The inspection of thin-film thickness on a wafer is one of the key steps for the semiconductor manufacturing processes. This paper proposes estimating the film thickness profile of the wafer, where the 3-band RGB color imaging camera and the hyperspectral imaging module are utilized to achieve the robust metrology performance. The simulation results are designed for investigating the characteristics of estimated film thickness profiles based on the Gaussian process regression. We demonstrate this cost-effective solution is beneficial for monitoring the CMP process with small computational power. The proposed measurement method has a great potential to solve bottlenecks from the physical metrology processes.
Measuring the thickness of thin films on a wafer is one of the most important steps for the semiconductor manufacturing process. This paper proposes a vision-based methodology for estimating a film thickness profile of the wafer. The scalability and industrial applicability of obtaining film thickness for the wafer with a small computational cost are demonstrated. Experimental results and numerical simulations are designed for investigating the characteristics of estimated solutions based on multiple representative nonlinear regression methods. The regression models are trained with the training data which consists of image value and thickness value pairs where the thickness value is obtained from the physical metrology system. There is an inevitable trade-off between the accuracy and the computational time in the spectrum-based film thickness measurement system in general, but the performance of the proposed methodology satisfied both the accuracy and the estimation time to a moderate extent.