Update app.py

app.py

@@ -1,120 +1,94 @@
-import gradio as gr
-import tensorflow as tf
-import keras_ocr
-import requests
+import gradio as gr 
 import cv2
-import os
-import csv
-import numpy as np
-import pandas as pd
-import huggingface_hub
-from huggingface_hub import Repository
-from datetime import datetime
-import scipy.ndimage.interpolation as inter
 import easyocr
-import datasets
-from datasets import load_dataset, Image
-from PIL import Image
-from paddleocr import PaddleOCR
-from save_data import flag
-            
+import pandas as pd
+import nltk
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+from nltk.stem import PorterStemmer
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.ensemble import RandomForestClassifier
+
+# Download necessary NLTK data
+nltk.data.path.append("/usr/local/lib/nltk_data")
+nltk.download('punkt')
+nltk.download('stopwords')
+
 """
-Paddle OCR
+EasyOCR for Text Extraction
 """
-def ocr_with_paddle(img):
-    finaltext = ''
-    ocr = PaddleOCR(lang='en', use_angle_cls=True)
-    # img_path = 'exp.jpeg'
-    result = ocr.ocr(img)
+def ocr_with_easy(img):
+    # Convert image to grayscale
+    gray_scale_image = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    cv2.imwrite('image.png', gray_scale_image)
     
-    for i in range(len(result[0])):
-        text = result[0][i][1][0]
-        finaltext += ' '+ text
-    return finaltext
+    # Use EasyOCR to read text from the image
+    reader = easyocr.Reader(['en'])
+    bounds = reader.readtext('image.png', paragraph="False", detail=0)
+    extracted_text = ' '.join(bounds)
+    return extracted_text
 
 """
-Keras OCR
+Text Preprocessing for Spam Classification
 """
-def ocr_with_keras(img):
-    output_text = ''
-    pipeline=keras_ocr.pipeline.Pipeline()
-    images=[keras_ocr.tools.read(img)]
-    predictions=pipeline.recognize(images)
-    first=predictions[0]
-    for text,box in first:
-        output_text += ' '+ text
-    return output_text
+def preprocess_text(text):
+    tokens = word_tokenize(text.lower())
+    stop_words = set(stopwords.words('english'))
+    filtered_tokens = [word for word in tokens if word.isalnum() and word not in stop_words]
+    stemmer = PorterStemmer()
+    stemmed_tokens = [stemmer.stem(word) for word in filtered_tokens]
+    return ' '.join(stemmed_tokens)
 
 """
-easy OCR
+Load and Train Spam Classifier
 """
-# gray scale image
-def get_grayscale(image):
-    return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+# Load the dataset
+data = pd.read_csv('spam.csv', encoding='latin-1')
+data['v2'] = data['v2'].apply(preprocess_text)
+
+# Feature Extraction (TF-IDF)
+tfidf_vectorizer = TfidfVectorizer()
+tfidf_matrix = tfidf_vectorizer.fit_transform(data['v2'])
+
+# Label Encoding
+data['v1'] = data['v1'].map({'ham': 0, 'spam': 1})
+
+# Create a Random Forest classifier
+rf_classifier = RandomForestClassifier(random_state=42)
+rf_classifier.fit(tfidf_matrix, data['v1'])
 
-# Thresholding or Binarization
-def thresholding(src):
-    return cv2.threshold(src,127,255, cv2.THRESH_TOZERO)[1]
-def ocr_with_easy(img):
-    gray_scale_image=get_grayscale(img)
-    thresholding(gray_scale_image)
-    cv2.imwrite('image.png',gray_scale_image)
-    reader = easyocr.Reader(['th','en'])
-    bounds = reader.readtext('image.png',paragraph="False",detail = 0)
-    bounds = ''.join(bounds)
-    return bounds
-        
 """
-Generate OCR
+OCR and Spam Classification Pipeline
 """
-def generate_ocr(Method,img):
+def ocr_and_classify_spam(img):
+    # Step 1: Extract text from the image using EasyOCR
+    extracted_text = ocr_with_easy(img)
     
-    text_output = ''
-    if (img).any():
-        add_csv = []
-        image_id = 1
-        print("Method___________________",Method)
-        if Method == 'EasyOCR':
-            text_output = ocr_with_easy(img)
-        if Method == 'KerasOCR':
-            text_output = ocr_with_keras(img)
-        if Method == 'PaddleOCR':
-            text_output = ocr_with_paddle(img)
-       
-        try:
-            flag(Method,text_output,img)
-        except Exception as e:
-            print(e)
-        return text_output
+    # Step 2: Preprocess and classify the extracted text
+    if extracted_text:
+        processed_text = preprocess_text(extracted_text)
+        input_tfidf = tfidf_vectorizer.transform([processed_text])
+        prediction = rf_classifier.predict(input_tfidf)
+        spam_result = "SPAM" if prediction[0] == 1 else "NOT SPAM"
     else:
-        raise gr.Error("Please upload an image!!!!")
-    
-    # except Exception as e:
-    #     print("Error in ocr generation ==>",e)
-    #     text_output = "Something went wrong"
-    # return text_output
-    
+        spam_result = "No text found in the image."
+        
+    return extracted_text, spam_result
 
 """
-Create user interface for OCR demo
+Create User Interface with Gradio
 """
-
-# image = gr.Image(shape=(300, 300))
 image = gr.Image()
-method = gr.Radio(["PaddleOCR","EasyOCR", "KerasOCR"],value="PaddleOCR")
-output = gr.Textbox(label="Output")
+output_text = gr.Textbox(label="Extracted Text")
+output_classification = gr.Textbox(label="Spam Classification")
 
 demo = gr.Interface(
-    generate_ocr,
-    [method,image],
-    output,
-    title="Optical Character Recognition",
-    css=".gradio-container {background-color: lightgray} #radio_div {background-color: #FFD8B4; font-size: 40px;}",
-    article = """<p style='text-align: center;'>Feel free to give us your thoughts on this demo and please contact us at 
-                    <a href="mailto:[email protected]" target="_blank">[email protected]</a> 
-                    <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com" target="_blank">Pragnakalp Techlabs</a></p>"""
-    
-
+    fn=ocr_and_classify_spam,
+    inputs=image,
+    outputs=[output_text, output_classification],
+    title="OCR and Spam Classifier",
+    description="Upload an image with text. The text will be extracted using EasyOCR and then classified as SPAM or NOT SPAM.",
+    css=".gradio-container {background-color: lightgray}"
 )
-# demo.launch(enable_queue = False)
-demo.launch()
+
+demo.launch()