Automatic classification of age and gender has become crucial for a rising number of applications, especially as social platforms and social media have risen. However, there is still substantial lack of performance of present approaches in real-world photos, especially when compared to the enormous performance jumps reported lately in the associated facial recognition job. In this research we show that a considerable gain in performance may be achieved by the application of convolution neural networks (CNN). This work is primarily designed to construct an algorithm that accurately guesses a person's age and gender.Haar cascade is one of the most often utilised approaches. In this research we provide a model that can help Haar Cascade to determine a person's gender. The model trained the classifier as positive and negative pictures using diverse photos of men and women. Various face characteristics are removed. With the help of Haar Cascade, the classifier determines if the picture input is men or women. Even with insufficient data, it functions effectively. A deep education framework created with Caffe is used to do the age or sex approximation task. Our model is able to detect multiple faces in single image and predict age and gender of all faces present in the image.