The paper introduces a real-time facial emotion detection system based on Convolutional Neural Networks(CNNs) and OpenCV. The system detects the faces and identifies emotions from facial expressions byprocessing video frames in real time. The model of CNN is trained on a big facial image dataset and emotions,and the performance shows accurate and speedy emotion detection. Integration of OpenCV with CNN modelfacilitates real-time processing of video frames, and thus the system is applicable in practical purposes.Application of machine learning includes the recognition of facial emotions of emotion.Those that were abstracted from an image on the basis of features,it classifies a face emotion image into one ofthe facial emotion categories. Among the classification methods, convolutional neural network (cnn) alsoextracts patterns from an image. Here, we employed the CNN model for facial expression recognition.In orderto enhance the accuracy of facial emotion detection, the wavelet transform is utilized afterward. There are sevenvarious face emotions contained in the facial emotion image dataset, which were collected from Kaggle.Experimental facial emotion recognition using the CNN and wavelet transform enhances the accuracy.