Industrial robotic systems increasingly rely on vision sensors to perform tasks requiring accurate spatial perception, such as object localization, inspection, and vision-guided manipulation. In these applications, the accuracy of the overall system strongly depends on the quality of the calibration process used to establish the geometric relationship between the camera and the robot reference frames. This thesis presents the design, implementation, and experimental validation of a complete vision-based calibration framework for industrial robotic applications. The proposed pipeline integrates camera intrinsic calibration, camera pose estimation using ChArUco calibration boards, and hand-eye calibration within a unified software architecture developed in Python using the OpenCV library.