Topology Optimization has been proven to be a useful tool in discovering non-intuitive optimal designs subject to certain design constraints. The results of Topology Optimization are either represented as a tessellation object composed of thousands of triangular surfaces, or as a point cloud. In either case, the results of Topology Optimization are not suited for use in subsequent steps of the design process which require 3D parametric CAD (Computer Aided Design) models. Converting Topology Optimization results into parametric CAD geometry by hand is an extremely tedious and time consuming process which is highly subjective. This thesis presents a shape recognition algorithm that uses a feature by feature CAD-centric approach to convert Topology Optimization results into parametric CAD geometry. This is accomplished by fitting 2D cross section geometry to various parts of a given feature through the use of Shape Templates and then constructing 3D surfaces through the set of 2D cross sections. This algorithm aids in measuring the geometric approximation error of the generated geometry as compared to the optimal model, and standardizes the process through automation techniques. It also aids the designer / engineer in managing the direct tradeoff between closeness of geometric approximation (measured by volumetric comparison) and model complexity (measured by the number of parameters required to represent the geometry).