update files

.gitignore

@@ -1 +1,2 @@
 .DS_Store
+./__pycache__

classification.py

@@ -9,55 +9,6 @@ def resize_image(image_path, save_path):
     img = cv2.resize(img, (128, 128))
     cv2.imwrite(save_path, img)
 
-# read image data from ./grass/ folder
-if not os.path.exists('./grass_resized/'):
-    os.makedirs('./grass_resized/')
-
-# rename the image file to 1.jpg, 2.jpg, 3.jpg, ...
-count = 1
-for file in os.listdir('./grass/'):
-    if file.endswith('.jpg') or file.endswith('.jpeg') or file.endswith('.png'):
-        resize_image('./grass/' + file, './grass_resized/' + str(count) + '.jpg')
-        count += 1
-
-print('Done!')
-
-# save the resized image to ./wood_resized/ folder
-if not os.path.exists('./wood_resized/'):
-    os.makedirs('./wood_resized/')
-
-# rename the image file to 1.jpg, 2.jpg, 3.jpg, ...
-count = 1
-for file in os.listdir('./wood/'):
-    if file.endswith('.jpg') or file.endswith('.jpeg') or file.endswith('.png'):
-        resize_image('./wood/' + file, './wood_resized/' + str(count) + '.jpg')
-        count += 1
-    
-print('Done!')
-
-# Divide the data into training and testing data: 70% training, 30% testing
-# Merge grass and wood data into training and testing data
-# Save the training data to ./train/ folder
-# Save the testing data to ./test/ folder
-import shutil
-
-if not os.path.exists('./train/'):
-    os.makedirs('./train/')
-if not os.path.exists('./test/'):
-    os.makedirs('./test/')
-
-# Rename files so that they do not overwrite each other
-for i in range(1, 36):
-    shutil.copy('./grass_resized/' + str(i) + '.jpg', './train/' + str(i) + '.jpg')
-for i in range(36, 51):
-    shutil.copy('./grass_resized/' +
-                str(i) + '.jpg', './test/' + str(i - 35) + '.jpg')
-for i in range(1, 36):
-    shutil.copy('./wood_resized/' + str(i) + '.jpg', './train/' + str(i + 35) + '.jpg')
-for i in range(36, 51):
-    shutil.copy('./wood_resized/' +
-                str(i) + '.jpg', './test/' + str(i - 20) + '.jpg')
-    
 # Do data augmentation by flipping the images horizontally on train data
 # Save the augmented data to the same folders
 def augment_image(image_path, save_path):
@@ -69,13 +20,6 @@ def augment_image(image_path, save_path):
     if np.random.rand() > 0.5:
         img = cv2.rotate(img, cv2.ROTATE_90_CLOCKWISE)
     cv2.imwrite(save_path, img)
-
-for i in range(1, 36):
-    augment_image('./train/' + str(i) + '.jpg', './train/' + str(i + 70) + '.jpg')
-for i in range(36, 51):
-    augment_image('./train/' + str(i) + '.jpg', './train/' + str(i + 70) + '.jpg')
-
-
     
 # Compute the GLCM for each image.
 # Extract features like contrast, correlaton, energy, and homogeneity.
@@ -112,27 +56,13 @@ def compute_glcm(image_path, ispath=True):
     mean_homogeneity = np.mean(homogeneity_flat)
     return [mean_contrast, mean_correlation, mean_energy, mean_homogeneity]
 
-# Compute the GLCM for each image in the training data
-data = []
-for i in range(1, 71):
-    data.append(compute_glcm('./train/' + str(i) + '.jpg'))
-df = pd.DataFrame(data, columns=['contrast', 'correlation', 'energy', 'homogeneity'])
-df['class'] = ['grass']*35 + ['wood']*35
-df.to_csv('train_glcm.csv', index=False)
-
-# Compute the GLCM for each image in the testing data
-data = []
-for i in range(1, 31):
-    data.append(compute_glcm('./test/' + str(i) + '.jpg'))
-df = pd.DataFrame(data, columns=['contrast', 'correlation', 'energy', 'homogeneity'])
-df['class'] = ['grass']*15 + ['wood']*15
-df.to_csv('test_glcm.csv', index=False)
-
 # Apply the LBP operator to each image.
 # Generate histograms of LBP codes to create feature vectors.
 # Save the features to a CSV file.
 # Label each feature vector with the correct class (grass or wood).
 from skimage.feature import local_binary_pattern
+import pickle
+import warnings
 
 def compute_lbp(image_path, ispath=True):
     if ispath:
@@ -143,78 +73,6 @@ def compute_lbp(image_path, ispath=True):
     hist, _ = np.histogram(lbp, bins=np.arange(0, 11), density=True)
     return hist
 
-# Compute the LBP for each image in the training data
-data = []
-for i in range(1, 71):
-    data.append(compute_lbp('./train/' + str(i) + '.jpg'))
-df = pd.DataFrame(data, columns=['lbp_' + str(i) for i in range(10)])
-df['class'] = ['grass']*35 + ['wood']*35
-df.to_csv('train_lbp.csv', index=False)
-
-# Compute the LBP for each image in the testing data
-data = []
-for i in range(1, 31):
-    data.append(compute_lbp('./test/' + str(i) + '.jpg'))
-df = pd.DataFrame(data, columns=['lbp_' + str(i) for i in range(10)])
-df['class'] = ['grass']*15 + ['wood']*15
-df.to_csv('test_lbp.csv', index=False)
-
-# Select Support Vector Machines (SVM) as the classifier.
-# Train the classifier using the training data.
-# Test the classifier using the testing data.
-from sklearn.svm import SVC
-from sklearn.metrics import accuracy_score
-from sklearn.metrics import precision_score
-import pandas as pd
-
-train_glcm = pd.read_csv('train_glcm.csv')
-test_glcm = pd.read_csv('test_glcm.csv')
-train_lbp = pd.read_csv('train_lbp.csv')
-test_lbp = pd.read_csv('test_lbp.csv')
-
-X_train_glcm = train_glcm.drop('class', axis=1)
-y_train_glcm = train_glcm['class']
-X_test_glcm = test_glcm.drop('class', axis=1)
-y_test_glcm = test_glcm['class']
-
-X_train_lbp = train_lbp.drop('class', axis=1)
-y_train_lbp = train_lbp['class']
-X_test_lbp = test_lbp.drop('class', axis=1)
-y_test_lbp = test_lbp['class']
-
-clf_glcm = SVC()
-clf_glcm.fit(X_train_glcm, y_train_glcm)
-y_pred_glcm = clf_glcm.predict(X_test_glcm)
-print('Accuracy for GLCM features:', accuracy_score(y_test_glcm, y_pred_glcm))
-# calculate the precsion
-precision = precision_score(y_test_glcm, y_pred_glcm, average='weighted')
-print('Precision for GLCM features:', precision)
-
-clf_lbp = SVC()
-clf_lbp.fit(X_train_lbp, y_train_lbp)
-y_pred_lbp = clf_lbp.predict(X_test_lbp)
-print('Accuracy for LBP features:', accuracy_score(y_test_lbp, y_pred_lbp))
-# calculate the precsion
-precision = precision_score(y_test_lbp, y_pred_lbp, average='weighted')
-print('Precision for LBP features:', precision)
-
-# Evaluate each classifier on the tesing set.
-# Compare the results.
-# Save the results to a CSV file.
-results = pd.DataFrame({'GLCM': [accuracy_score(y_test_glcm, y_pred_glcm)], 'LBP': [accuracy_score(y_test_lbp, y_pred_lbp)]})
-# Add the precision to the results
-results['GLCM_precision'] = precision_score(y_test_glcm, y_pred_glcm, average='weighted')
-results['LBP_precision'] = precision_score(y_test_lbp, y_pred_lbp, average='weighted')
-results.to_csv('results.csv', index=False)
-
-import pickle
-# save clf_glcm and clf_lbp as pickle files
-with open('clf_glcm.pkl', 'wb') as f:
-    pickle.dump(clf_glcm, f)
-with open('clf_lbp.pkl', 'wb') as f:
-    pickle.dump(clf_lbp, f)
-
-import warnings
 def classify_image(image, algorithm):
     # Suppress the warning about feature names
     warnings.filterwarnings("ignore", message="X does not have valid feature names")
@@ -239,4 +97,145 @@ def classify_image(image, algorithm):
     else:
         prediction = clf_lbp.predict(features_df)[0]
     
-    return prediction
+    return prediction
+
+if __name__ == '__main__':
+    # read image data from ./grass/ folder
+    if not os.path.exists('./grass_resized/'):
+        os.makedirs('./grass_resized/')
+
+    # rename the image file to 1.jpg, 2.jpg, 3.jpg, ...
+    count = 1
+    for file in os.listdir('./grass/'):
+        if file.endswith('.jpg') or file.endswith('.jpeg') or file.endswith('.png'):
+            resize_image('./grass/' + file, './grass_resized/' + str(count) + '.jpg')
+            count += 1
+
+    print('Done!')
+
+    # save the resized image to ./wood_resized/ folder
+    if not os.path.exists('./wood_resized/'):
+        os.makedirs('./wood_resized/')
+
+    # rename the image file to 1.jpg, 2.jpg, 3.jpg, ...
+    count = 1
+    for file in os.listdir('./wood/'):
+        if file.endswith('.jpg') or file.endswith('.jpeg') or file.endswith('.png'):
+            resize_image('./wood/' + file, './wood_resized/' + str(count) + '.jpg')
+            count += 1
+        
+    print('Done!')
+
+    # Divide the data into training and testing data: 70% training, 30% testing
+    # Merge grass and wood data into training and testing data
+    # Save the training data to ./train/ folder
+    # Save the testing data to ./test/ folder
+    import shutil
+
+    if not os.path.exists('./train/'):
+        os.makedirs('./train/')
+    if not os.path.exists('./test/'):
+        os.makedirs('./test/')
+
+    # Rename files so that they do not overwrite each other
+    for i in range(1, 36):
+        shutil.copy('./grass_resized/' + str(i) + '.jpg', './train/' + str(i) + '.jpg')
+    for i in range(36, 51):
+        shutil.copy('./grass_resized/' +
+                    str(i) + '.jpg', './test/' + str(i - 35) + '.jpg')
+    for i in range(1, 36):
+        shutil.copy('./wood_resized/' + str(i) + '.jpg', './train/' + str(i + 35) + '.jpg')
+    for i in range(36, 51):
+        shutil.copy('./wood_resized/' +
+                    str(i) + '.jpg', './test/' + str(i - 20) + '.jpg')
+
+
+    for i in range(1, 36):
+        augment_image('./train/' + str(i) + '.jpg', './train/' + str(i + 70) + '.jpg')
+    for i in range(36, 51):
+        augment_image('./train/' + str(i) + '.jpg', './train/' + str(i + 70) + '.jpg')
+
+    # Compute the LBP for each image in the training data
+    data = []
+    for i in range(1, 71):
+        data.append(compute_lbp('./train/' + str(i) + '.jpg'))
+    df = pd.DataFrame(data, columns=['lbp_' + str(i) for i in range(10)])
+    df['class'] = ['grass']*35 + ['wood']*35
+    df.to_csv('train_lbp.csv', index=False)
+
+    # Compute the LBP for each image in the testing data
+    data = []
+    for i in range(1, 31):
+        data.append(compute_lbp('./test/' + str(i) + '.jpg'))
+    df = pd.DataFrame(data, columns=['lbp_' + str(i) for i in range(10)])
+    df['class'] = ['grass']*15 + ['wood']*15
+    df.to_csv('test_lbp.csv', index=False)
+
+    # Compute the GLCM for each image in the training data
+    data = []
+    for i in range(1, 71):
+        data.append(compute_glcm('./train/' + str(i) + '.jpg'))
+    df = pd.DataFrame(data, columns=['contrast', 'correlation', 'energy', 'homogeneity'])
+    df['class'] = ['grass']*35 + ['wood']*35
+    df.to_csv('train_glcm.csv', index=False)
+
+    # Compute the GLCM for each image in the testing data
+    data = []
+    for i in range(1, 31):
+        data.append(compute_glcm('./test/' + str(i) + '.jpg'))
+    df = pd.DataFrame(data, columns=['contrast', 'correlation', 'energy', 'homogeneity'])
+    df['class'] = ['grass']*15 + ['wood']*15
+    df.to_csv('test_glcm.csv', index=False)
+
+    # Select Support Vector Machines (SVM) as the classifier.
+    # Train the classifier using the training data.
+    # Test the classifier using the testing data.
+    from sklearn.svm import SVC
+    from sklearn.metrics import accuracy_score
+    from sklearn.metrics import precision_score
+    import pandas as pd
+
+    train_glcm = pd.read_csv('train_glcm.csv')
+    test_glcm = pd.read_csv('test_glcm.csv')
+    train_lbp = pd.read_csv('train_lbp.csv')
+    test_lbp = pd.read_csv('test_lbp.csv')
+
+    X_train_glcm = train_glcm.drop('class', axis=1)
+    y_train_glcm = train_glcm['class']
+    X_test_glcm = test_glcm.drop('class', axis=1)
+    y_test_glcm = test_glcm['class']
+
+    X_train_lbp = train_lbp.drop('class', axis=1)
+    y_train_lbp = train_lbp['class']
+    X_test_lbp = test_lbp.drop('class', axis=1)
+    y_test_lbp = test_lbp['class']
+
+    clf_glcm = SVC()
+    clf_glcm.fit(X_train_glcm, y_train_glcm)
+    y_pred_glcm = clf_glcm.predict(X_test_glcm)
+    print('Accuracy for GLCM features:', accuracy_score(y_test_glcm, y_pred_glcm))
+    # calculate the precsion
+    precision = precision_score(y_test_glcm, y_pred_glcm, average='weighted')
+    print('Precision for GLCM features:', precision)
+
+    clf_lbp = SVC()
+    clf_lbp.fit(X_train_lbp, y_train_lbp)
+    y_pred_lbp = clf_lbp.predict(X_test_lbp)
+    print('Accuracy for LBP features:', accuracy_score(y_test_lbp, y_pred_lbp))
+    # calculate the precsion
+    precision = precision_score(y_test_lbp, y_pred_lbp, average='weighted')
+    print('Precision for LBP features:', precision)
+
+    # Evaluate each classifier on the tesing set.
+    # Compare the results.
+    # Save the results to a CSV file.
+    results = pd.DataFrame({'GLCM': [accuracy_score(y_test_glcm, y_pred_glcm)], 'LBP': [accuracy_score(y_test_lbp, y_pred_lbp)]})
+    # Add the precision to the results
+    results['GLCM_precision'] = precision_score(y_test_glcm, y_pred_glcm, average='weighted')
+    results['LBP_precision'] = precision_score(y_test_lbp, y_pred_lbp, average='weighted')
+    results.to_csv('results.csv', index=False)
+    # save clf_glcm and clf_lbp as pickle files
+    with open('clf_glcm.pkl', 'wb') as f:
+        pickle.dump(clf_glcm, f)
+    with open('clf_lbp.pkl', 'wb') as f:
+        pickle.dump(clf_lbp, f)