init

process_data_2.py

@@ -0,0 +1,99 @@
+import os
+import cv2
+import joblib
+import numpy as np
+from sklearn.svm import SVC
+from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.metrics import classification_report, accuracy_score
+from sklearn.cluster import MiniBatchKMeans
+
+# Path to your dataset (ensure it is extracted and organized into subfolders by class)
+dataset_dir = 'natural_images'  # update with your actual path
+
+# Initialize SIFT feature extractor
+sift = cv2.SIFT_create()
+
+# Prepare lists for storing descriptors and labels
+all_descriptors = []  # will accumulate all SIFT descriptors for building the vocabulary
+image_descriptors = []  # list of descriptors for each image
+labels = []
+
+# Iterate over each class folder in the dataset
+for label in os.listdir(dataset_dir):
+    label_folder = os.path.join(dataset_dir, label)
+    if not os.path.isdir(label_folder):
+        continue
+
+    # Process each image in the folder
+    for file in os.listdir(label_folder):
+        file_path = os.path.join(label_folder, file)
+        # Read the image in grayscale
+        image = cv2.imread(file_path, cv2.IMREAD_GRAYSCALE)
+        if image is None:
+            continue  # Skip if image reading fails
+
+        # Resize the image to a fixed size (optional, adjust based on your dataset)
+        image = cv2.resize(image, (128, 128))
+
+        # Extract SIFT features (keypoints and descriptors)
+        keypoints, descriptors = sift.detectAndCompute(image, None)
+        if descriptors is None:
+            continue  # Skip images with no detected keypoints
+
+        image_descriptors.append(descriptors)
+        labels.append(label)
+        # Accumulate descriptors for vocabulary creation
+        all_descriptors.extend(descriptors)
+
+# Convert the list of all descriptors to a NumPy array
+all_descriptors = np.array(all_descriptors)
+
+# Build a visual vocabulary using k-means clustering (Bag of Visual Words)
+vocab_size = 50  # You can adjust the number of clusters
+kmeans = MiniBatchKMeans(n_clusters=vocab_size, random_state=42)
+kmeans.fit(all_descriptors)
+
+# Create a histogram of visual words for each image
+features = []
+for descriptors in image_descriptors:
+    # Assign each descriptor to the nearest cluster (visual word)
+    words = kmeans.predict(descriptors)
+    # Build a histogram with bins for each cluster
+    hist, _ = np.histogram(words, bins=np.arange(vocab_size + 1))
+    # Normalize the histogram (L1 normalization)
+    hist = hist.astype('float32')
+    hist /= (hist.sum() + 1e-7)
+    features.append(hist)
+
+# Convert lists to NumPy arrays
+features = np.array(features)
+labels = np.array(labels)
+
+# Split the data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=0.2, random_state=42)
+
+# Define parameter grid for GridSearchCV with SVM
+param_grid = [
+    {'kernel': ['linear'], 'C': [0.1, 1, 10, 100]},
+    {'kernel': ['poly'], 'C': [0.1, 1, 10, 100], 'degree': [2, 3, 4], 'gamma': ['scale', 'auto']},
+    {'kernel': ['rbf'], 'C': [0.1, 1, 10, 50, 100], 'gamma': ['scale', 'auto']},
+]
+
+svm_model = SVC(probability=True)
+grid_search = GridSearchCV(svm_model, param_grid, cv=5, n_jobs=-1, verbose=3)
+
+# Train the SVM with grid search
+grid_search.fit(X_train, y_train)
+
+print("Best parameters found:", grid_search.best_params_)
+print("Best cross-validation score:", grid_search.best_score_)
+
+# Evaluate on the test set
+best_model = grid_search.best_estimator_
+y_pred = best_model.predict(X_test)
+
+print("Test Accuracy:", accuracy_score(y_test, y_pred))
+print(classification_report(y_test, y_pred))
+
+# Save the trained SVM model and the k-means vocabulary for later use
+joblib.dump({'grid_search': grid_search, 'kmeans': kmeans}, 'svm_natural_images_model_with_sift.pkl')