movingHEADmaster

1 files changed, 159 insertions, 0 deletions

diff --git a/cv.py b/cv.py
new file mode 100644
index 0000000..21b1664
--- /dev/null
+++ b/cv.py
@@ -0,0 +1,159 @@
+import kagglehub
+import numpy as np
+import os
+from pathlib import Path
+import cv2
+import pandas as pd
+from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics import accuracy_score, classification_report
+from sklearn.model_selection import train_test_split
+from skimage.feature import hog
+from skimage.filters import sobel
+import xgboost as xgb
+
+# Download dataset
+path = kagglehub.dataset_download("lsind18/gemstones-images")
+print("Path to dataset files:", path)
+
+# Set paths
+train_dataset_path = Path(path) / "train"
+test_dataset_path = Path(path) / "test"
+
+# ------------------- Preprocessing -------------------
+def preprocess_image(image_path):
+    image = cv2.imread(str(image_path))
+    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    image = cv2.GaussianBlur(image, (5, 5), 0)
+    lab = cv2.cvtColor(image, cv2.COLOR_RGB2LAB)
+    l, a, b = cv2.split(lab)
+    clahe = cv2.createCLAHE(clipLimit=5.0, tileGridSize=(10, 10))
+    l = clahe.apply(l)
+    lab = cv2.merge((l, a, b))
+    image = cv2.cvtColor(lab, cv2.COLOR_LAB2RGB)
+    image = cv2.resize(image, (128, 128))
+    return image
+
+# ------------------- Gabor Kernel Bank -------------------
+def build_gabor_kernels():
+    kernels = []
+    ksize = 31
+    for theta in np.arange(0, np.pi, np.pi / 4):
+        for sigma in (1, 3):
+            for lamda in (np.pi / 4, np.pi / 2):
+                kernel = cv2.getGaborKernel((ksize, ksize), sigma, theta, lamda, 0.5, 0, ktype=cv2.CV_32F)
+                kernels.append(kernel)
+    return kernels
+
+gabor_kernels = build_gabor_kernels()
+
+# ------------------- Feature Extraction -------------------
+sift = cv2.SIFT_create()
+
+def extract_features(image):
+    features = []
+
+    image_resized = cv2.resize(image, (128, 128))
+
+    # Color histograms
+    for i in range(3):
+        hist = cv2.calcHist([image_resized], [i], None, [64], [0, 256])
+        hist = hist.flatten() / (np.sum(hist) + 1e-5)
+        features.extend(hist)
+
+    # HOG
+    hog_feat = hog(image_resized, orientations=9, pixels_per_cell=(8, 8),
+                   cells_per_block=(2, 2), visualize=False, channel_axis=2)
+    features.extend(hog_feat)
+
+    # Harris Corners
+    gray = cv2.cvtColor(image_resized, cv2.COLOR_RGB2GRAY)
+    corners = cv2.cornerHarris(np.float32(gray), 2, 3, 0.04)
+    corner_count = np.sum(corners > 0.01 * corners.max())
+    features.append(corner_count)
+
+    # Sobel Edge Mean
+    sobel_img = sobel(gray)
+    features.append(np.mean(sobel_img))
+
+    # SIFT (mean + std of descriptors)
+    kp, des = sift.detectAndCompute(gray, None)
+    if des is not None:
+        des_mean = np.mean(des, axis=0)
+        des_std = np.std(des, axis=0)
+        features.extend(des_mean)
+        features.extend(des_std)
+    else:
+        features.extend([0]*128)  # mean
+        features.extend([0]*128)  # std
+
+    # Gabor filter responses (mean)
+    for kernel in gabor_kernels:
+        fimg = cv2.filter2D(gray, cv2.CV_8UC3, kernel)
+        features.append(np.mean(fimg))
+
+    return features
+
+# ------------------- Load Dataset -------------------
+def load_dataset(dataset_path):
+    all_features = []
+    all_labels = []
+
+    for gemstone_folder in os.listdir(dataset_path):
+        gemstone_path = dataset_path / gemstone_folder
+        if gemstone_path.is_dir():
+            image_files = list(gemstone_path.glob("**/*.jpg"))
+            print(f"📂 {gemstone_folder}: {len(image_files)} images")
+            for image_path in image_files:
+                try:
+                    image = preprocess_image(image_path)
+                    features = extract_features(image)
+                    all_features.append(features)
+                    all_labels.append(gemstone_folder)
+                except Exception as e:
+                    print(f"⚠️ Error processing {image_path}: {e}")
+    return all_features, all_labels
+
+print("\n📥 Loading training data...")
+train_features, train_labels = load_dataset(train_dataset_path)
+
+print("\n📥 Loading test data...")
+test_features, test_labels = load_dataset(test_dataset_path)
+
+# ------------------- Encode Labels -------------------
+le = LabelEncoder()
+y_train = le.fit_transform(train_labels)
+y_test = le.transform(test_labels)
+
+# ------------------- Create DataFrames -------------------
+X_train = pd.DataFrame(train_features)
+X_test = pd.DataFrame(test_features)
+
+print("\n📊 Features DataFrame shape:", X_train.shape)
+
+# ------------------- Optional Train/Val Split -------------------
+X_tr, X_val, y_tr, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)
+
+# ------------------- Train XGBoost -------------------
+clf = xgb.XGBClassifier(
+    objective='multi:softmax',
+    num_class=len(le.classes_),
+    eval_metric='mlogloss',
+    use_label_encoder=False,
+    max_depth=6,
+    subsample=0.8,
+    colsample_bytree=0.8,
+    n_estimators=100,
+    learning_rate=0.1,
+    random_state=42
+)
+
+print("\n⚙️ Training XGBoost...")
+clf.fit(X_tr, y_tr)  # No early stopping due to version limit
+
+# ------------------- Evaluate -------------------
+y_pred = clf.predict(X_test)
+acc = accuracy_score(y_test, y_pred)
+
+print(f"\n✅ Accuracy on test set: {acc * 100:.2f}%")
+print("\n📄 Classification Report:\n", classification_report(le.inverse_transform(y_test), le.inverse_transform(y_pred)))
+