Update app.py

app.py

@@ -4,7 +4,8 @@
 # from keras.models import load_model
 # import numpy as np
 
-
+# # Sidebar controls
+# st.sidebar.title("Canvas Settings")
 # drawing_mode = st.sidebar.selectbox("Drawing tool:", ("freedraw", "line", "rect", "circle", "transform"))
 # stroke_width = st.sidebar.slider("Stroke width: ", 1, 25, 10)
 # stroke_color = st.sidebar.color_picker("Stroke color hex: ", "#000000")  # black
@@ -12,35 +13,56 @@
 # bg_image = st.sidebar.file_uploader("Background image:", type=["png", "jpg"])
 # realtime_update = st.sidebar.checkbox("Update in realtime", True)
 
+# # Load model with caching
 # @st.cache_resource
 # def load_mnist_model():
 #     return load_model("mnist_model.keras")
 
 # model = load_mnist_model()
 
-# canvas_result = st_canvas(
-#     fill_color="rgba(255, 165, 0, 0.3)",
-#     stroke_width=stroke_width,
-#     stroke_color=stroke_color,
-#     background_color=bg_color,
-#     update_streamlit=realtime_update,
-#     height=280,
-#     width=280,
-#     drawing_mode=drawing_mode,
-#     key="canvas",
-# )
+# st.title("🖌️ Mindist: Draw a Number, Predict Instantly")
+
+# # Create a two-column layout
+# col1, col2 = st.columns([1, 1])
+
+# with col1:
+#     st.subheader("Draw Here 👇")
+#     canvas_result = st_canvas(
+#         fill_color="rgba(255, 165, 0, 0.3)",
+#         stroke_width=stroke_width,
+#         stroke_color=stroke_color,
+#         background_color=bg_color,
+#         update_streamlit=realtime_update,
+#         height=280,
+#         width=280,
+#         drawing_mode=drawing_mode,
+#         key="canvas",
+#     )
+
+# with col2:
+#     if canvas_result.image_data is not None:
+#         st.subheader("Original Drawing")
+#         st.image(canvas_result.image_data, use_column_width=True)
 
+# # Below the two columns: Show preprocessing and prediction
 # if canvas_result.image_data is not None:
-#     st.image(canvas_result.image_data, caption="Original Drawing")
+#     st.markdown("---")
+#     st.subheader("Preprocessed Image & Prediction")
+    
 #     img = cv2.cvtColor(canvas_result.image_data.astype("uint8"), cv2.COLOR_RGBA2GRAY)
-#     img = 255 - img
+#     img = 255 - img  # Invert colors
 #     img_resized = cv2.resize(img, (28, 28))
 #     img_normalized = img_resized / 255.0
 #     final_img = img_normalized.reshape(1, 28, 28, 1)
-#     st.image(img_resized, caption="Preprocessed (28x28)")
-#     prediction = model.predict(final_img)
-#     st.write("Prediction:", np.argmax(prediction))
-import streamlit as st
+    
+#     col3, col4 = st.columns([1, 1])
+#     with col3:
+#         st.image(img_resized, caption="28x28 Preprocessed", clamp=True, channels="GRAY")
+#     with col4:
+#         prediction = model.predict(final_img)
+#         predicted_digit = np.argmax(prediction)
+#         st.markdown(f"### 🧠 Predicted Digit: **{predicted_digit}**")
+import streamlit as st 
 import cv2
 from streamlit_drawable_canvas import st_canvas
 from keras.models import load_model
@@ -90,17 +112,30 @@ with col2:
 if canvas_result.image_data is not None:
     st.markdown("---")
     st.subheader("Preprocessed Image & Prediction")
-    
+
     img = cv2.cvtColor(canvas_result.image_data.astype("uint8"), cv2.COLOR_RGBA2GRAY)
     img = 255 - img  # Invert colors
-    img_resized = cv2.resize(img, (28, 28))
-    img_normalized = img_resized / 255.0
-    final_img = img_normalized.reshape(1, 28, 28, 1)
-    
+    _, thresh_img = cv2.threshold(img, 50, 255, cv2.THRESH_BINARY)
+
+    # Find contours of digits
+    contours, _ = cv2.findContours(thresh_img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+    contours = sorted(contours, key=lambda ctr: cv2.boundingRect(ctr)[0])  # Sort left-to-right
+
+    predictions = []
+
     col3, col4 = st.columns([1, 1])
     with col3:
-        st.image(img_resized, caption="28x28 Preprocessed", clamp=True, channels="GRAY")
+        st.image(img, caption="Thresholded Image", clamp=True, channels="GRAY")
+
     with col4:
-        prediction = model.predict(final_img)
-        predicted_digit = np.argmax(prediction)
-        st.markdown(f"### 🧠 Predicted Digit: **{predicted_digit}**")
+        for cnt in contours:
+            x, y, w, h = cv2.boundingRect(cnt)
+            if w > 5 and h > 5:  # Filter out noise/small contours
+                digit_roi = thresh_img[y:y+h, x:x+w]
+                digit_resized = cv2.resize(digit_roi, (28, 28))
+                digit_normalized = digit_resized / 255.0
+                input_img = digit_normalized.reshape(1, 28, 28, 1)
+                pred = np.argmax(model.predict(input_img))
+                predictions.append(str(pred))
+
+        st.markdown(f"### 🧠 Predicted Digits: **{''.join(predictions) if predictions else 'No digits found'}**")