Purpose – This paper describes the development of a novel automated vision system used to detect the visual defects on painted slates. Design/methodology/approach – The vision system that has been developed consists of two major components covering the opto-mechanical and algorithmical aspects of the system. The first component addresses issues including the mechanical implementation and interfacing the inspection system with the development of a fast image processing procedure able to identify visual defects present on the slate surface. Findings – The inspection system was developed on 400 slates to determine the threshold settings that give the best trade-off between no false positive triggers and correct defect identification. The developed system was tested on more than 300 fresh slates and the success rate for correct identification of acceptable and defective slates was 99.32 per cent for defect free slates based on 148 samples and 96.91 per cent for defective slates based on 162 samples. Practical implications – The experimental data indicates that automating the inspection of painted slates can be achieved and installation in a factory is a realistic target. Testing the devised inspection system in a factory-type environment was an important part of the development process as this enabled us to develop the mechanical system and the image processing algorithm able to perform slate inspection in an industrial environment. The overall performance of the system indicates that the proposed solution can be considered as a replacement for the existing manual inspection system. Originality/value – The development of a real-time automated system for inspecting painted slates proved to be a difficult task since the slate surface is dark coloured, glossy, has depth profile non-uniformities and is being transported at high speeds on a conveyor. In order to address these issues, the system described in this paper proposed a number of novel solutions including the illumination set-up and the development of multi-component image-processing inspection algorithm.