Update README.md

README.md

@@ -14,7 +14,9 @@ This project is a face recognition system powered by HumanexAI and coded by Ahma
 * Customizable: The system can be customized to work with different datasets or classifiers, depending on the user's requirements.
 ## HumanexAI Face Recognition System Pipeline
 
-To commence the training process, we must first prepare the training data. For instance, if we have three individuals representing three distinct classes, we will create a central file named "Data" to store all the training data. Within this file, we will have a dedicated file for each individual's (class's) data. For example, suppose we have individuals named Ahmad, Hassan, and Asad. In that case, the file structure would be organized as Data/Ahmad - Hassan - Asad. After executing the train.py file, we will receive two outputs, a .npz file containing the detected faces, and another .npz file containing the embeddings of these faces. The embeddings file is a numerical vector that represents the unique features of an individual's face. This high-dimensional vector captures the distinct characteristics of a face such as the distance between the eyes, nose, and mouth. The embeddings are generated using a deep neural network that has been trained on a large amount of face data. These embeddings are used to compare and measure the similarity of different faces. In a face recognition system, the embeddings file is commonly used as an input to a classifier, such as an SVM or KNN, to verify or identify individuals based on their facial features. The figure below illustrates training and testing process.
+To commence the training process, we must first prepare the training data. For instance, if we have three individuals representing three distinct classes, we will create a central file named "Data" to store all the training data. Within this file, we will have a dedicated file for each individual's (class's) data. For example, suppose we have individuals named Ahmad, Hassan, and Asad. In that case, the file structure would be organized as Data/Ahmad - Hassan - Asad. After executing the train.py file, we will receive two outputs, a .npz file containing the detected faces, and another .npz file containing the embeddings of these faces.
+
+The embeddings file is a numerical vector that represents the unique features of an individual's face. This high-dimensional vector captures the distinct characteristics of a face such as the distance between the eyes, nose, and mouth. The embeddings are generated using a deep neural network that has been trained on a large amount of face data. These embeddings are used to compare and measure the similarity of different faces. In a face recognition system, the embeddings file is commonly used as an input to a classifier, such as an SVM or KNN, to verify or identify individuals based on their facial features. The figure below illustrates training and testing process.
 
 
 ![pipeline](pipeline.png)