Update app.py

app.py

@@ -2,7 +2,10 @@ import gradio as gr
 import logging
 from roboflow import Roboflow
 from PIL import Image, ImageDraw, ImageFont, ImageFilter
+import cv2
+import numpy as np
 import os
+from math import atan2, degrees
 
 # Configure logging
 logging.basicConfig(
@@ -20,6 +23,36 @@ PROJECT_NAME = "model_verification_project"
 VERSION_NUMBER = 2
 FONT_PATH = "./STEVEHANDWRITING-REGULAR.TTF"
 
+# Function to detect paper angle within bounding box
+def detect_paper_angle(image, bounding_box):
+    x1, y1, x2, y2 = bounding_box
+
+    # Crop the region of interest (ROI) based on the bounding box
+    roi = np.array(image)[y1:y2, x1:x2]
+
+    # Convert ROI to grayscale
+    gray = cv2.cvtColor(roi, cv2.COLOR_RGBA2GRAY)
+
+    # Apply edge detection
+    edges = cv2.Canny(gray, 50, 150)
+
+    # Detect lines using Hough Line Transformation
+    lines = cv2.HoughLinesP(edges, 1, np.pi / 180, threshold=100, minLineLength=50, maxLineGap=10)
+
+    if lines is not None:
+        # Find the longest line (most prominent edge)
+        longest_line = max(lines, key=lambda line: np.linalg.norm((line[0][2] - line[0][0], line[0][3] - line[0][1])))
+        x1, y1, x2, y2 = longest_line[0]
+
+        # Calculate the angle of the line relative to the horizontal axis
+        dx = x2 - x1
+        dy = y2 - y1
+        angle = degrees(atan2(dy, dx))
+
+        return angle  # Angle of the paper
+    else:
+        return 0  # Default to no rotation if no lines are found
+
 # Function to process image and overlay text
 def process_image(image, text):
     try:
@@ -54,9 +87,13 @@ def process_image(image, text):
 
             logging.debug(f"Bounding box coordinates: ({x1}, {y1}), ({x2}, {y2}).")
 
+            # Detect the angle of the paper
+            angle = detect_paper_angle(np.array(image), (x1, y1, x2, y2))
+            logging.debug(f"Detected paper angle: {angle} degrees.")
+
             # Calculate padded bounding box dimensions
-            padding_x = int((x2 - x1) * 0.2)  # 10% padding horizontally
-            padding_y = int((y2 - y1) * 0.2)  # 10% padding vertically
+            padding_x = int((x2 - x1) * 0.1)  # 10% padding horizontally
+            padding_y = int((y2 - y1) * 0.1)  # 10% padding vertically
 
             x1_padded = x1 + padding_x
             y1_padded = y1 + padding_y
@@ -94,14 +131,15 @@ def process_image(image, text):
                     total_text_height = len(lines) * line_height
                 return font, line_height
 
-            # Split and wrap text to fit within the bounding box
+            # Improved text wrapping logic to fit within the bounding box
             words = text.split()
             lines = []
             current_line = ""
+
             for word in words:
                 test_line = f"{current_line} {word}".strip()
                 bbox = text_draw.textbbox((0, 0), test_line, font=font)
-                if bbox[2] - bbox[0] <= box_width * 0.95:
+                if bbox[2] - bbox[0] <= box_width * 0.9:
                     current_line = test_line
                 else:
                     lines.append(current_line)
@@ -122,12 +160,11 @@ def process_image(image, text):
 
             logging.debug(f"Drew text within bounding box: ({x1_padded}, {y1_padded}), ({x2_padded}, {y2_padded}).")
 
-            # Apply slight blur to the text layer
-            blurred_text_layer = text_layer.filter(ImageFilter.GaussianBlur(radius=1.0))
-            logging.debug("Applied Gaussian blur to the text layer.")
+            # Apply rotation to align with the paper's angle
+            rotated_text_layer = text_layer.rotate(-angle, resample=Image.BICUBIC, center=(x1 + box_width / 2, y1 + box_height / 2))
 
-            # Composite the blurred text onto the original image
-            pil_image = Image.alpha_composite(pil_image, blurred_text_layer)
+            # Composite the rotated text layer onto the original image
+            pil_image = Image.alpha_composite(pil_image, rotated_text_layer)
             logging.debug("Composite the text layer onto the original image.")
 
         # Save and return output image path
@@ -182,3 +219,4 @@ if __name__ == "__main__":
 
 
 
+