We have developed a method that can cluster and map large astronomical images onto a two-dimensional map. A combination of various state of the art machine learning algorithms is used to develop a fully unsupervised image quality assessment and clustering system. Our pipeline consists of a data pre-processing step where individual image objects are identified in a large astronomical image and converted to smaller pixel images. This data is then consumed by a deep convolutional autoencoder jointly trained with a self-organizing map. The resulting latent data is further compressed using a second autoencoder and eventually mapped onto a two-dimensional grid using a second self-organizing map. We used data taken from ground-based telescopes and, as a case study, compared the system’s ability and performance with the results obtained by supervised methods presented by Teimoorinia et al. (2020). The availability of target labels in a subset of this data allowed a comprehensive performance comparison between our unsupervised and supervised methods. We investigated the accuracy, precision and recall and observed that our unsupervised method outperforms the supervised method in some aspects. In addition to image quality assessments performed in this project, our method can have various other applications. As an example, it can help experts label images in a considerably shorter time with minimum human intervention. It can also be used as a content-based recommendation system capable of filtering images based on the desired content.