Wooden Knot Detection Using ConvNet Transfer Learning

Rickard Norlander, Josef Grahn, Atsuto Maki

Abstract: This paper presents a method of localizing wooden knots in images of oak boards using deep convolutional networks (ConvNets). In particular, we show that transfer learning from generic images works effectively with a limited amount of available data when training a classifier for this highly specialized problem domain. We compare our method with a previous commercially developed technique based on kernel SVM with local feature descriptors. Our method is found to improve the detection performance significantly: \(F_1\) score \(0.750 \pm 0.018\) vs 0.695. Furthermore, we report some observations regarding the behavior of KL-divergence on the test set which is counter-intuitive in its relation to the accuracy of classification.