Human emotions estimated from face become more effective compared to various modes of extracting emotion owing to its robustness, high accuracy and better efficiency. This paper proposes detecting happiness of human face using minimal facial features from geometric deformable model and supervised classifier. First, the face detection and tracking is observed by constrained local model (CLM). Using CLM grid node, the entire and minimal feature vectors displacement is obtained by facial feature extraction. Compared to entire features, minimal feature vectors is considered for detecting happiness to improve accuracy. Facial animation parameters (FAPs) helps in identifying the facial feature movements to forms the feature vectors displacement. The feature vectors displacement is computed in supervised bilinear support vector machines (SVMs) classifier to detect the happiness in human frontal face image sequences. This paper focuses on minimal feature vectors of happiness (frontal face) in both training and testing phases. MMI facial expression database is used in training, and real-time data are used for testing phases. As a result, the overall accuracy of happiness is achieved 91.66% using minimal feature vectors. © Springer Nature Singapore Pte Ltd. 2018.