The FinFET has been introduced in the last decade to provide better transistor performance as the device size shrinks. The performance of FinFET is highly sensitive to the size and shape of the fin, which needs to be optimized with tighter control. Manual measurement of nano-scale features on TEM images of FinFET is not only a time consuming and tedious task, but also prone to error owing to visual judgment. Here, an auto-metrology approach is presented to extract the measured values with higher precision and accuracy so that the uncertainty in the manual measurement can be minimized. Firstly, a FinFET TEM image is processed through an edge detecting algorithm to reveal the fin profile precisely. Finally, an algorithm is utilized to calculate out the required geometrical data relevant to the FinFET parameters and summarizes them to a table or plots a graph based on the purpose of data interpretation. This auto-metrology approach is expected to be adopted by academia and/or industry for proper data analysis and interpretation with higher precision and efficiency.