Update app.py

app.py

@@ -1,5 +1,5 @@
-import glob
 import cv2
+import glob
 import gradio as gr
 import numpy as np
 import matplotlib.pyplot as plt
@@ -7,16 +7,17 @@ from sklearn.model_selection import KFold
 from skimage.feature import graycomatrix, graycoprops
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+import pandas as pd
 from sklearn.model_selection import GridSearchCV
+from sklearn.neighbors import KNeighborsClassifier
 from skimage.feature import local_binary_pattern
 
 # Visualize GLCM features for grass and wood
 def plot_features(features, title):
     plt.figure(figsize=(10, 6))
     for i, feature in enumerate(features.T):  # Transpose to plot feature by feature
-        plt.plot(feature)  # Remove label if no legend is needed
+        plt.plot(feature)
     plt.title(title)
-    # plt.legend()  # Removed the legend to avoid warning
     plt.show()
 
 # Define directories for grass and wood images
@@ -176,13 +177,19 @@ for train_index, test_index in kf.split(lbp_features):
 # Print overall LBP accuracy
 print(f"LBP Cross-validated accuracy: {np.mean(lbp_accuracy_list) * 100:.2f}%")
 
+# Preprocess uploaded image for classification
+def preprocess_image(image):
+    gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)  # Convert to grayscale
+    resized_image = cv2.resize(gray_image, TARGET_SIZE, interpolation=cv2.INTER_AREA)  # Resize to match training size
+    return resized_image
+
 # Define the Gradio interface
 def classify_uploaded_image(image, algorithm):
-    image = np.array(image, dtype=np.uint8)  # Ensure correct type
+    image = preprocess_image(np.array(image, dtype=np.uint8))  # Preprocess uploaded image
 
     if algorithm == "GLCM":
         features = calc_glcm_features([image])  # Use parentheses, pass as a list
-        prediction = glcm_knn.predict(features)
+        prediction = glcm_classifier.predict(features)
     elif algorithm == "LBP":
         features = extract_lbp_features([image])
         prediction = lbp_classifier.predict(features)