Purpose-Automated technologies have been applied to facility management (FM) practices to address labour demands of, and time consumed by, inputting and processing manual data. Less attention has been focused on automation of visual information, such as images, when improving timely maintenance decisions. This study aimed to develop image classification algorithms to improve information flow in the inspection-repair process through building information modelling (BIM). Design/methodology/approach-To improve and automate the inspection-repair process, image classification algorithms were employed to connect images with a corresponding image database in a BIM knowledge repository. QR code decoding and Bag of Words were chosen to classify images in the system. Graphical user interfaces (GUIs) were developed to facilitate activity collaboration and communication. A pilot case study in an inspection-repair process was applied to demonstrate the applications of this system. Findings-The system developed in this study associates the inspection-repair process with a digital three dimensional (3D) model, GUIs, a BIM knowledge repository and image classification algorithms. By implementing the proposed application in a case study, the authors found that improvement of the inspection-repair process and automated image classification with a BIM knowledge repository (such as the one developed in this study) can enhance FM practices by increasing productivity and reducing time and costs associated with decision-making. Originality/value-This study introduces an innovative approach that applies image classification and leverages a BIM knowledge repository to enhance the inspection-repair process in facility management practice. The system designed provides automated image-classifying data from a smart phone, eliminates time required to input image data manually, and improves communication and collaboration between FM personnel for maintenance in the decision-making process.