This paper presents a fuzzy tracking control design method for nonlinear systems. Takagi-Sugeno fuzzy model is utilized to represent a nonlinear dynamic systems subject to external disturbance and measurement noise. Based on the fuzzy model, a fuzzy observer-based fuzzy controller is developed with guaranteed cost performance. The model reference tracking control scheme based on the augmented system is proposed and sufficient condition is derived for minimizing the cost function. The output feedback tracking control design is formulated in terms of linear matrix inequalities, which can be solved using the convex optimization techniques. The effectiveness of the proposed method is demonstrated through simulation example.