Facial expression is a very difficult task (FER) due to the variation of facial expression across the human population and to the context-dependent variation even for the same individual. We can see that FER  has many applications in the fields like human behavior interpretation and human-computer interface. The study of Mehrabian shows that 55% of the message is comprised of facial expression while 7% of the communication is conveyed by linguistic language whereas 38% by paralanguage during human communication. This shows that facial expression has a significant role in communication. The proposed system uses a webcam to capture our face and determine whether you were smiling or not. The system uses an OpenCV computer vision library to preprocess the webcam image, and in this system, we have used a logistic regression algorithm to train on a provided dataset and evaluate the new image.