Hamza TahirZeeshan AtherAhmed Usman Zafar2018-02-262018-02-262017https://escholar.umt.edu.pk/handle/123456789/2765Supervised by: Syed Farooq AliThe automatic analysis of human facial emotion is a demanding problem with many applications. Emotion detection and recognition is an emerging area of researchers for last few years. The human face has several emotions in which 7 are basic emotions and 15 are compound emotions. The basic emotions are sadness, fear, surprise, anger, and disgust, happiness and the last one is the neutral and the compound emotions are those which are made up of the combination of the basic emotions. It is cleared by the example that a person see something unexpected then he gets surprised and when he faces some scared environment or some unpredictable than he get fearful so when these both things happen together than a new emotion comes into existence that is fearfully surprised this emotion is called the compound emotion because it is made up of the two basic emotions. In this paper we explore the deep learning for the increase of accuracy in detection of both basic and compound emotions. We use the Martinez dataset [1] to extract the features and to find more valid and clear accuracy while image detection. We find the accuracy of basic and compound emotions individually in which we will use different types of approaches in the deep learning.enHuman facial emotionEmotion detection and recognitionBS ThesisThesis