Estimating the head pose of a person provides important cues concerning visual focus of attention. Applications such as, human-computer interacting model and driver monitor system. In this paper, we present to estimate the head pose from different angles. The estimation of head pose angles from a single 2D face image using a 3D face model morphed from a suggestion face model. A reference model refers to a 3D face of a person of the same ethnicity and gender as the query subject. The proposed algorithm able to estimate the various head pose angles such as nodding, shaking, tilting, yaw, pitch and roll with performed query face image. To estimate head pose from an input image, the detection of specific facial features are important. Therefore, in this work the locations of both eyes and nose are used to estimate head pose. For facial feature detection from the detected facial region, Haarlike feature is utilized along with AdaBoost learning. Then the Haar-like features are mapped with optimized parameters of reference 3D model. The 3D face model is morphed from a reference model to be more specific to the query face in terms of the depth error at the feature points. Optimal depth parameters are create by minimizing the distance between the 2D features of the query face image and the matching features on the morphed 3D model projected onto 2D space. The proposed method able to measure various head poses with expected accuracy.