This paper deals with the problem concerned with tracking control for a class of the uncertain strict-feedback nonlinear systems with unkown dead-zone. Firstly, the state observer is established for estimating the unmeasured states. Then, by employing the radial basis function neural networks(RBF NNs), the unknown functions are approximated. Finally, the Backstepping technique is utilized to construct an adaptive neural output feedback control scheme.The designed controller decreases the number of learning parameters, and thus reduces the computational burden.It is shown that the designed neural output-feedback controller can ensure that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded(SGUUB), and the tracking error converges to a small neighborhood of the origin. Two examples are presented to illustrate the effectiveness of the proposed approach.