Real-time fault detection in manufacturing environments using face recognition techniques

New image processing techniques as well digital image capture equipment provide an opportunity for fast detection and diagnosis of quality problems in manufacturing environments compared with traditional dimensional measurement techniques. This paper proposes a new use of image processing to detect in real-time quality faults using images traditionally obtained to guide manufacturing processes. The proposed method utilizes face recognition tools to eliminate the need of specific feature detection on determining out-of-specification parts. The focus of the proposed methodology is on computational efficiency to ensure that the algorithm runs in real time in high volume manufacturing environments. The algorithm is trained with previously classified images. New images are then classified into two groups, healthy and unhealthy. This paper proposes a method that combines Discrete Cosine Transform with Fisher's Linear Discriminant Analysis to detect faults, such as cracks, directly from aluminum stamped parts.