Update main.py

main.py

@@ -3,6 +3,7 @@ import os
 import cv2
 import imutils
 import numpy as np
+from tensorflow.keras.preprocessing.image import load_img, img_to_array
 from tensorflow.keras.models import load_model
 from werkzeug.utils import secure_filename
 import tempfile
@@ -29,41 +30,6 @@ def allowed_file(filename):
     """Check if the file is a valid image format (png, jpg, jpeg)."""
     return '.' in filename and filename.rsplit('.', 1)[1] in ALLOWED_EXTENSIONS
 
-def preprocess_imgs(set_name, img_size):
-    """
-    Preprocess images by resizing them to the target size (128x128) 
-    and applying appropriate resizing techniques.
-    """
-    set_new = []
-    for img in set_name:
-        img = cv2.resize(img, dsize=img_size, interpolation=cv2.INTER_CUBIC)  # Resize image
-        set_new.append(img)
-    return np.array(set_new)
-
-def crop_imgs(set_name, add_pixels_value=0):
-    """
-    Crop the region of interest (ROI) in the image for brain tumor detection.
-    """
-    set_new = []
-    for img in set_name:
-        gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
-        gray = cv2.GaussianBlur(gray, (5, 5), 0)
-        thresh = cv2.threshold(gray, 45, 255, cv2.THRESH_BINARY)[1]
-        thresh = cv2.erode(thresh, None, iterations=2)
-        thresh = cv2.dilate(thresh, None, iterations=2)
-        cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
-        cnts = imutils.grab_contours(cnts)
-        c = max(cnts, key=cv2.contourArea)
-        extLeft = tuple(c[c[:, :, 0].argmin()][0])
-        extRight = tuple(c[c[:, :, 0].argmax()][0])
-        extTop = tuple(c[c[:, :, 1].argmin()][0])
-        extBot = tuple(c[c[:, :, 1].argmax()][0])
-        ADD_PIXELS = add_pixels_value
-        new_img = img[extTop[1]-ADD_PIXELS:extBot[1]+ADD_PIXELS,
-                      extLeft[0]-ADD_PIXELS:extRight[0]+ADD_PIXELS].copy()
-        set_new.append(new_img)
-    return np.array(set_new)
-
 @app.route('/')
 def brain_tumor():
     """Render the HTML form for the user to upload an image."""
@@ -89,21 +55,16 @@ def resultbt():
             flash('Image successfully uploaded and displayed below')
 
             try:
-                # Process the image
-                img = cv2.imread(temp_file.name)
-                img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  # Convert to RGB
-                img = crop_imgs([img])
-                img = img.reshape(img.shape[1:])  # Reshape to (height, width, channels)
-                img = preprocess_imgs([img], (128, 128))  # Resize to (128, 128, 3)
-
-                # Ensure the input shape matches the model's expectation
-                img = img[0]  # Remove unnecessary extra dimension
-                img = np.expand_dims(img, axis=0)  # Add batch dimension to match (1, 128, 128, 3)
+                # Load and preprocess the image
+                img = load_img(temp_file.name, target_size=(128, 128))  # Resize image to match model's input size
+                img_array = img_to_array(img)  # Convert image to array
+                img_array = np.expand_dims(img_array, axis=0) / 255.0  # Normalize image and add batch dimension
 
                 # Make prediction
-                pred = braintumor_model.predict(img)
-                prediction = 'Tumor Detected' if pred[0][0] >= 0.5 else 'No Tumor Detected'
-                confidence_score = float(pred[0][0])
+                pred = braintumor_model.predict(img_array)
+                prediction = pred[0][0]
+                confidence = prediction if prediction > 0.5 else 1 - prediction  # Calculate confidence
+                predicted_class = 'Tumor Detected' if prediction > 0.5 else 'No Tumor Detected'  # Determine class based on threshold
 
                 # Prepare data for MongoDB
                 result = {
@@ -114,8 +75,8 @@ def resultbt():
                     "gender": gender,
                     "age": age,
                     "image_name": filename,
-                    "prediction": prediction,
-                    "confidence_score": confidence_score,
+                    "prediction": predicted_class,
+                    "confidence_score": confidence,
                     "timestamp": datetime.utcnow()
                 }
 
@@ -123,7 +84,7 @@ def resultbt():
                 collection.insert_one(result)
 
                 # Return the result to the user
-                return render_template('resultbt.html', filename=filename, fn=firstname, ln=lastname, age=age, r=prediction, gender=gender)
+                return render_template('resultbt.html', filename=filename, fn=firstname, ln=lastname, age=age, r=predicted_class, gender=gender)
             finally:
                 os.remove(temp_file.name)  # Ensure temporary file is deleted
         else: