图像处理与神经网络识别技术在船舶分类中的应用

应用图像处理和神经网络技术,提出一种基于静态照片对船舶进行分类的方法.首先通过图像处理技术对照片提取特征,然后将这些特征作为多层前向神经网络的输入,该神经网络用BP算法(反向传播算法)来进行,由该神经网络将照片中的船只分为大型船、中型船、小型船等3类.用真实的船的尺寸作实验,实验结果证明了该方法的有效性.另外,提出一种识别船舶类型的方法,用户可以通过GUI进行模拟实验.最后,讨论海上值班系统的研究现状.研究的目的是将图像处理技术集成到传统的船舶导航设备中.

Classification of ship by image processing and neural network

A method for classification of ship in image recorded by a stationary camera is presented. The classification of ship is mainly performed by using image processing. The dimension and parameters of the ship are extracted and calculated by using image processing techniques and then these parameters are given to the inputs of neural network, which classifies the ships into three categories: small, medium and large. A feed forward neural network trained with the back-propagation learning algorithm is used to classify the ships. The experimental results are provided by using actual data of ship, which demonstrate the effectiveness of the method. Moreover, a method is presented to recognize the type of ship and the Graphical User Interface (GUI) is provided, which allows the user to simulate the classification result. The present condition of marine watch system is also discussed.The objective of this study is to achieve the integration of the traditional navigation equipment with an image processing system.