Update app.py

app.py

@@ -36,29 +36,31 @@ def predict(image):
         # Unpack the normalized bounding box (x_min, y_min, x_max, y_max)
         x_min, y_min, x_max, y_max = box
 
-        # Calculate width and height (denormalize)
-        width = x_max - x_min
-        height = y_max - y_min
-
-        # Filter for columns based on aspect ratio (height > width)
-        if height / width > 2:  # A threshold for vertical aspect ratio (adjust if needed)
-            # Convert normalized coordinates to pixel values
-            left = int(x_min * image_width)
-            top = int(y_min * image_height)
-            right = int(x_max * image_width)
-            bottom = int(y_max * image_height)
-
-            # Crop the image to the bounding box area
-            cropped_image = image.crop((left, top, right, bottom))
-
-            # Perform OCR on the cropped image
-            ocr_text = pytesseract.image_to_string(cropped_image)
-
-            # Append OCR result for this box
-            ocr_results.append({
-                "box": [left, top, right, bottom],
-                "text": ocr_text
-            })
+        # Ensure the coordinates are valid (x_max > x_min, y_max > y_min)
+        if x_min >= x_max or y_min >= y_max:
+            continue
+
+        # Convert normalized coordinates to pixel values
+        left = max(int(x_min * image_width), 0)
+        top = max(int(y_min * image_height), 0)
+        right = min(int(x_max * image_width), image_width)
+        bottom = min(int(y_max * image_height), image_height)
+
+        # Double-check that the coordinates are valid after conversion
+        if right <= left or bottom <= top:
+            continue
+
+        # Crop the image to the bounding box area
+        cropped_image = image.crop((left, top, right, bottom))
+
+        # Perform OCR on the cropped image
+        ocr_text = pytesseract.image_to_string(cropped_image)
+
+        # Append OCR result for this box
+        ocr_results.append({
+            "box": [left, top, right, bottom],
+            "text": ocr_text
+        })
 
     # Return OCR results
     return {"ocr_results": ocr_results}