cleaned some code, redundant tasks and old code removed

app.py

@@ -13,12 +13,6 @@ import matplotlib.pyplot as plt
 
 # Initialize PaddleOCR model
 ocr = PaddleOCR(use_angle_cls=True, lang='en')
-# Define the class names based on your dataset
-class_names = [
-    'fresh_apple', 'fresh_banana', 'fresh_bitter_gourd', 'fresh_capsicum',
-    'fresh_orange', 'fresh_tomato', 'stale_apple', 'stale_banana',
-    'stale_bitter_gourd', 'stale_capsicum', 'stale_orange', 'stale_tomato'
-]
 
 # Team details
 team_members = [
@@ -77,6 +71,8 @@ def make_image_circular1(img, size=(256, 256)):
     output = ImageOps.fit(img, mask.size, centering=(0.5, 0.5))
     output.putalpha(mask)  # Apply the mask as transparency
     return output
+
+
 # Function to check if a file exists
 def file_exists(file_path):
     return os.path.isfile(file_path)
@@ -332,70 +328,6 @@ elif app_mode == "Task 1":
     else:
         st.write("Please upload images to extract product details.")
 
-elif app_mode == "Task 2":
-    st.write("## Task 2:📅 Expiry Date Validation ✅")
-    st.write("Use OCR to get expiry and MRP details printed on items.")
-    # File uploader for images (supports multiple files)
-    uploaded_files = st.file_uploader("Upload images of products containing expiry date", type=["jpeg", "png", "jpg"], accept_multiple_files=True)
-
-    if uploaded_files:
-        st.write("### Uploaded Images in Circular Format:")
-        circular_images = []
-
-        for uploaded_file in uploaded_files:
-            img = Image.open(uploaded_file)
-            circular_img = make_image_circular(img)  # Create circular images
-            circular_images.append(circular_img)
-
-        # Display the circular images in a matrix/grid format
-        display_images_in_grid(circular_images, max_images_per_row=4)
-
-        # Function to simulate loading process with a progress bar
-        def simulate_progress():
-            progress_bar = st.progress(0)
-            for percent_complete in range(100):
-                time.sleep(0.02)
-                progress_bar.progress(percent_complete + 1)
-
-        for idx, uploaded_file in enumerate(uploaded_files):
-            image = Image.open(uploaded_file)
-            img_array = np.array(image)
-            result = ocr.ocr(img_array, cls=True)
-
-            if result and result[0]:
-                # Extract recognized texts
-                recognized_texts = [line[1][0] for line in result[0]]
-
-                # Clean up recognized texts by removing extra spaces and standardizing formats
-                cleaned_texts = []
-                for text in recognized_texts:
-                    cleaned_text = re.sub(r'\s+', ' ', text.strip())  # Replace multiple spaces with a single space
-                    cleaned_text = cleaned_text.replace('.', '').replace(',', '')  # Remove dots and commas for date detection
-                    cleaned_texts.append(cleaned_text)
-
-                # Extract dates from recognized texts
-                extracted_dates, date_texts, date_boxes, date_scores = extract_dates_with_dateparser(cleaned_texts, result)
-
-                if extracted_dates:
-                    # Display extracted dates
-                    st.write("**Extracted Dates**:")
-                    for date, text in zip(extracted_dates, date_texts):
-                        st.write(f"Detected Date: **{date}**, Original Text: *{text}*")
-                else:
-                    st.write("No valid dates found in the image.")
-
-                # Option to visualize the bounding boxes on the image
-                if st.checkbox(f"Show image with highlighted dates for {uploaded_file.name}", key=f"highlight_{idx}"):
-                    # Draw the OCR results on the image
-                    image_with_boxes = draw_ocr(image, date_boxes, date_texts, date_scores,font_path='CedarvilleCursive-Regular.ttf')  # Removed font path
-
-                    # Display the image with highlighted boxes
-                    plt.figure(figsize=(10, 10))
-                    plt.imshow(image_with_boxes)
-                    plt.axis('off')  # Hide axes
-                    st.pyplot(plt)
-            else:
-                st.write("No text detected in the image.")
 
 
 def make_image_circular1(image):
@@ -425,158 +357,6 @@ def display_images_in_grid1(images, max_images_per_row=4):
             if idx < len(cols):
                 cols[idx].image(img, use_column_width=True)
 
-# Initialize your Streamlit app
-if app_mode == "Task 3":
-    st.write("## Task 3: Image Recognition 📸 and IR-Based Counting 📊")
-    
-    # File uploader for images (supports multiple files)
-    uploaded_files = st.file_uploader("Upload images of fruits, vegetables, or products for brand recognition and freshness detection", 
-                                      type=["jpeg", "png", "jpg"], accept_multiple_files=True)
-    if uploaded_files:
-        st.write("### Uploaded Images:")
-        # Load the pre-trained YOLOv8 model
-        model = YOLO('yolov9c.pt')  # Adjust path to your YOLO model if needed
-
-        # Initialize a dictionary to store counts of detected products
-        product_count_dict = {}
-        circular_images = []
-        images=[]
-
-        for uploaded_file in uploaded_files:
-            img = Image.open(uploaded_file)
-            circular_img = make_image_circular(img)  # Create circular images
-            circular_images.append(circular_img)
-            images.append(img)
-
-        # Display the circular images in a matrix/grid format
-        display_images_in_grid(circular_images, max_images_per_row=4)
-
-        detected_images = []
-        
-        for idx, image in enumerate(images):
-            # Run object detection
-            results = model(image)
-
-            # Initialize counts for this image
-            image_counts = {}
-
-            # Display results with bounding boxes
-            for result in results:
-                img_with_boxes = result.plot()  # Get image with bounding boxes
-                detected_images.append(make_image_circular(image.resize((150, 150))))  # Resize and make circular
-                
-                # Display detected object counts per class
-                counts = result.boxes.cls.tolist()  # Extract class IDs
-                class_counts = {int(cls): counts.count(cls) for cls in set(counts)}
-                
-                # Update the image counts for this image
-                for cls_id, count in class_counts.items():
-                    product_name = result.names[cls_id]  # Get the product name from class ID
-                    image_counts[product_name] = count
-                
-                # Aggregate counts into the main product count dictionary
-                for product, count in image_counts.items():
-                    if product in product_count_dict:
-                        product_count_dict[product] += count
-                    else:
-                        product_count_dict[product] = count
-
-            # Option to visualize the bounding boxes on the image
-            if st.checkbox(f"Show image with highlighted boxes for image {idx + 1}", key=f"checkbox_{idx}"):
-                st.image(img_with_boxes, caption="Image with Highlighted Boxes", use_column_width=True)
-
-        # Display the total counts as a bar chart
-        st.write("### Total Product Counts Across All Images:")
-        if product_count_dict:
-            product_count_df = pd.DataFrame(product_count_dict.items(), columns=["Product", "Count"])
-            st.bar_chart(product_count_df.set_index("Product"))
-        else:
-            st.write("No products detected.")
-
-elif app_mode == "Task 4":
-    st.write("## Task 4: 🍏 Fruit and Vegetable Freshness Detector 🍅")
-    # Load the trained model
-    try:
-        model = tf.keras.models.load_model('fruit_freshness_model.h5')  # Using TensorFlow to load the model
-        st.success("Model loaded successfully!")
-    except Exception as e:
-        st.error(f"Error loading model: {e}")
-    
-    # File uploader for images (supports multiple files)
-    uploaded_files = st.file_uploader("Upload images of fruits/vegetables", type=["jpeg", "png", "jpg"], accept_multiple_files=True)
-
-    if uploaded_files:
-        st.write("### Uploaded Images in Circular Format:")
-        circular_images = []
-        images=[]
-
-        for uploaded_file in uploaded_files:
-            img = Image.open(uploaded_file)
-            circular_img = make_image_circular(img)  # Create circular images
-            circular_images.append(circular_img)
-            images.append(img)
-
-        # Display the circular images in a matrix/grid format
-        display_images_in_grid(circular_images, max_images_per_row=4)
-
-        # Function to simulate loading process with a progress bar
-        def simulate_progress():
-            progress_bar = st.progress(0)
-            for percent_complete in range(100):
-                time.sleep(0.02)
-                progress_bar.progress(percent_complete + 1)
-
-        # Create an empty DataFrame to hold the image name and prediction results
-        results_df = pd.DataFrame(columns=["Image", "Prediction"])
-
-        # Create a dictionary to count the occurrences of each class
-        class_counts = {class_name: 0 for class_name in class_names}
-
-        # Button to initiate predictions
-        if st.button("Run Prediction"):
-            # Display progress bar
-            simulate_progress()
-
-            for idx, img in enumerate(images):  # Use circular images for predictions
-                img_array = preprocess_image(img.convert('RGB'))  # Convert to RGB
-
-                try:
-                    # Perform the prediction
-                    prediction = model.predict(img_array)
-
-                    # Get the class with the highest probability
-                    result = class_names[np.argmax(prediction)]
-                    st.success(f'Prediction for Image {idx + 1}: **{result}**')
-
-                    # Increment the class count
-                    class_counts[result] += 1
-
-                    # Add the result to the DataFrame
-                    result_data = pd.DataFrame({"Image": [uploaded_files[idx].name], "Prediction": [result]})
-                    results_df = pd.concat([results_df, result_data], ignore_index=True)
-
-                except Exception as e:
-                    st.error(f"Error occurred during prediction: {e}")
-
-            # Display class distribution as a bar chart
-            st.write("### Class Distribution:")
-            class_counts_df = pd.DataFrame(list(class_counts.items()), columns=['Class', 'Count'])
-            st.bar_chart(class_counts_df.set_index('Class'))
-
-            # Option to download the prediction results as a CSV file
-            st.write("### Download Results:")
-            csv = results_df.to_csv(index=False).encode('utf-8')
-            st.download_button(
-                label="Download prediction results as CSV",
-                data=csv,
-                file_name='prediction_results.csv',
-                mime='text/csv',
-            )
-
-            # Display the dataframe after the graph
-            st.write("### Prediction Data:")
-            st.dataframe(results_df)
-
 # Footer with animation
 st.markdown(""" 
     <style>