An integrated multiscale and multivariate image analysis framework for process monitoring of colour random textures: MSMIA

We present an integrated approach for conducting on-line and off-line image-based monitoring of processes whose products (raw materials, intermediate or final) consist of colour random textures. The methodology combines the principles underlying wavelet texture analysis and multivariate image analysis into a single framework, able to detect both abnormal changes in texture and colour. By taking into account a scale-dependent description of colour, it can detect subtle changes on how colour interacts with texture across the several length-scales considered. The proposed methodology was studied and characterized following best practice procedures for developing statistical process control methods, where controlled simulated test scenarios are employed to generate normal operation condition (NOC) data, as well as faults of different types and magnitudes. By simulating normal operation and faulty images in this way, it is possible to assess the monitoring potential of the proposed methodology to detect abnormal situations under a diversity of monotonically increasing faulty conditions. Results show that the proposed methodology is able to effectively detect changes in both colour and texture characteristics and one type of monitoring statistics in particular leads the performance in most of the tested scenarios: the PCA statistics for monitoring multiscale textural features. For this reason and for encompassing less computational and programming effort, its adoption is particularly recommended.