Nanoindentations is an advanced method of measuring the mechanical properties of small volumes of materials using an instrumented indentation technique. Properties such as elastic modulus and hardness can be measured and explored by Nanoindentation. To support the material designers and specialists, this research is aiming to segment the captured data into regions with homogenous physical properties that can be used to optimize the process of mixing composite materials. During the Nanoindentation tests, and depending on the grid size, the resulting image/map of mechanical properties from the tested material's layer has a large dimensionality variety of values. Image processing technique and Machine Learning algorithms were utilized to cluster the physical property map and reduce its dimensionality. The sample data for this study is data of SLA 3D printed Nanocomposite of acrylic polymer (boron nitride), which is used as a case study to apply denoising and clustering techniques