Automatic face detection and localization is a key problem in many computer vision tasks. In this paper, a simple yet effective approach for detecting and locating human faces in color images is proposed. The contribution of this paper is twofold. First, a particular reference to face detection techniques along with a background to neural networks is given. Second, and maybe most importantly, an adaptive cubic-spline neural network is designed to be used to detect and lo- cate human faces in uncontrolled environments. The experimental results conducted on our test set show the effective- ness of the proposed approach and it can compare favorably with other state-of-the-art approaches in the literature.