Update app.py

app.py

@@ -16,7 +16,7 @@ def load_model():
 processor, model = load_model()
 
 # Helper function to preprocess the image and detect lines
-def detect_lines(image):
+def detect_lines(image, min_height=20, min_width=100):
     # Convert the PIL image to a NumPy array
     image_np = np.array(image)
 
@@ -26,23 +26,33 @@ def detect_lines(image):
     # Apply binary thresholding
     _, binary = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
 
+    # Dilate to merge nearby text
+    kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
+    dilated = cv2.dilate(binary, kernel, iterations=1)
+
     # Find contours
-    contours, _ = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+    contours, _ = cv2.findContours(dilated, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
 
     # Sort contours top-to-bottom
     bounding_boxes = [cv2.boundingRect(c) for c in contours]
     bounding_boxes = sorted(bounding_boxes, key=lambda b: b[1])  # Sort by y-coordinate
 
+    # Filter out small contours and merge nearby ones
+    filtered_boxes = []
+    for x, y, w, h in bounding_boxes:
+        if h >= min_height and w >= min_width:  # Filter small boxes
+            filtered_boxes.append((x, y, w, h))
+
+    # Extract individual lines as images
     line_images = []
-    for (x, y, w, h) in bounding_boxes:
-        # Extract each line as a separate image
+    for (x, y, w, h) in filtered_boxes:
         line = image_np[y:y+h, x:x+w]
         line_images.append(line)
 
     return line_images
 
 # Streamlit app
-st.title("MMSai Meeeting Image Tools 1.0")
+st.title("Multiline Handwritten OCR with Hugging Face and OpenCV")
 uploaded_file = st.file_uploader("Upload an Image (JPG, JPEG, PNG)", type=["jpg", "jpeg", "png"])
 
 if uploaded_file is not None:
@@ -54,7 +64,7 @@ if uploaded_file is not None:
         st.write("Processing the image...")
 
         # Detect lines in the image
-        line_images = detect_lines(image)
+        line_images = detect_lines(image, min_height=30, min_width=100)
         st.write(f"Detected {len(line_images)} lines in the image.")
 
         # Perform OCR on each detected line