A new multi-decision based on Bayesian decision tree algorithm for ship recognition

Abstract Ship recognition is a key topic for intelligent shipping in canal. A new multi-decision algorithm based on Bayesian decision tree proposed. The combine three Convolutional Neural Networks module - VGG, VGG19 and ResNet to get better classify result. quantization method adopt quantize the output of these network. construct proposed improve accurate tree. In experiment, implement various compared algorithms prove has performance.