nabil_oh/SignsDetectionAI
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Dernière version fonctionnelle en date.

Browse source
This commit is contained in:
yanis.bouarfa 2025-01-07 20:23:25 +01:00
parent 5e601c889e
commit 7abdb91d06
4 changed files with 117 additions and 156 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
main.py
View file

@ -1,31 +1,12 @@
import os import os
import subprocess import cv2
from src.pipeline import ObjectDetectionPipeline from src.pipeline import ObjectDetectionPipeline
from src.classifiers.bayesian import BayesianClassifier from src.classifiers.bayesian import BayesianClassifier
from collections import defaultdict from collections import defaultdict
# Définissez le mode d'analyse ici : "plan" ou "page"
analysis_mode = "plan"
if __name__ == "__main__": if __name__ == "__main__":
# Configuration basée sur le mode # Chemin vers le modèle entraîné
if analysis_mode == "plan":
dataset_path = "data/catalogueSymbol"
model_path = "models/bayesian_modelPLAN.pth"
image_path = "data/plan.png"
else:
dataset_path = "data/catalogue"
model_path = "models/bayesian_modelPAGE.pth" model_path = "models/bayesian_modelPAGE.pth"
image_path = "data/page.png"
# Lancer l'entraînement via train.py
print(f"Lancement de l'entraînement pour le mode '{analysis_mode}'...")
try:
subprocess.run(["python", "train.py", dataset_path, model_path], check=True)
print(f"Entraînement terminé et modèle sauvegardé dans {model_path}")
except subprocess.CalledProcessError as e:
print(f"Erreur lors de l'exécution de train.py : {e}")
exit(1)
# Chargement du modèle bayésien # Chargement du modèle bayésien
print(f"Chargement du modèle bayésien depuis {model_path}") print(f"Chargement du modèle bayésien depuis {model_path}")
@ -37,7 +18,8 @@ if __name__ == "__main__":
print(f"Erreur lors du chargement du modèle : {e}") print(f"Erreur lors du chargement du modèle : {e}")
exit(1) exit(1)
# Vérification de l'existence de l'image # Chemin de l'image de test
image_path = "data/page.png"
if not os.path.exists(image_path): if not os.path.exists(image_path):
print(f"L'image de test {image_path} n'existe pas.") print(f"L'image de test {image_path} n'existe pas.")
exit(1) exit(1)
@ -51,9 +33,6 @@ if __name__ == "__main__":
print("Initialisation de la pipeline...") print("Initialisation de la pipeline...")
pipeline = ObjectDetectionPipeline(image_path=image_path, model=bayesian_model, output_dir=output_dir) pipeline = ObjectDetectionPipeline(image_path=image_path, model=bayesian_model, output_dir=output_dir)
# Définition du mode (plan ou page)
pipeline.set_mode(analysis_mode)
# Chargement de l'image # Chargement de l'image
print("Chargement de l'image...") print("Chargement de l'image...")
try: try:
@ -66,7 +45,7 @@ if __name__ == "__main__":
print("Détection et classification des objets...") print("Détection et classification des objets...")
try: try:
class_counts, detected_objects = pipeline.detect_and_classify_objects() class_counts, detected_objects = pipeline.detect_and_classify_objects()
print("Classes détectées :", class_counts) print("Classes détectées :", class_counts) # Added debug info
except Exception as e: except Exception as e:
print(f"Erreur lors de la détection/classification : {e}") print(f"Erreur lors de la détection/classification : {e}")
exit(1) exit(1)

87
src/classifiers/bayesian.py
View file

@ -12,7 +12,6 @@ class BayesianClassifier:
self.feature_variances = {} self.feature_variances = {}
self.class_priors = {} self.class_priors = {}
self.classes = [] self.classes = []
self.mode = None # Défini par le main.py ("plan" ou "page")
# Initialize HOG descriptor with standard parameters # Initialize HOG descriptor with standard parameters
self.hog = cv2.HOGDescriptor( self.hog = cv2.HOGDescriptor(
@ -23,51 +22,66 @@ class BayesianClassifier:
_nbins=9 _nbins=9
) )
def set_mode(self, mode):
"""
Configure le mode d'analyse (plan ou page) et ajuste les classes autorisées.
"""
self.mode = mode
if mode == "plan":
self.classes = ['Figure1', 'Figure2', 'Figure3', 'Figure4', 'Figure5', 'Figure6']
elif mode == "page":
self.classes = ['2', 'd', 'I', 'n', 'o', 'u']
else:
raise ValueError(f"Mode inconnu : {mode}")
def extract_features(self, image): def extract_features(self, image):
"""
Extrait des caractéristiques d'une image (via HOG et normalisation).
"""
try: try:
# Convert image to grayscale
if len(image.shape) == 3 and image.shape[2] == 3: if len(image.shape) == 3 and image.shape[2] == 3:
gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
else: else:
gray_image = image gray_image = image
resized_image = cv2.resize(gray_image, (28, 28)) # Apply adaptive thresholding for better segmentation
hog_features = self.hog.compute(resized_image) binary_image = cv2.adaptiveThreshold(
gray_image, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 11, 2
)
features = hog_features.flatten() # Find contours
norm = np.linalg.norm(features) contours, _ = cv2.findContours(binary_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
return features / norm if norm > 1e-6 else features if not contours:
print("No contours found.")
return np.array([])
features = []
for contour in contours:
if cv2.contourArea(contour) < 20: # Lowered area threshold
continue
x, y, w, h = cv2.boundingRect(contour)
letter_image = gray_image[y:y + h, x:x + w]
letter_image = cv2.resize(letter_image, (28, 28))
# Compute HOG features
hog_features = self.hog.compute(letter_image)
features.append(hog_features.flatten())
features = np.array(features)
if features.size == 0:
print("No features extracted.")
return np.array([])
# Normalize features for better consistency
norms = np.linalg.norm(features, axis=1, keepdims=True)
features = features / np.where(norms > 1e-6, norms, 1)
return features
except Exception as e: except Exception as e:
print(f"Error in extract_features: {e}") print(f"Error in extract_features: {e}")
return np.array([]) return np.array([])
def train(self, dataset_path): def train(self, dataset_path):
"""
Entraîne le modèle bayésien sur un dataset structuré en sous-dossiers par classe.
"""
class_features = defaultdict(list) class_features = defaultdict(list)
total_images = 0 total_images = 0
allowed_classes = ['2', 'd', 'I', 'n', 'o', 'u'] # Modifiez selon vos besoins
for class_name in os.listdir(dataset_path): for class_name in os.listdir(dataset_path):
if class_name not in self.classes: if class_name not in allowed_classes:
continue continue
class_folder_path = os.path.join(dataset_path, class_name) class_folder_path = os.path.join(dataset_path, class_name)
if os.path.isdir(class_folder_path): if os.path.isdir(class_folder_path):
if class_name not in self.classes:
self.classes.append(class_name)
for img_name in os.listdir(class_folder_path): for img_name in os.listdir(class_folder_path):
img_path = os.path.join(class_folder_path, img_name) img_path = os.path.join(class_folder_path, img_name)
if os.path.isfile(img_path): if os.path.isfile(img_path):
@ -76,8 +90,11 @@ class BayesianClassifier:
if image is not None: if image is not None:
features = self.extract_features(image) features = self.extract_features(image)
if features.size > 0: if features.size > 0:
class_features[class_name].append(features) for feature in features:
class_features[class_name].append(feature)
total_images += 1 total_images += 1
else:
print(f"No features extracted for {img_path}")
else: else:
print(f"Failed to load image: {img_path}") print(f"Failed to load image: {img_path}")
except Exception as e: except Exception as e:
@ -93,9 +110,6 @@ class BayesianClassifier:
print("Training completed for classes:", self.classes) print("Training completed for classes:", self.classes)
def save_model(self, model_path): def save_model(self, model_path):
"""
Sauvegarde le modèle entraîné dans un fichier.
"""
model_data = { model_data = {
"feature_means": self.feature_means, "feature_means": self.feature_means,
"feature_variances": self.feature_variances, "feature_variances": self.feature_variances,
@ -108,11 +122,8 @@ class BayesianClassifier:
print(f"Model saved to {model_path}") print(f"Model saved to {model_path}")
def load_model(self, model_path): def load_model(self, model_path):
"""
Charge un modèle existant depuis un fichier.
"""
if os.path.exists(model_path): if os.path.exists(model_path):
model_data = torch.load(model_path) model_data = torch.load(model_path, weights_only=False)
self.feature_means = model_data["feature_means"] self.feature_means = model_data["feature_means"]
self.feature_variances = model_data["feature_variances"] self.feature_variances = model_data["feature_variances"]
self.class_priors = model_data["class_priors"] self.class_priors = model_data["class_priors"]
@ -121,10 +132,7 @@ class BayesianClassifier:
else: else:
print(f"No model found at {model_path}.") print(f"No model found at {model_path}.")
def predict(self, image, threshold=-65000): def predict(self, image, threshold=0.3): # Lowered threshold
"""
Prédit la classe d'une image en utilisant le modèle bayésien.
"""
try: try:
features = self.extract_features(image) features = self.extract_features(image)
if features.size == 0: if features.size == 0:
@ -144,7 +152,7 @@ class BayesianClassifier:
max_class = max(posteriors, key=posteriors.get) max_class = max(posteriors, key=posteriors.get)
max_posterior = posteriors[max_class] max_posterior = posteriors[max_class]
print(f"Class: {max_class}, Posterior: {max_posterior}") print(f"Class: {max_class}, Posterior: {max_posterior}") # Added debug info
if max_posterior < threshold: if max_posterior < threshold:
return None return None
return max_class return max_class
@ -153,9 +161,6 @@ class BayesianClassifier:
return None return None
def visualize(self): def visualize(self):
"""
Visualise les moyennes des caractéristiques par classe.
"""
if not self.classes: if not self.classes:
print("No classes to visualize.") print("No classes to visualize.")
return return

56
src/pipeline.py
View file

@ -6,9 +6,7 @@ from collections import defaultdict
class ObjectDetectionPipeline: class ObjectDetectionPipeline:
def __init__(self, image_path, model=None, output_dir="output", min_contour_area=20, binary_threshold=None): def __init__(self, image_path, model=None, output_dir="output", min_contour_area=20, binary_threshold=None):
""" # Initialize the object detection pipeline
Initialise le pipeline de détection et classification d'objets.
"""
self.image_path = image_path self.image_path = image_path
self.image = None self.image = None
self.binary_image = None self.binary_image = None
@ -16,38 +14,19 @@ class ObjectDetectionPipeline:
self.output_dir = output_dir self.output_dir = output_dir
self.min_contour_area = min_contour_area self.min_contour_area = min_contour_area
self.binary_threshold = binary_threshold self.binary_threshold = binary_threshold
self.mode = None # Défini par le main.py ("plan" ou "page")
if not os.path.exists(self.output_dir): if not os.path.exists(self.output_dir):
os.makedirs(self.output_dir) os.makedirs(self.output_dir)
def set_mode(self, mode):
"""
Configure le mode d'analyse (plan ou page).
"""
self.mode = mode
if self.mode == "plan":
self.annotated_output_path = os.path.join(self.output_dir, "annotated_plan.jpg")
self.detection_threshold = -395000 # Seuil pour le mode plan
elif self.mode == "page":
self.annotated_output_path = os.path.join(self.output_dir, "annotated_page.jpg")
self.detection_threshold = -65000 # Seuil pour le mode page
else:
raise ValueError(f"Mode inconnu : {mode}")
def load_image(self): def load_image(self):
""" # Load the specified image
Charge l'image spécifiée.
"""
self.image = cv2.imread(self.image_path) self.image = cv2.imread(self.image_path)
if self.image is None: if self.image is None:
raise FileNotFoundError(f"Image {self.image_path} non trouvée.") raise FileNotFoundError(f"Image {self.image_path} not found.")
return self.image return self.image
def preprocess_image(self): def preprocess_image(self):
""" # Preprocess the image for inference
Prétraite l'image pour la détection.
"""
channels = cv2.split(self.image) channels = cv2.split(self.image)
binary_images = [] binary_images = []
@ -64,11 +43,9 @@ class ObjectDetectionPipeline:
return binary_image return binary_image
def detect_and_classify_objects(self): def detect_and_classify_objects(self):
""" # Detect and classify objects in the image
Détecte et classe les objets dans l'image.
"""
if self.model is None: if self.model is None:
raise ValueError("Aucun modèle de classification fourni.") raise ValueError("No classification model provided.")
self.binary_image = self.preprocess_image() self.binary_image = self.preprocess_image()
contours, _ = cv2.findContours(self.binary_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) contours, _ = cv2.findContours(self.binary_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
@ -83,10 +60,9 @@ class ObjectDetectionPipeline:
x, y, w, h = cv2.boundingRect(contour) x, y, w, h = cv2.boundingRect(contour)
letter_image = self.image[y:y + h, x:x + w] letter_image = self.image[y:y + h, x:x + w]
# Prédit la classe de l'objet détecté predicted_class = self.model.predict(letter_image, threshold=-65000) # Adjusted threshold
predicted_class = self.model.predict(letter_image, threshold=self.detection_threshold)
if predicted_class is None: if predicted_class is None:
print("Objet ignoré en raison d'une faible ressemblance.") print("Object ignored due to low resemblance.")
continue continue
class_counts[predicted_class] += 1 class_counts[predicted_class] += 1
@ -95,9 +71,7 @@ class ObjectDetectionPipeline:
return dict(sorted(class_counts.items())), detected_objects return dict(sorted(class_counts.items())), detected_objects
def save_results(self, class_counts, detected_objects): def save_results(self, class_counts, detected_objects):
""" # Save detection and classification results
Sauvegarde les résultats de la détection et de la classification.
"""
binary_output_path = os.path.join(self.output_dir, "binary_image.jpg") binary_output_path = os.path.join(self.output_dir, "binary_image.jpg")
cv2.imwrite(binary_output_path, self.binary_image) cv2.imwrite(binary_output_path, self.binary_image)
@ -106,8 +80,8 @@ class ObjectDetectionPipeline:
cv2.rectangle(annotated_image, (x, y), (x + w, y + h), (0, 255, 0), 2) cv2.rectangle(annotated_image, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.putText(annotated_image, str(predicted_class), (x, y - 10), cv2.putText(annotated_image, str(predicted_class), (x, y - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2) cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
annotated_output_path = os.path.join(self.output_dir, "annotated_page.jpg")
cv2.imwrite(self.annotated_output_path, annotated_image) cv2.imwrite(annotated_output_path, annotated_image)
results_text_path = os.path.join(self.output_dir, "results.txt") results_text_path = os.path.join(self.output_dir, "results.txt")
with open(results_text_path, "w") as f: with open(results_text_path, "w") as f:
@ -115,14 +89,12 @@ class ObjectDetectionPipeline:
f.write(f"{class_name}: {count}\n") f.write(f"{class_name}: {count}\n")
def display_results(self, class_counts, detected_objects): def display_results(self, class_counts, detected_objects):
""" # Display and save the results
Affiche et sauvegarde les résultats.
"""
self.save_results(class_counts, detected_objects) self.save_results(class_counts, detected_objects)
plt.figure(figsize=(10, 5)) plt.figure(figsize=(10, 5))
plt.bar(class_counts.keys(), class_counts.values()) plt.bar(class_counts.keys(), class_counts.values())
plt.xlabel("Classes") plt.xlabel("Classes")
plt.ylabel("Nombre d'objets détectés") plt.ylabel("Object count")
plt.title("Distribution des classes détectées") plt.title("Detected Class Distribution")
plt.show() plt.show()

63
train.py
View file

@ -1,57 +1,62 @@
from main import analysis_mode import os
from collections import defaultdict
if analysis_mode == "plan": import numpy as np
dataset_path = "data/catalogueSymbol" import cv2
allowed_classes = ['Figure1', 'Figure2', 'Figure3', 'Figure4', 'Figure5', 'Figure6']
model_path = "models/bayesian_modelPLAN.pth"
else:
dataset_path = "data/catalogue"
allowed_classes = ['2', 'd', 'I', 'n', 'o', 'u']
model_path = "models/bayesian_modelPAGE.pth"
from src.classifiers.bayesian import BayesianClassifier from src.classifiers.bayesian import BayesianClassifier
from collections import defaultdict
import os
import cv2
import numpy as np
# Initialisation if __name__ == "__main__":
bayesian_model = BayesianClassifier() # Chemin vers le dataset d'entraînement
dataset_path = "data/catalogue"
print("Début de l'entraînement...") # Initialisation du classifieur Bayésien
class_features = defaultdict(list) bayesian_model = BayesianClassifier()
total_images = 0
# Parcours des classes dans le dataset print("Début de l'entraînement...")
for class_name in os.listdir(dataset_path):
# Dictionnaire pour stocker les caractéristiques par classe
class_features = defaultdict(list)
total_images = 0
# Liste des classes autorisées
allowed_classes = ['2', 'd', 'I', 'n', 'o', 'u'] # Classes spécifiques au projet
# Parcours des classes dans le dataset
for class_name in os.listdir(dataset_path):
if class_name not in allowed_classes: if class_name not in allowed_classes:
continue continue # Ignorer les classes non autorisées
class_folder_path = os.path.join(dataset_path, class_name) class_folder_path = os.path.join(dataset_path, class_name)
if not os.path.isdir(class_folder_path): if not os.path.isdir(class_folder_path):
continue continue # Ignorer les fichiers qui ne sont pas des dossiers
# Ajouter la classe au modèle si elle n'existe pas déjà
if class_name not in bayesian_model.classes: if class_name not in bayesian_model.classes:
bayesian_model.classes.append(class_name) bayesian_model.classes.append(class_name)
# Parcours des images dans le dossier de la classe
for image_name in os.listdir(class_folder_path): for image_name in os.listdir(class_folder_path):
image_path = os.path.join(class_folder_path, image_name) image_path = os.path.join(class_folder_path, image_name)
image = cv2.imread(image_path) image = cv2.imread(image_path)
if image is not None: if image is not None:
# Extraire les caractéristiques de l'image
features = bayesian_model.extract_features(image) features = bayesian_model.extract_features(image)
for feature in features: for feature in features:
class_features[class_name].append(feature) class_features[class_name].append(feature)
total_images += 1 total_images += 1
# Calcul des statistiques pour chaque classe # Calcul des statistiques pour chaque classe
for class_name in bayesian_model.classes: for class_name in bayesian_model.classes:
if class_name in class_features: if class_name in class_features:
features = np.array(class_features[class_name]) features = np.array(class_features[class_name])
bayesian_model.feature_means[class_name] = np.mean(features, axis=0) bayesian_model.feature_means[class_name] = np.mean(features, axis=0)
bayesian_model.feature_variances[class_name] = np.var(features, axis=0) + 1e-6 bayesian_model.feature_variances[class_name] = np.var(features, axis=0) + 1e-6 # Éviter la division par zéro
bayesian_model.class_priors[class_name] = len(features) / total_images bayesian_model.class_priors[class_name] = len(features) / total_images
print("Entraînement terminé.") print("Entraînement terminé.")
bayesian_model.save_model(model_path)
print(f"Modèle sauvegardé dans : {model_path}") # Sauvegarde du modèle entraîné
model_path = "models/bayesian_modelPAGE.pth"
bayesian_model.save_model(model_path)
print(f"Modèle sauvegardé dans : {model_path}")