Recently, there has been a significant interest in employing high frequency radar imagery for many industrial oriented and security applications. The quality control of aeronautics composite multi-layered materials and structures through Non-Destructive Testing (NDT) is the main focus of this study. The main motivations for using this technology are: it allows penetration of most non-metal and non-polarized materials, it provides the ability for three-dimensional (3-D) imagery and in-depth information, and the millimeter waves (mmW) pose no health risk to the operator. The main goal of this research is to develop an integrated, semi-automatic and near real-time mode-operated image processing methodology for frequency-modulated continuous-wave (FMCW) millimeter wave images with center frequencies around 100 GHz and 300 GHz. The proposed methodology firstly foresees to process reflectance and transmittance 3-D imagery by extracting areas of interest and object's boundaries at two operated frequencies. Then, the detected areas are subjected to a multi-source database and integrated by a decision tree algorithm. The fused information is used to identify defects and in-homogeneities within the objects. Finally, the post-processing phase examines and evaluates the spatial accuracy of the extracted information.