Title | ||
---|---|---|
Real-time flaw detection on a complex object: comparison of results using classification with a support vector machine, boosting, and hyperrectangle-based method |
Abstract | ||
---|---|---|
We present a classification work performed on industrial parts using artificial vision, a support vector machine (SVM), boosting, and a combination of classifiers. The object to be controlled is a coated heater used in television sets. Our project consists of detecting anomalies under manufacturer production, as well as in classifying the anomalies among 20 listed categories. Manufacturer specifications require a minimum of ten inspections per second without a decrease in the quality of the produced parts. This problem is addressed by using a classification system relying on real-time machine vision. To fulfill both real-time and quality constraints, three classification algorithms and a tree-based classification method are compared. The first one, hyperrectangle based, proves 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. (c) 2006 SPIE and IS&T. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1117/1.2179436 | JOURNAL OF ELECTRONIC IMAGING |
Keywords | Field | DocType |
classification system,real time,algorithms,feature extraction,machine vision,inspection,decision tree,neural networks,support vector machine,feature selection | Hyperrectangle,Decision tree,Machine vision,Feature selection,Computer science,Artificial intelligence,Computer vision,Pattern recognition,Support vector machine,Feature extraction,Boosting (machine learning),Statistical classification,Machine learning | Journal |
Volume | Issue | ISSN |
15 | 1 | 1017-9909 |
Citations | PageRank | References |
0 | 0.34 | 11 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Johel Mitéran | 1 | 47 | 5.52 |
Sebastien Bouillant | 2 | 0 | 0.68 |
Michel Paindavoine | 3 | 115 | 21.70 |
Fabrice Meriaudeau | 4 | 423 | 52.78 |
Julien Dubois | 5 | 146 | 18.76 |