Real-time flaw detection on complex object: comparison of results using classification with SVM, Boosting and Hyperrectangle based method

This paper presents a classification work performed on industrial parts using artificial vision, Support Vector Machine (SVM), Boosting and a combination of classifiers. The object to be controlled is a coated heater used in television set. Our project consists of detecting anomalies under manufacturer production as well as in classifying the anomalies among twenty listed categories. Manufacturer’s specifications require a minimum of ten inspections per second without a decrease in the quality of the produced parts. This problem is here addressed by using a classification system relying on a real-time machine vision. To fulfill both real time and quality constraints, three classification algorithms and a tree based classification method were compared. The first one, Hyperrectangle based, has been proved to be well adapted for real-time constraints. The second one is based on the Adaboost algorithm, and the third one, based on (SVM), has a better power of generalization. Finally, a decision tree allowing improving classification performances is presented.