initial commit

collect_imgs.py

+import os
+
+import cv2
+
+
+DATA_DIR = './data'
+if not os.path.exists(DATA_DIR):
+    os.makedirs(DATA_DIR)
+
+number_of_classes = 3
+dataset_size = 100
+
+cap = cv2.VideoCapture(2)
+for j in range(number_of_classes):
+    if not os.path.exists(os.path.join(DATA_DIR, str(j))):
+        os.makedirs(os.path.join(DATA_DIR, str(j)))
+
+    print('Collecting data for class {}'.format(j))
+
+    done = False
+    while True:
+        ret, frame = cap.read()
+        cv2.putText(frame, 'Ready? Press "Q" ! :)', (100, 50), cv2.FONT_HERSHEY_SIMPLEX, 1.3, (0, 255, 0), 3,
+                    cv2.LINE_AA)
+        cv2.imshow('frame', frame)
+        if cv2.waitKey(25) == ord('q'):
+            break
+
+    counter = 0
+    while counter < dataset_size:
+        ret, frame = cap.read()
+        cv2.imshow('frame', frame)
+        cv2.waitKey(25)
+        cv2.imwrite(os.path.join(DATA_DIR, str(j), '{}.jpg'.format(counter)), frame)
+
+        counter += 1
+
+cap.release()
+cv2.destroyAllWindows()

create_dataset.py

+import os
+import pickle
+
+import mediapipe as mp
+import cv2
+import matplotlib.pyplot as plt
+
+
+mp_hands = mp.solutions.hands
+mp_drawing = mp.solutions.drawing_utils
+mp_drawing_styles = mp.solutions.drawing_styles
+
+hands = mp_hands.Hands(static_image_mode=True, min_detection_confidence=0.3)
+
+DATA_DIR = './data'
+
+data = []
+labels = []
+for dir_ in os.listdir(DATA_DIR):
+    for img_path in os.listdir(os.path.join(DATA_DIR, dir_)):
+        data_aux = []
+        img = cv2.imread(os.path.join(DATA_DIR, dir_, img_path))
+        img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+
+        results = hands.process(img_rgb)
+        if results.multi_hand_landmarks:
+            for hand_landmarks in results.multi_hand_landmarks:
+                for i in range(len(hand_landmarks.landmark)):
+                    x = hand_landmarks.landmark[i].x
+                    y = hand_landmarks.landmark[i].y
+                    data_aux.append(x)
+                    data_aux.append(y)
+
+            data.append(data_aux)
+            labels.append(dir_)
+
+f = open('data.pickle', 'wb')
+pickle.dump({'data': data, 'labels': labels}, f)
+f.close()

data/.gitignore

+.gitignore
+

inference_classifier.py

+import pickle
+
+import cv2
+import mediapipe as mp
+import numpy as np
+
+model_dict = pickle.load(open('./model.p', 'rb'))
+model = model_dict['model']
+
+cap = cv2.VideoCapture(2)
+
+mp_hands = mp.solutions.hands
+mp_drawing = mp.solutions.drawing_utils
+mp_drawing_styles = mp.solutions.drawing_styles
+
+hands = mp_hands.Hands(static_image_mode=True, min_detection_confidence=0.3)
+
+labels_dict = {0: 'A', 1: 'B', 2: 'L'}
+while True:
+
+    data_aux = []
+    x_ = []
+    y_ = []
+
+    ret, frame = cap.read()
+
+    H, W, _ = frame.shape
+
+    frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+
+    results = hands.process(frame_rgb)
+    if results.multi_hand_landmarks:
+        for hand_landmarks in results.multi_hand_landmarks:
+            mp_drawing.draw_landmarks(
+                frame,  # image to draw
+                hand_landmarks,  # model output
+                mp_hands.HAND_CONNECTIONS,  # hand connections
+                mp_drawing_styles.get_default_hand_landmarks_style(),
+                mp_drawing_styles.get_default_hand_connections_style())
+
+        for hand_landmarks in results.multi_hand_landmarks:
+            for i in range(len(hand_landmarks.landmark)):
+                x = hand_landmarks.landmark[i].x
+                y = hand_landmarks.landmark[i].y
+                data_aux.append(x)
+                data_aux.append(y)
+                x_.append(x)
+                y_.append(y)
+
+        x1 = int(min(x_) * W) - 10
+        y1 = int(min(y_) * H) - 10
+
+        x2 = int(max(x_) * W) - 10
+        y2 = int(max(y_) * H) - 10
+
+        prediction = model.predict([np.asarray(data_aux)])
+
+        predicted_character = labels_dict[int(prediction[0])]
+
+        cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 0), 4)
+        cv2.putText(frame, predicted_character, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 1.3, (0, 0, 0), 3,
+                    cv2.LINE_AA)
+
+    cv2.imshow('frame', frame)
+    cv2.waitKey(1)
+
+
+cap.release()
+cv2.destroyAllWindows()

requirements.txt

+opencv-python==4.7.0.68
+mediapipe==0.9.0.1
+scikit-learn==1.2.0

train_classifier.py

+import pickle
+
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+import numpy as np
+
+
+data_dict = pickle.load(open('./data.pickle', 'rb'))
+
+data = np.asarray(data_dict['data'])
+labels = np.asarray(data_dict['labels'])
+
+x_train, x_test, y_train, y_test = train_test_split(data, labels, test_size=0.2, shuffle=True, stratify=labels)
+
+model = RandomForestClassifier()
+
+model.fit(x_train, y_train)
+
+y_predict = model.predict(x_test)
+
+score = accuracy_score(y_predict, y_test)
+
+print('{}% of samples were classified correctly !'.format(score * 100))
+
+f = open('model.p', 'wb')
+pickle.dump({'model': model}, f)
+f.close()