Camera calibration is an important procedure for the image-based three-dimensional (3D) shape reconstruction of existing objects. Methods that use different mathematics for the computation of the camera calibration have been reported in the literature. But a reliable detection of calibration patterns is not considered in these methods, which prevents their practical use. A robust recognition method for the detection of a checkerboard pattern for camera calibration is proposed. After introduction of the principle of this method, experiments are used to check the method on a wide range of real data. The results show that the method is robust over a range of illumination and a complicated background. The proposed method can be used for automatic camera calibration in real-world environments.