Support vector machine (SVM), is a popular kernel method for data classification that demonstrated its efficiency for a large range of practical applications. The method suffers, however, from some weaknesses including; risk of failure of the optimization process especially for high dimension cases, and the inherent processing time, non-systematic generalization to multi-classes, and dynamical classification. In this paper an alternative method is proposed with a comparable performance to SVM, while demonstrating a sensitive improvement of the aforementioned shortcomings. The new method is based on a minimum distance to optimal subspaces containing the mapped original data.