Amélioration résultat console

main.py

@@ -3,7 +3,7 @@ from src.pipeline import ObjectDetectionPipeline
 from src.classifiers.bayesian import BayesianClassifier
 
 # Définissez le mode d'analyse ici : "plan" ou "page"
-analysis_mode = "plan"
+analysis_mode = "page"
 
 if __name__ == "__main__":
     # Configuration basée sur le mode
@@ -52,8 +52,12 @@ if __name__ == "__main__":
     # Détection et classification des objets
     print("Détection et classification des objets...")
     try:
-        class_counts, detected_objects = pipeline.detect_and_classify_objects()
-        print("Classes détectées :", class_counts)
+        class_counts, detected_objects, total_objects, ignored_objects, identified_objects = pipeline.detect_and_classify_objects()
+        print(f"Classes détectées : {class_counts}")
+        print("Résumé des objets :")
+        print(f"- Objets totaux : {total_objects}")
+        print(f"- Objets identifiés : {identified_objects}")
+        print(f"- Objets ignorés : {ignored_objects}")
     except Exception as e:
         print(f"Erreur lors de la détection/classification : {e}")
         exit(1)

src/classifiers/bayesian.py

@@ -64,7 +64,6 @@ class BayesianClassifier:
 
             features = np.array(features)
             if features.size == 0:
-                print("No features extracted.")
                 return np.array([])
 
             # Normalize features
@@ -140,7 +139,6 @@ class BayesianClassifier:
         try:
             features = self.extract_features(image)
             if features.size == 0:
-                print("Empty features, skipping prediction.")
                 return None
 
             posteriors = {}

src/pipeline.py

@@ -59,9 +59,15 @@ class ObjectDetectionPipeline:
 
         class_counts = defaultdict(int)
         detected_objects = []
+        total_objects = 0
+        ignored_objects = 0
+        identified_objects = 0
 
         for contour in contours:
+            total_objects += 1  # Compteur total des objets
+
             if cv2.contourArea(contour) < self.min_contour_area:
+                ignored_objects += 1
                 continue
 
             x, y, w, h = cv2.boundingRect(contour)
@@ -69,13 +75,14 @@ class ObjectDetectionPipeline:
 
             predicted_class = self.model.predict(letter_image, threshold=self.threshold)
             if predicted_class is None:
-                print("Object ignored due to low resemblance.")
+                ignored_objects += 1
                 continue
 
+            identified_objects += 1
             class_counts[predicted_class] += 1
             detected_objects.append((x, y, w, h, predicted_class))
 
-        return dict(sorted(class_counts.items())), detected_objects
+        return dict(sorted(class_counts.items())), detected_objects, total_objects, ignored_objects, identified_objects
 
     def save_results(self, class_counts, detected_objects):
         binary_output_path = os.path.join(self.output_dir, "binary_image.jpg")