There has been an increasing number of occurrences of neuromuscular disorders, making difficulty in communicating with the surrounding world. However, the recent advancements in technology aid these people in overcoming the barriers that obstruct them in communication. One such technology is Brain Computer Interface (BCI). This BCI provides an alternative non-neuromuscular route towards communicating with the environment. Among the various electroencephalogram (EEG) components that can be modulated by the user’s intent, BCIs based on the steady state visual evoked potential (SSVEP) are studied due to their high information transfer rate (ITR) and minimal training time. The performance of SSVEP based BCI depends mainly on the number of targets present in the user interface and the target detection accuracy. The focus of the study is to develop signal processing approaches for the enhancement of accuracy with minimal computations. Two methods namely, empirical mode decomposition based conventional correlation (EMDCC) and subject specific spatial filtering (SSSF) for target detection are proposed. The proposed methods are tested on two different datasets, one collected using an in-house developed hardware and the other a benchmark dataset. The developed methods and preliminary results will be shared in the presentation.