The ability to characterize higher-order structures formed by nanoparticle (NP) assembly is critical for predicting and engineering the properties of advanced nanocomposite materials. Here we develop a quantitative image analysis software to characterize key structural properties of NP clusters from experimental images of nanocomposites. This analysis can be carried out on images captured at intermittent times during assembly to monitor the time evolution of NP clusters in a highly automated manner. The software outputs averages and distributions in the size, radius of gyration, fractal dimension, backbone length, end-to-end distance, anisotropic ratio, and aspect ratio of NP clusters as a function of time along with bootstrapped error bounds for all calculated properties. The polydispersity in the NP building blocks and biases in the sampling of NP clusters are accounted for through the use of probabilistic weights. This software, named Particle Image Characterization Tool (PICT), has been made publicly available and could be an invaluable resource for researchers studying NP assembly. To demonstrate its practical utility, we used PICT to analyze scanning electron microscopy images taken during the assembly of surface-functionalized metal NPs of differing shapes and sizes within a polymer matrix. PICT is used to characterize and analyze the morphology of NP clusters, providing quantitative information that can be used to elucidate the physical mechanisms governing NP assembly.