The efficient model generation to 3D printing based on self-calibration

In order to improve the performance of three-dimensional reconstruction and overcome highly dependent relationship of calibration board, an efficient generation 3D printing model method was proposed in this paper. Without using the calibration board to calculate the camera parameters, image captured by single camera can be used to generate 3D model. However, self-calibration method is deeply influence by the image quality and point matching accuracy. In order to overcome these effects, firstly the captured image is removed background area and restrain noise by interactive and graph partition to improve the robustness. Second feature point is extracted from sequences pictures by improved Speed-Up Robust Features (SURF) algorithm and is matched based on its´ Matching Factor, which shows faster than the previous program. Then camera model parameters is calculated by Self-Calibration matching information. Finally, dense 3D object is reconstructed by combining camera model and feature point matching information. The paper proposed an effective generating 3D printing model based on self-calibration. A series of experiments show the effectiveness, convenience and widely application of the proposed method.