├── README.md
└── main2.py


/README.md:
--------------------------------------------------------------------------------
1 | task4:
2 | Develop a hand gesture recognition model that can accurately identify and classify different hand gestures from image or video data, enabling intuitive human-computer interaction and gesture-based control systems.
3 | 
4 | Dataset :-  https://www.kaggle.com/gti-upm/leapgestrecog
5 | 


--------------------------------------------------------------------------------
/main2.py:
--------------------------------------------------------------------------------
  1 | import numpy as np
  2 | import pandas as pd
  3 | import matplotlib.pyplot as plt
  4 | import os
  5 | import cv2
  6 | from tqdm import tqdm
  7 | import random
  8 | from sklearn.model_selection import train_test_split
  9 | import tensorflow as tf
 10 | from tensorflow.keras.models import Sequential
 11 | from tensorflow.keras.layers import Flatten, Dense, LeakyReLU
 12 | from tensorflow.math import confusion_matrix
 13 | from sklearn.metrics import classification_report
 14 | import seaborn as sns
 15 | 
 16 | # Set seed for reproducibility
 17 | tf.random.set_seed(3)
 18 | 
 19 | # Define folder paths and file names
 20 | folders_names = [r'D:/prodigy tasks/task4/train']  # Update with your folder path
 21 | files_names = ['01_palm', '02_l', '03_fist', '04_fist_moved', '05_thumb']
 22 | 
 23 | 
 24 | # Function to create training data
 25 | def create_training_data():
 26 |     training_data = []
 27 |     for folder in folders_names:
 28 |         Class_num = folder[-1]
 29 |         print('Class', Class_num)
 30 |         for file in files_names:
 31 |             path = os.path.join(folder, file)
 32 |             print('Class', Class_num, file)
 33 |             for img in tqdm(os.listdir(path)):
 34 |                 img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE)
 35 |                 training_data.append([img_array, int(Class_num)])
 36 | 
 37 | 
 38 | create_training_data()
 39 | 
 40 | 
 41 | # Function to check image sizes
 42 | def check_image_sizes():
 43 |     first_img_shape = None
 44 |     for folder in folders_names:
 45 |         for file in files_names:
 46 |             path = os.path.join(folder, file)
 47 |             for img in os.listdir(path):
 48 |                 img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE)
 49 |                 if first_img_shape is None:
 50 |                     first_img_shape = img_array.shape
 51 |                 elif img_array.shape != first_img_shape:
 52 |                     print("Image sizes are not consistent.")
 53 |                     return False
 54 |     print("All images have the same size:", first_img_shape)
 55 | 
 56 | 
 57 | check_image_sizes()
 58 | 
 59 | # Shuffle the training data
 60 | random.shuffle(training_data)
 61 | 
 62 | # Print class numbers for a few images
 63 | for i in range(5):
 64 |     print("Class number for image", i + 1, ":", training_data[i][1])
 65 | 
 66 | # Extract features and labels
 67 | X = [feature for feature, _ in training_data]
 68 | y = [label for _, label in training_data]
 69 | X = np.array(X)
 70 | y = np.array(y)
 71 | print(X.shape)
 72 | print(y.shape)
 73 | 
 74 | # Split data into training and testing sets
 75 | X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 76 | 
 77 | # Normalize pixel values
 78 | X_train = X_train / 255.0
 79 | X_test = X_test / 255.0
 80 | 
 81 | # Define the model architecture
 82 | model = Sequential([
 83 |     Flatten(input_shape=(240, 640)),
 84 |     Dense(64),
 85 |     LeakyReLU(alpha=0.1),
 86 |     Dense(32),
 87 |     LeakyReLU(alpha=0.1),
 88 |     Dense(16),
 89 |     LeakyReLU(alpha=0.1),
 90 |     Dense(10, activation='softmax')
 91 | ])
 92 | 
 93 | # Compile the model
 94 | model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
 95 | 
 96 | # Train the model
 97 | history = model.fit(X_train, y_train, epochs=3, validation_split=0.1, batch_size=32, verbose=2)
 98 | 
 99 | # Evaluate the model
100 | loss, accuracy = model.evaluate(X_train, y_train)
101 | print(f"Training Loss: {loss:.4f}")
102 | print(f"Training Accuracy: {accuracy * 100:.2f}%")
103 | 
104 | loss, accuracy = model.evaluate(X_test, y_test)
105 | print(f"Testing Loss: {loss:.4f}")
106 | print(f"Testing Accuracy: {accuracy * 100:.2f}%")
107 | 
108 | # Plot the training history
109 | plt.plot(history.history['loss'])
110 | plt.plot(history.history['val_loss'])
111 | plt.title('Model Loss')
112 | plt.xlabel('Epoch')
113 | plt.ylabel('Loss')
114 | plt.legend(['Train', 'Test'], loc='upper left')
115 | plt.show()
116 | 
117 | # Make predictions on the test set
118 | y_pred = model.predict(X_test)
119 | y_pred = [np.argmax(i) for i in y_pred]
120 | 
121 | # Generate classification report
122 | print(classification_report(y_test, y_pred))
123 | 
124 | # Generate confusion matrix
125 | conf_mat = confusion_matrix(y_test, y_pred)
126 | plt.figure(figsize=(15, 7))
127 | sns.heatmap(conf_mat, annot=True, fmt='d', cmap='bone')
128 | plt.ylabel('True Labels')
129 | plt.xlabel('Predicted Labels')
130 | plt.show()
131 | 


--------------------------------------------------------------------------------