/captions.txt', sep=",")
captions = captions.rename(columns=lambda x: x.strip().lower())
captions['image'] = captions['image'].apply(lambda x: x.split(".")[0])
captions = captions[['image', 'caption']]
# adding <start> and <end> to every caption
captions['caption'] = "<start> " + captions['caption'] + " <end>"

akash-ch2812

import spacy
nlp = spacy.load('en', disable=['tagger', 'parser', 'ner'])

# tokenize evry captions, remove punctuations, lowercase everything
for key, value in train_image_captions.items():
    ls = []
    for v in value:
        doc = nlp(v)
        new_v = " "
        for token in doc: