modified

app.py

@@ -21,7 +21,130 @@ from sklearn.preprocessing import StandardScaler  # Standardization of image dat
 
 # Load Gemini API key from Streamlit Secrets configuration
 api_key = st.secrets["gemini"]["api_key"]  # Get API key from Streamlit secrets
-genai.configure(api_key=api_key)  # Configure the Gemini API with the API key
+genai.configure(api_key=api_key)  # Configure the Gemini API with the API keyimport streamlit as st
+import numpy as np
+import google.generativeai as genai
+import matplotlib.pyplot as plt
+
+from sklearn.ensemble import RandomForestClassifier   
+from sklearn.linear_model import LogisticRegression   
+from skimage.filters import sobel  
+from skimage.segmentation import watershed  
+from skimage.feature import canny, hog  
+from skimage.color import rgb2gray  
+from skimage import io  
+from sklearn.preprocessing import StandardScaler  
+from sklearn.metrics import accuracy_score
+
+# Load Gemini API key
+api_key = st.secrets["gemini"]["api_key"]
+genai.configure(api_key=api_key)
+MODEL_ID = "gemini-1.5-flash"
+gen_model = genai.GenerativeModel(MODEL_ID)
+
+def explain_ai(prompt):
+    try:
+        response = gen_model.generate_content(prompt)
+        return response.text
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Streamlit app with multiple pages
+st.set_page_config(page_title="Imaize: Smart Image Analyzer with XAI")
+
+# Sidebar navigation
+st.sidebar.title("Navigation")
+page = st.sidebar.radio("Go to", ["Home", "Edge Detection", "Segmentation", "Feature Extraction", "AI Classification"])
+
+# Home Page
+if page == "Home":
+    st.title("Imaize: Smart Image Analyzer with XAI")
+    st.markdown("""
+    **Welcome to Imaize!** This app allows you to analyze images using AI-powered techniques:
+    - **Edge Detection**
+    - **Image Segmentation**
+    - **Feature Extraction**
+    - **AI Classification**
+    
+    Upload an image and explore how AI explains the techniques!
+    """)
+    uploaded_file = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])
+    if uploaded_file is not None:
+        image = io.imread(uploaded_file)
+        if image.shape[-1] == 4:
+            image = image[:, :, :3]
+        gray = rgb2gray(image)
+        st.image(image, caption="Uploaded Image", use_container_width=True)
+        st.session_state["gray"] = gray  # Store for use in other pages
+
+# Edge Detection Page
+elif page == "Edge Detection":
+    st.title("Edge Detection")
+    gray = st.session_state.get("gray")
+    if gray is not None:
+        edge_method = st.selectbox("Select Edge Detection Method", ["Canny", "Sobel"])
+        edges = canny(gray) if edge_method == "Canny" else sobel(gray)
+        st.image(edges, caption=f"{edge_method} Edge Detection", use_container_width=True)
+        st.text_area("Explanation", explain_ai(f"Explain how {edge_method} edge detection works in computer vision."), height=300)
+    else:
+        st.warning("Please upload an image on the Home page.")
+
+# Segmentation Page
+elif page == "Segmentation":
+    st.title("Image Segmentation")
+    gray = st.session_state.get("gray")
+    if gray is not None:
+        seg_method = st.selectbox("Select Segmentation Method", ["Watershed", "Thresholding"])
+        if seg_method == "Watershed":
+            elevation_map = sobel(gray)
+            markers = np.zeros_like(gray)
+            markers[gray < 0.3] = 1
+            markers[gray > 0.7] = 2
+            segmented = watershed(elevation_map, markers.astype(np.int32))
+        else:
+            threshold_value = st.slider("Choose threshold value", 0, 255, 127)
+            segmented = (gray > (threshold_value / 255)).astype(np.uint8) * 255
+        st.image(segmented, caption=f"{seg_method} Segmentation", use_container_width=True)
+        st.text_area("Explanation", explain_ai(f"Explain how {seg_method} segmentation works in image processing."), height=300)
+    else:
+        st.warning("Please upload an image on the Home page.")
+
+# Feature Extraction Page
+elif page == "Feature Extraction":
+    st.title("HOG Feature Extraction")
+    gray = st.session_state.get("gray")
+    if gray is not None:
+        fd, hog_image = hog(gray, pixels_per_cell=(8, 8), cells_per_block=(2, 2), visualize=True)
+        st.image(hog_image, caption="HOG Features", use_container_width=True)
+        st.text_area("Explanation", explain_ai("Explain how Histogram of Oriented Gradients (HOG) feature extraction works."), height=300)
+    else:
+        st.warning("Please upload an image on the Home page.")
+
+# AI Classification Page
+elif page == "AI Classification":
+    st.title("AI Classification")
+    gray = st.session_state.get("gray")
+    if gray is not None:
+        model_choice = st.selectbox("Select AI Model", ["Random Forest", "Logistic Regression"])
+        flat_image = gray.flatten().reshape(-1, 1)
+        labels = (flat_image > 0.5).astype(int).flatten()
+        ai_model = RandomForestClassifier(n_jobs=1) if model_choice == "Random Forest" else LogisticRegression()
+        scaler = StandardScaler()
+        flat_image_scaled = scaler.fit_transform(flat_image)
+        ai_model.fit(flat_image_scaled, labels)
+        predictions = ai_model.predict(flat_image_scaled).reshape(gray.shape)
+        predictions = (predictions * 255).astype(np.uint8)
+        accuracy = accuracy_score(labels, ai_model.predict(flat_image_scaled))
+        st.image(predictions, caption=f"{model_choice} Pixel Classification", use_container_width=True)
+        st.text_area("Explanation", explain_ai(f"Explain how {model_choice} is used for image classification."), height=300)
+        st.write(f"### Accuracy: {accuracy:.2f}")
+        fig, ax = plt.subplots()
+        ax.bar(["Accuracy"], [accuracy], color='blue')
+        ax.set_ylim([0, 1])
+        st.pyplot(fig)
+    else:
+        st.warning("Please upload an image on the Home page.")
+
 
 MODEL_ID = "gemini-1.5-flash"  # Specify the model ID for Gemini
 gen_model = genai.GenerativeModel(MODEL_ID)  # Initialize the Gemini model