Recognition of Facial Structures Using Extreme Learning Machine Algorithm

Abstract

Recognition of natural emotions from human

faces is an interesting topic with a wide range of potential applications like human-system interaction, automated systems, image and video retrieval, smart environments, and driver warning systems. Traditionally, facial emotion recognition systems have been initiated on laboratory controlled  data,  which is  not  representative  of the environment faced in real-world applications. To robustly recognize facial emotions in real-world natural situations, this paper proposes an approach called Extreme Sparse Learning (ESL), which has the ability to combine and learn both dictionary (set of basis) and a non-linear classification model. The proposed approach combines the discriminative power of Extreme Learning Machine (ELM) with the reconstruction property of sparse representation to enable the accuracy of classification when presented with noisy signals and imperfect data recorded in natural settings. Additionally, this work presents a new local spatiotemporal descriptor that is distinctive and pose-invariant. The proposed framework is able to achieve the modern recognition accuracy on both acted and actual facial emotion databases.