The automatic Face Expression Recognition is very important in computer vision since it has widespread applications in real time. However, the main issue is the design of an efficient descriptor that describes the appearance changes on the face. Towards such design, in this paper we have introduced a novel binary compact coding called as Edge Adaptive Local Directional Binary Pattern (EALDBP) that encodes the texture features of facial image. The proposed EALDBP is resilient to noise and illumination variations as well as it encodes the directionality of expressions. The directionality is discovered by the computation of edge responses through different compass masks. Further to encode intensity variations, we have considered the relationship between gradient pixels in the local neighborhood. Finally, a compact face descriptor is constructed with the help of Histograms computation over the encoded face image. To evaluate the performance, we tested out approach on two datasets; they are CK+ and JAFFE. The average recognition accuracy of these two datasets is observed as 90.3898% and 93.5922% for JAFFE and CK+ respectively. These accuracies demonstrate that the proposed approach outperforms the several state-of-art methods.
Micro-Expressions (MEs) are one kind of facial movement which is very spontaneous and involuntary in nature. MEs are observed when a person attempts to hide or conceal the experiencing emotion in a high-stakes environment. The duration of ME is very short and approximately less than 500 milliseconds. Recognition of such kinds of expressions from lengthy video consequences to a limited Micro Expression Recognition Performance and also creates the computational burden. Hence, in this paper, we propose a new ME spotting (detection of ME frames) method based on a new texture descriptor called Composite Binary Pattern (CBP). As a pre-processing, we employ the viola jones algorithm for landmark regions detection followed by landmark points detection for facial alignment. Next, every aligned face is described through CBP and subjected to feature difference analysis followed by the threshold for ME spotting. For simulation, the REVIEW dataset is used and the performance is measured through Recall, Precision, and F-Score.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.