Visual anomaly detection via soft computing: a prototype application at NASA

Abstract

A visual system prototype that detects anomalies or defects in real time under normal lighting operating conditions was built for NASA at the Kennedy Space Center (KSC). The system prototype is basically a learning machine that integrates the three elements of soft computing, Fuzzy Logic (FL), Artificial Neural Network (ANN), and Genetic Algorithm (GA) schemes to process the image, run the learning process, and finally detect the anomalies or defects. The system acquires the image, performs segmentation to separate the object being tested from the background, preprocesses the image using fuzzy reasoning, performs the final segmentation using fuzzy reasoning techniques to retrieve regions with potential anomalies or defects, and finally retrieves them using a learning model built via artificial neural network optimized using genetic algorithm techniques. This prototype system was originally tested on the detection of anomaly or defects at slidewires used in the emergency egress system at the NASA Space Shuttle launch pad at KSC. The prototype system successfully detected all defects classified under "loose strand". The imaging technologies based on fuzzy reasoning approach and created to preprocess the images have received NASA Space Awards and are currently being filed for patents by NASA; companies from different fields including security, medical, text digitalization and aerospace, are currently in the process of licensing these technologies from NASA.