added fcnn classifier

.gitignore

@@ -60,4 +60,7 @@ Thumbs.db.meta
 *.DS_Store
 
 # VS Code
-*.vscode
+*.vscode
+
+data/*
+venv/*

fcnn/main.py

@@ -0,0 +1,43 @@
+import os
+import cv2
+from sklearn.neural_network import MLPClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import classification_report
+
+def preprocess(img):
+    scale_percent = 15 
+    width = int(img.shape[1] * scale_percent / 100)
+    height = int(img.shape[0] * scale_percent / 100)
+    dim = (width, height)
+    resized = cv2.resize(img, dim, interpolation = cv2.INTER_AREA)
+    resized = resized.flatten()
+    return resized
+
+def readData(data_links):
+    x, y = [], []
+    for link in data_links:
+        img = cv2.imread(link, cv2.IMREAD_GRAYSCALE)
+        img = preprocess(img)
+        label = link.split("/")[1].split('_')[1]
+        x.append(img)
+        y.append(label)
+
+    return x, y
+
+data_links = os.listdir("data/")
+data_links = ["data/" + x for x in data_links]
+
+x, y = readData(data_links)
+
+X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=42)
+
+clf = MLPClassifier(solver='adam', alpha=1e-5, hidden_layer_sizes=(1000, 500, 500), random_state=1, 
+    activation='relu', batch_size='auto', shuffle=True, verbose=True)
+clf.fit(X_train, y_train)
+
+print("Score:")
+print(clf.score(X_test, y_test))
+
+print("Summary:")
+Y_pred = clf.predict(X_test)
+print(classification_report(y_test, Y_pred))

fcnn/requirements.txt

@@ -0,0 +1,2 @@
+opencv_python==4.5.4.60
+scikit_learn==1.0.1