This project presents an advanced face detection and recognition system designed specifically for cricket players. The system utilizes a webpage-based model that accepts face images of cricket players in formats such as.jpg or.png. The preprocessing step includes resizing the images and applying noise filtering techniques to enhance the quality of the input data. Face detection is performed using the FaceNet algorithm, which extracts unique feature embeddings for each face, allowing for accurate identification The photos are then divided into training and testing datasets, with 80% used to train the model and 20% used for assessment. Convolutional Neural Networks (CNNs), a deep learning technique well-suited for image recognition, are used to solve the classification problem. The CNN model is trained to classify and predict the identity of cricket players based on the face images provided. The system’s performance is assessed using a variety of measures, including accuracy, precision, recall, and ROC curves. Furthermore, the confusion matrix and error rate are utilized to analyze the model’s performance in accurately recognizing cricket players. This system aims to provide a robust, real-time solution for recognizing cricket players in various contexts, such as player authentication or event management, by accurately detecting and classifying faces from a large dataset.