An image-based process monitoring scheme for outlier detection in manufacturing process




Tiokeng Kenyantio, Adrien

Journal Title

Journal ISSN

Volume Title



In the course of the past two decades, statistical process control (SPC) has evolved from monitoring individual data points to linear profiles to image data. Image sensors are now increasingly being deployed to complex systems due to rich information they can provide. As a result, image data plays a significant role in process monitoring in different application domains ranging from manufacturing to service systems. However, many of the existing methods fail to fully utilize the information of image data due to their complex nature in both spatial and temporal domains. This paper proposes a spatiotemporal outlier detection methodology based on Principal Component Analysis (PCA) and Hotelling T-square of prediction error to improve the performance of image monitoring schemes. First, PCA is used to extract the important features of high-dimensional image data to estimate the in-control images of the products. Hotelling T-square is used to analysis and draw the in-control chart. Next, we will define some errors to simulate the process in a different scenario. A real case study at a paper product manufacturing company with mass customization is used to demonstrate the performance of the proposed methodology in detecting different types of outliers in comparison with some of the existing methods in the literature.


This item is available only to currently enrolled UTSA students, faculty or staff. To download, navigate to Log In in the top right-hand corner of this screen, then select Log in with my UTSA ID.


Image processing



Mechanical Engineering